From 729b2e91e510c0385f5326eb39ecf3bc0f969319 Mon Sep 17 00:00:00 2001 From: Sim Pi Agent Date: Mon, 19 Oct 2026 22:45:49 +0000 Subject: [PATCH 1/3] feat(library): Best Dust Alternatives in 2026 for AI Agent Workflows --- .../best-dust-alternatives-2026/index.mdx | 122 ++++++++++++++++++ .../best-dust-alternatives-2026/cover.jpg | Bin 0 -> 27683 bytes 2 files changed, 122 insertions(+) create mode 100644 apps/sim/content/library/best-dust-alternatives-2026/index.mdx create mode 100644 apps/sim/public/library/best-dust-alternatives-2026/cover.jpg diff --git a/apps/sim/content/library/best-dust-alternatives-2026/index.mdx b/apps/sim/content/library/best-dust-alternatives-2026/index.mdx new file mode 100644 index 00000000000..89ac0dba8cd --- /dev/null +++ b/apps/sim/content/library/best-dust-alternatives-2026/index.mdx @@ -0,0 +1,122 @@ +--- +slug: best-dust-alternatives-2026 +title: 'Best Dust Alternatives in 2026 for AI Agent Workflows' +seoTitle: 'Best Dust Alternatives for AI Agent Workflows' +description: 'Compare Dust alternatives for AI agent workflows: Sim, n8n, Gumloop, Relevance AI, Zapier Agents, and Glean on hosting and workflow depth.' +date: 2026-10-19 +updated: 2026-10-19 +authors: + - andrew +readingTime: 8 +tags: [AI Agents, Workflow Automation, AI Tools, Sim] +ogImage: /library/best-dust-alternatives-2026/cover.jpg +draft: false +faq: + - q: "Can Dust run multi-step automations?" + a: "Yes, within its agent model. Dust agents use tools that can take actions in third-party platforms, can call other agents, and can run on schedules or webhook triggers. The agent decides which tools to use for each request, so Dust is less suited to automations that must follow the same explicit sequence of steps every run." + - q: "Can Sim handle the knowledge Q&A we use Dust for?" + a: "Yes. Sim knowledge bases let agents retrieve relevant document passages, and you can use them inside workflows. If you need automatic knowledge-base updates, KB Live Sync starts on Max." + - q: "Which tools can we self-host?" + a: "Anyone can run Sim's Apache 2.0 core for free, subject to the enterprise exception at https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE. Enterprise features require an active Enterprise subscription for production use. n8n supports self-hosting under a source-available license at https://docs.n8n.io/n8n-community-license. Glean offers a Customer Hosted deployment in your GCP or AWS account that Glean still operates, as described at https://docs.glean.com/get-started/prepare/about-deployment. Dust's pricing page at https://dust.tt/home/pricing lists hosted plans with single-tenant deployment on Enterprise, though its source code is public under the MIT license at https://github.com/dust-tt/dust/blob/main/LICENSE. Gumloop offers hosted plans at https://www.gumloop.com/pricing; contact the vendor about deployment options. Relevance AI's docs at https://relevanceai.com/docs/sdk/authentication describe hosted regional deployments." + - q: "What does \"workflow depth\" mean here?" + a: "Workflow depth describes how much control you have over the steps an agent takes after receiving a request. For example, Sim lets you branch on conditions, repeat steps, run steps in parallel, and pause for human input." +--- + +## TL;DR + +- **Sim** fits Dust users who need [multi-step agent workflows](https://docs.sim.ai/introduction) with explicit branching, human review, and knowledge retrieval in one tool. +- **n8n** fits technical users who want [self-hosted automation](https://github.com/n8n-io/n8n) with visual workflows and custom code, under a source-available license. +- **Gumloop** fits teams that want agents that use connected tools and [run from schedules, app events, or webhooks](https://docs.gumloop.com/core-concepts/agent_triggers). +- **Relevance AI** fits enterprise teams that want an [AI workforce with agents and tools](https://relevanceai.com/pricing) rather than building each workflow from scratch. +- **Zapier Agents** fits users who already rely on Zapier and want agents that [act across 9,000+ apps](https://zapier.com/agents). +- **Glean** fits teams comparing enterprise search and knowledge assistants with Dust, rather than prioritizing workflow automation. + +## Why teams outgrow Dust for workflow automation + +Dust works well when you need agents that answer questions across company material. Its [Business plans](https://dust.tt/home/pricing) connect Slack, Notion, GitHub, Drive, and more than 20 other sources, and agents combine instructions, skills, knowledge, and tools. Dust also runs agents on [schedules and webhook triggers](https://docs.dust.tt/docs/user-documentation/agents/triggers), so its agents can do more than answer questions. + +The difference is how the steps are defined. In Dust, [the agent evaluates each request and picks a combination of tools](https://docs.dust.tt/docs/user-documentation/agents/tools) to use. Dust's tools documentation does not describe explicit branches, loops, or a step-by-step visual builder. That model suits open-ended requests, but recurring tasks that must follow the same steps every time, with controlled tool access at each step, are easier to build and audit in a workflow builder. Our guide to [AI agent workflow builders](https://www.sim.ai/library/ai-agent-workflow-builders-multi-step-tasks) explains why this distinction matters for multi-step tasks. + +The comparison below weighs pricing, hosting options, workflow depth, knowledge features, and integrations. Prices and product details are current as of October 2026. If Dust already handles your knowledge questions, focus on how each alternative defines workflow steps and controls access to external tools. + +## Comparison at a glance + +**Best overall: Sim** for custom agent workflows, while Dust provides the knowledge-assistant baseline. Listed prices are starting points, not comparable usage allowances. + +| Tool | Starting price | Hosting and self-hosting | Workflow depth | Knowledge features | Integrations | +|---|---|---|---|---|---| +| Sim | [Free; Pro $25/user/month](https://www.sim.ai/pricing) | [Apache 2.0 core](https://github.com/simstudioai/sim) can be self-hosted; [enterprise exception](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE) | Visual blocks for branching, loops, parallel runs, human review, and code | [Knowledge bases](https://docs.sim.ai/knowledgebase); KB Live Sync on Max | [273](https://www.sim.ai/integrations) | +| n8n | [€20/month billed annually](https://n8n.io/pricing/) | [Self-hosted options](https://github.com/n8n-io/n8n) under a [source-available license](https://docs.n8n.io/n8n-community-license) | Visual workflows with custom code | AI and integration nodes | Every integration is included in its [listed plans](https://n8n.io/pricing/) | +| Gumloop | [See current plans](https://www.gumloop.com/pricing) | Hosted; consult Gumloop for enterprise deployment options | Agents run from schedules, app events, and webhooks | Connected company data | Connected tools and an API | +| Relevance AI | [Custom Enterprise pricing](https://relevanceai.com/pricing) | [Hosted regional projects](https://relevanceai.com/docs/sdk/authentication) | Agents, tools, and Workforces | [RAG-powered knowledge](https://relevanceai.com/docs/get-started/core-concepts/knowledge) | [2,000+](https://relevanceai.com/pricing) | +| Zapier Agents | [See current plans](https://zapier.com/pricing) | Managed cloud | Agents act through connected apps | [Company knowledge](https://zapier.com/agents) | [9,000+ apps](https://zapier.com/agents) | +| Glean | Contact sales | [Glean Hosted or Customer Hosted](https://docs.glean.com/get-started/prepare/about-deployment) | [Agent orchestration](https://www.glean.com/ai-agents/agent-orchestration) | Enterprise search | [275+ connectors](https://www.glean.com/platform/connectors) | +| Dust | [Free and paid Business plans](https://dust.tt/home/pricing) | Hosted; single-tenant deployment on Enterprise | Agent tools, multi-agent workflows, and triggers | Connectors to 20+ data sources | Slack, Notion, GitHub, Drive, other sources, and MCP | + +### Sim + +**Best for** + +Sim fits you if Dust handles your company knowledge questions but you need to build multi-step agent workflows with explicit branching. The [Sim and Dust comparison](https://www.sim.ai/comparisons/dust) covers the two approaches side by side. + +**What it is** + +Sim, the open-source AI workspace, combines a visual workflow builder with [knowledge bases](https://docs.sim.ai/knowledgebase) that agents can search for relevant document passages. You connect blocks, configure their inputs, and review each step of a run in the [run logs](https://docs.sim.ai/execution/logging), where a trace shows every block with its timing, status, inputs, and outputs. + +**Pros** + +Sim gives you direct control over how an agent proceeds. [Agent](https://docs.sim.ai/workflows/blocks/agent), [Condition](https://docs.sim.ai/workflows/blocks/condition), and [Router](https://docs.sim.ai/workflows/blocks/router) blocks let you define different paths. [Loop](https://docs.sim.ai/workflows/blocks/loop) and [Parallel](https://docs.sim.ai/workflows/blocks/parallel) blocks handle repeated or concurrent work. A [Human in the Loop](https://docs.sim.ai/workflows/blocks/human-in-the-loop) block pauses a run for submitted input, and a downstream Condition can route on an approval field. A [Function](https://docs.sim.ai/workflows/blocks/function) block runs custom code. That structure makes a multi-step workflow easier to inspect than a single agent carrying a long set of instructions. For more design context, see [AI agent orchestration frameworks explained](https://www.sim.ai/library/ai-agent-orchestration-frameworks-explained). + +[Sim's Apache 2.0 core](https://github.com/simstudioai/sim) can be [self-hosted](https://docs.sim.ai/platform/self-hosting) with Docker Compose or Kubernetes, with [enterprise-licensed features excluded](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Its knowledge bases cover the retrieval use case you may already rely on Dust for, and Sim connects to [273 integrations](https://www.sim.ai/integrations). Sim can also [deploy workflows as an MCP server](https://docs.sim.ai/workflows/deployment/mcp), so MCP clients can call them as tools. + +**Cons** + +You have to design the workflow paths yourself, which takes more setup than a straightforward knowledge assistant. Enterprise features such as SSO, SCIM, audit logs, and access control use the [separate Sim Enterprise License](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE), which requires an active Sim Enterprise subscription for production use. + +**Pricing** + +Sim's [cloud plans](https://www.sim.ai/pricing) are Free, Pro at $25 per user per month, Max at $100 per user per month, and Enterprise at custom pricing. KB Live Sync starts on Max, while SSO requires Enterprise. Anyone can self-host [Sim's Apache 2.0 core](https://github.com/simstudioai/sim) for free, subject to the [enterprise exception](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Supported self-hosting is listed with Enterprise services on the pricing table, but local models through Ollama, vLLM, LM Studio, or LiteLLM work on any self-hosted Sim deployment. + +### n8n + +n8n fits technical teams that want to self-host automations and connect apps, even if building and maintaining workflows takes more work. Its [repository describes both self-hosted and cloud deployment](https://github.com/n8n-io/n8n), along with visual building and custom code. + +n8n's source code is public, but its [Sustainable Use License](https://github.com/n8n-io/n8n/blob/master/LICENSE.md) limits permitted use and distribution. n8n [describes its licenses as fair-code](https://docs.n8n.io/n8n-community-license) rather than open source. By comparison, [Sim's core uses Apache 2.0](https://github.com/simstudioai/sim), with a [separate license for enterprise code](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Our [Apache 2.0 versus fair-code guide](https://www.sim.ai/library/apache-2-0-vs-fair-code) explores the practical difference. + +For cloud use, n8n charges [by monthly workflow executions, regardless of complexity](https://n8n.io/pricing/). Its pricing page lists Starter at €20 per month and Pro at €50 per month, both billed annually; Business starts at €667 per month billed annually, and Enterprise pricing is custom. If you self-host, you also run the infrastructure. + +### Gumloop + +Gumloop fits teams that want a hosted platform for AI agents that work across their tools. Its [pricing page](https://www.gumloop.com/pricing) presents its hosted offering. [Agent triggers](https://docs.gumloop.com/core-concepts/agent_triggers) can run on a schedule, from an app event, or through a webhook, while its [API](https://docs.gumloop.com/api-reference/getting-started) can trigger automations programmatically. + +Gumloop's [pricing page](https://www.gumloop.com/pricing) provides its current hosted plans. Compare the included usage, connected tools, and enterprise deployment options against your expected run volume before choosing a plan. + +### Relevance AI + +Relevance AI fits enterprise teams that want specialist agents instead of building each workflow from scratch. Its [Enterprise plan](https://relevanceai.com/pricing) centers on agents, tools, Workforces, integrations, and governance features. + +Its [pricing page](https://relevanceai.com/pricing) lists an Enterprise plan at custom pricing, with 2,000+ integrations, unlimited agents and tools, SSO, RBAC, and audit logs. Agents can use [RAG-powered knowledge](https://relevanceai.com/docs/get-started/core-concepts/knowledge) to ground their responses. Relevance AI projects are deployed to a [US, Europe, or Australia region](https://relevanceai.com/docs/sdk/authentication). Ask sales for a current quote and verify the specific apps your agents need. + +### Zapier Agents + +Zapier Agents fits you if you already use Zapier and want AI agents to act through your existing app connections. Its main draw is access to [more than 9,000 apps](https://zapier.com/agents), and you can equip agents with company knowledge. If you need long, custom agent workflows, validate the required sequence with your own use case before choosing it. + +Zapier changes product packaging over time, so use its [current pricing page](https://zapier.com/pricing) to compare plans and limits. Focus on whether an agent can reliably complete your whole task and whether the connected apps expose the actions it needs. + +### Glean + +Glean fits teams whose primary need remains enterprise search and answers drawn from company knowledge, rather than custom multi-step automation. That makes it a closer alternative to Dust's knowledge-assistant use case than to a workflow builder. + +Glean lists [275+ connectors](https://www.glean.com/platform/connectors), enterprise search, and [agent orchestration](https://www.glean.com/ai-agents/agent-orchestration). Contact Glean for pricing and plan on a demo using your own knowledge sources. For data control, Glean offers a [Customer Hosted deployment](https://docs.glean.com/get-started/prepare/about-deployment) that runs in your own GCP or AWS environment, with Glean responsible for infrastructure and application management. + +## How to choose + +If you mainly need answers from company documents, Dust may still fit. Consider Glean if you want another knowledge-focused option, but expect to contact sales for pricing. + +For lightweight automation, choose Zapier Agents if you already use Zapier's app connections, or Gumloop if you want a hosted agent platform with triggers and schedules. If you need custom workflows that branch, loop, and involve multiple agents, Sim lets you combine those steps with [knowledge retrieval](https://docs.sim.ai/knowledgebase). That makes it a closer fit when Dust answers your questions but cannot easily carry out the work that follows. You can also compare broader licensing and deployment choices in our guide to [open-source AI agent platforms](https://www.sim.ai/library/open-source-ai-agent-platforms). + +Workflow depth and self-hosting may settle the choice. Compare Sim with n8n if you want to run workflows on your own infrastructure. [Sim's Apache 2.0 core](https://github.com/simstudioai/sim) can be self-hosted by anyone, with the [enterprise exception](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE), while n8n uses a source-available license. + +## Conclusion + +If Dust handles your company knowledge questions well, workflow depth should decide whether you add another tool or switch. Sim lets you build agents that branch, loop, and take actions across connected apps while still retrieving information from documents. If you need those workflows, use the [Sim vs Dust comparison](https://www.sim.ai/comparisons/dust) to assess which setup fits. diff --git a/apps/sim/public/library/best-dust-alternatives-2026/cover.jpg b/apps/sim/public/library/best-dust-alternatives-2026/cover.jpg new file mode 100644 index 0000000000000000000000000000000000000000..4f57fb2f263540c206f974ef9aa6ac323d8f818a GIT binary patch literal 27683 zcmeFXWmufevM4&ZL-61Z!GaAC2<}dB_uwwU-ED9k+}$O(1b24}?iL&Z9J1E;t-bC! z&)NI#d!KuMop)xQ?&-I?tgEZ4tNV5Fbp;>{fc@tK2M3FQ`1V0TMnXbH!9qoQ`(Tk^ z;$XggNeIXY@ZNqb)a2yUET5PdnLdf|@`|V`sM^^j{Q&~;{~E{-06IKm9&|Mn1UUc_ z9Rdm+;8pLqYy|i}mmA|LpL(3_yl@8}kn8-CILL*T07S zw<|FGMg-aa?NOroqT_`yX0(>Uq11rQA zY8@@&Zy7kg|2-5lV*53$NN7XxNSP_kT>ur;%JKk>gpTaSTlTSBh50dAs|1xRVW+TT z`Bm(k{N^%ghS|w>vN0Oz{~j8VKAtAA7LP)Df=qfk00dsVYVSE+d;&hLsGD6PRh^O+ z74|gG+B8jtx$(UJNCiX97%$_07YTa6aHcl7`X9o?ZmtB&mjcCv!K7EV*;D7R(XQ}3 zKmS`Kvwt>tAMg9$8uEWS{~rnb9|`<_A^~)tIOXt{xTG|PzraI;muzacXpQbIDOZ+qD;=>@!FAvE z4FgDMW-vcI!zkPp-F&ozz|KD#mSG}#7<*Xo(w8;yTyVkA2LPaYZ;f`4c}6kf8$LXx zC;I}(u%Xk`jjs7QRs#po5e@eXQ3HBL=dpDL1oXr%png6X?!KXgA{=yk1Rxtx?H;lG zVv*t-EjZn>FIsgYTys3RHIaDhu>XDp05?vX^85MU3FaDigBs>Wko=vbLJ-eHqbNVP zR8-DV;a|9_J!fEMbD*^otU|&T*FN5E06QRh{^0Qwsc-+vatMEQO?cNb z8bO3M?u9qjmu9HO!BUaUbmsXnOj~{@ROrQ4C^A;_Cf0lk*91Yv-EFC`ab@NVfZtwV zqB{SqFu99a6F;{v#r_0ICZm1b?K-VCt6cibb6N*GG%qfz;&^47u=lc7JQ8gxrDF`y zIDHIi+%TZU+U=9UxR2~`P-@(@jdCJ}^-?s;ODl8A-G4|7n_fM4wUm-S-|A;~PU3GC zSaoV27kHs=Ae)Xv{?+JfB7vlf-I5zwF0H7nc!zCW#B}f3nbD7RJMbZbjR3mg-v#8D zIibPBk~Ele!Ht#?vDJ3hMeZ2txzj&;-e*4bjvhMuw-2A7xFiMYoX{crz)MZ@96)cJ*bYE0>4q?9qrnRJ3%GD(Ue`nQ*Wgf$2`NE%)lB3_aCkzR;b=Y zn7Vxwd;F5hNtcq(R@vfG&9|2vq<=|>*qjJKU8q*Zqe|y9;r>)2*@KOv+-SXdTe;%? zip4ir?Q`(=pi5y7Gs%p+{J8WL2jxy0aoXd+_k9Y4KWb#bcBGFH{G)p-)5*zk!~a+t z^Cz8h9_eXC0%(V(MFv$|^rNqJcXX4Xe{!+oktNxkl|R+31J!Mbms4H1;D zttquUZ0y#O0;M{^NfkcKc_Vl98JxX83WpPL&YS*CjozJyWe2^C_L_(u0PaI&g1&Xc z`?72)Dd^Y~7+qcSN1616Bd|Pw&#Dp)Kk$1*;ZeGnw=eAJrNG z7I|zn*ojbZpM-WEvH=t+wNq7~F}RQ>v+b*H!q|{VJ}dfW!axX&MOy*<`_)NTkKin6 zRx~CBgn=v+6XM^Z#)9RMa)ENvXJihtzK~pD9|3%Pz5FVMq4jy!JiNV3I)6&Yxdd3m;=uj^MqteOa^A!+O6OFHPgd5 zyBtMfr(w!J#(kF@P246Ab|L{vFcpX6^XL};B;xm#{~Vm;^K`O0+(fTM{F_x}qXs}- zjdMy8(cDekJv{zRD|U%7x#HyC|NbuNmxzpcsm{5zTd{k;wknGT$_o5`UPy433*O{t zY0lmoy7kp{VyqD(&@#pODtz=2R6Zs;Fy{46nVTO85dT|Boco-^?ke}lgFhoO!bgXl zy}`KkS|Rxb$Bqa2qgSlBw3M5~xa9F(JA)|tt!^mc1=gWGeTKOeJv|U$ju;`oZH>(@ zzYc-kejh>$eKD&$+NOiIeq$6lRL* z^vZ{^wF(7Xn|V-MNOEyWw%Qz`9Cc=#P;HfW(VloBn5%Ybs(;*n-#c{Q5zR5t6?-fS zK-Vgq86vDQpCe;_im!dBx40AeAIw5PWGPUGI z%6mC|_LdNA@LCz7xJ$@;IkE77;R; zEy3(4;S1vX&3qVOjy>8eYt;+H5|?yrwi-Py!xAWJ@YB9d{(P)$vjOiOO>}bE*c^j9m_E&V`|-ewLOUuJPu&f;VQQ5XET- zD4V;-uR?i#)^lBDKU}0PV|!))i{HO0aKL47SSMEQ}ykPKK-6alE7Jo+35PzSz3204C#!aD_9z zC)!n}!^D!|3zWFfHKUEp&N8T3cdnflnSxLK74Vhg=TH)=%RzY4eFIq?DJ-g!Q(gs% zY>J6r{#umz_lD0D#*!Ni4{Y%k9NXLH$_nvlLk}%bxE~z9g{A(KGiyBpDlH|cm)2BT zd~J7j^~lS(<)m`{D%`j-&FJp>HNjgZelas3W1l3BTu)e!=zmVX$c_e-A&pv-1*hIj!aSSOD$d=*S3VTx8x9;{pc4(UIyLrqLNMs91AGYvw& zfXOr2io@Jae=1JLuJu^wy5v3NNfy#X?JQ4lP3vn-y7dWJH_oALeyTg9uiyV{QrIYY zqPHGPJw14GU1C`4+RdK1F!QT=>6pW~@9IW5t+-s(*=V9nqIp`SH;&MHzwK(Wu(EY! z&Qx@_$2iC*LrHUIxOLVHWqgE#Rr4v+t20{QKPUFjTNp2uje3O1Ys$0ckMDyj(8+%t z)v61+qsARTW=`&$jD#GJeq%osAwtrS)9+<{EIhA?NDOz(2+%`rZuj9}{3${kk(u&l zn#z|FR3|j*7`>g_iydaFw^@yTg>+a@V04$-=A|(Wa|}=@6ogyuu>-rR-0@S|rQkSz zlt#q6jWxqO)s&rFUH{jV0`@C|ibHJ{#0_zh>P)zbHVles=6i*7mAFU5;iEe~8gmLMy_PNUGmUu0QlM2F4>N0I>IsZhflODV#qq&XlW2xp>6H+r@ z3th(N1@)&^njk*38nSL>L@qmB)^%7sneDZW;jrjlX9#C)DGLClu z2xv%%w@lqz0SO5O06;@PLcsuF-?77?V_;%&VB_GDvH|tUm<7I2ijq^<`Lf1zz2(#3 z-?D5F@PJpqnM&}vC7JD)Vn)@yM)HhTKv$Y^O~NJ$bJpke{qeh|*7jRV0^Xe47+BNw zZ>O>rWm2;9embi;>H+$FuBiq&vShZd$~Sg1e(z!_CrfiF(&yQ=@ARf?*0F>=ejKuJj%u2P?n|IYE~cAPD_1w5ZhN(sY#g3R<&XA26Q9g|Y;GQyWKB^y zaCaMkIXOu+hQCUdO^WbqMYXb-7LmNL*xg=P;a0cR6kPTF*mc1ox3ruHG`7|9?j(nt zh_#X)iDraPXF=FpQw9T#Erc8)?e~@Ol3`Jpe!z?5&R#=>s62)|-z#7Sa_kR|6%`~q zieS=b)*VhR!^n}+5DEgV_AI33nck03A)&GV!V_}QH(-`^{jjw0JaF~=AM}Ff8?bpK zc^pnU^2!xrbA@X2e~VhsP}R;w*Y?CQ=vDtEN;s-2-K-p@?u3dfka$+fO10#E znrYFoQL#nRgG-d_GqZ2%b4N1KsFOtJngq|klPPDZIjek0dG!jgbj=5=u}-=(rniW7 zVELFS-1FaLy4?-r$60=(m)9V~uxfXnVAr#qzeL-Nh??R*ysGPbir#PK{WXn*FZv3g z{N<=QpIa10ll2sQlwivH)zL{xtXV~%sJu+{I>k9v)y*-P(UnCt1Q7GvPab5!Qej~{ z25`wto1OUrCw}C`NkXdh3gB)k!Z}d!cPG-<6!k271zi3fYWmWD*MFYD{`+A@um4Q* zSCs>(S}~<~(WmdzW|^29KT%0VqSakn^bdiC2Z4F|v5f!aRBh2;^jNDPbK>3l~TbRs%wBY<#sn!@WIz;`+uq zfHmsz)kt^Z>{QJ;M+Y6SoH&-VfE<`r=XCp^XT~9}I<$vSWnH~YFUs^ZkLD>rK*49+ zJ|^))uIOv;^U7REVR@vOK2;kOEZryLua}}gPn%~%Ia+sKIjfy}1|6z~qgbjLa8HIT9?zBBwOnTHM@}i#i3e z-Y?LVo9ADx)p(1b@94E|xyFoC#)Z4p=oPTB(Um|mt1u?93r0^a^0tZn6x)aaX-VLlsAeYW&^pj!|1JWAM zp^uJk;8sFErZm5140*5&7xpF9(~O8PlRB83JPyxWGq+p#{d-09&g%UJkQy&4!no@9 z6G!l@ic1w#Z$+=N19{OSrjK3Q$=#KvV*?SqQz8393F4)hkoev}6Dd;+_peBXB^<@t z+Q;#dQ-y=G{#I<`2oCE4I<;wdjXe^Y6jc}#FOR7$%T^DDeEksHX^9cisY=K6_A|@$ zxpUhL&ZQO)&&ofld<9gPz=|2MfhuE=Msey)*i9a$xF=-ife~=&YUT0 z8_+T97TR9{xR)l~EnLyA4N9?GiVX3)szauVw|R8dVofN4(aCI5$vDN}wG|73uOjof z^NkK%GlxXqQd^qGa$~jjWrI%(c>sP0D%z!G5Nr_?#w03Bs!QQyZpL33zr=OGfBZHC1NV=*k=?k(_c`fKzPkq@e>t}UtXR^kWWdvqtB zjHQ`cbCdSq8GZ|lAaf-O>*6J*Zf~kTd`}hf2=z9_19m%=(dL;%C>ExFutfiA#R>Hs6QHNlt zNa6CKIqoz$JpI))=hdloYgwlqGj}X4omdA!wHfjyXmXa)(SM*<98EM^#0l4fVWNK|&rT~6=2fuBAYGu)0b?ZI{>L zen+(+-ncDsps;rfS6mU=-!QyDk*02_t`@9m^24Rq1|&Qm@6k?c(e}rqd2E3V!5TO#Es5kxL_)u zECZIR5z+L5(V7kj2Ek!DLF- z7nzA-YU8s3_7kI8^?WDR0eS@m1?-P4eT`<_VzPC6@&7Q&$X4M=CFSFj%NsCCzevW= zXsqhlr}_Kk%~*=ukqnx&7KMSRW5O#9i?)Z!{eDwJe=~7WlgF$G8xu;2@0J}e$Ulah zt>f*|Q;JH)rc`x}mFLqtwrC5w^eSRZCND-^E~6U7a0pujrYnTqday?-2C8JqR{zoI=hkl_*##K{pg1ua zN6*8$@igo=>upw!Q#;G5#_1hIgVj!4#EE93ep%r}H_nN})rv4&ufo{EC8GB)4vajJ zjU0~4wMPB2Ihekbaux ziY8g7!zY~ABijN8JD1<4PMhBRu%|7lyQONv+LyOX6M5x}%QZCYjBlf=LD-vl3{88& zW`v5T`(Yin4f`JgtU%iALZsGI^0P%0(EvlBsC)^VI~P4yYmWvE4;Qnh>m^ELOv%7lkNl@ieT*_i}<5MpsQ#`*iaylaCq#^ z1eXVQddKoGRJ)-IL&mZY9AgYqchL%`LD3L!-Xi)1-iWBtk&A`L))2LL_?A!S8!=^z zd!_w7OR!q=fH_5H*_zu5JAZPzDhCUv%91Lzu@I4Ju(ovW;t$&1h>td$%y4?lGGi1u z;>nzTirw2;daLT5(`W|$gWX1LHTo@>y5HHj{;|M-k>6;7_{R2n<}{gAl@=-rVsiEe zu^xWG@Ok>lCxi9%Ro|(*m8pA*rKo-WV+N(CjvQ@8b({xU+1>D{P%P>=F9_oi^p|^f z%6W_^pf}6KB4g_;mT*cx4WL$eXzYYT{qLudS9`yC;^cw!7lR6$ZM`pDNx$~YbF)tH zpI`^gVm7IF(SI}i!BjWiCF!D55ugMG(gI~8%UneU9az-+Mm3b-13 z{&895@%cBO)6%|dp9;$YX10)=W4@YM0ud8wFlJFPYvTF z(-z5Zj3yd;;k_%%&N_h2grh5ZQ*|W7-lP4pUY!YjRad**VGfm)3~}9*A2~ef8-OIX z9IoQhIdS%nXPO&`%Dlf+R3&K$-X`@)^j)5@gxCV`*7p|Ap#NB!w4b}5(0Z=bNMZ$k z2Yi^s^QOUW-z}jr=}-KXRZDY2YIOj;Q5cP_(~C77pLR0E#EHv9j`UX#cR_Wcl=94y zU33OTgt>tZP1d^eqh%N5SpkTVWD?XuG%=}rnX-_bk9hho#-Mm{N=0?p3)Bzd2T8=D zf!+LnO|HW#dv!Tb^-a;wjrw^eTc1BB8tYrvAb+^XuE8)cZ7N_*Nes7}0K%2^CYyJr zX2NlednAs}vZs=HFpU3kpBY)+yCI)Dh2q0?qm>5C^n$C%eotQ3Pmib>04tEEkM|{e zy|=4*!&fb3>lyK*jkY}&pT$P+Pr4y0MI7i=d-2LZq#D_jvAR_x+TZKxesyr2{S`rk z)YP(^c%{fyRx^kjzb8Q{MK&HXjB?En*9p+32AlHcB}l~O=Y3qNF5^K0&Y)8iq$$l8 zu)0RGo|Pn%N>G&3%aGq8<9$}`KS-;$s?|>W&&ZsA%$G-xy<0T4{Bq?16 z6HFbRhpeG^>HoNX^)1@on`Bn_NzBJk7E+HP z2>*Z)&nJ@KJ7tdUfWqgGeXb5msOn~PMQN279VHCZ%q8CMMl4R&iHV=15Bt>L7`rQ)DYfl@V>+A4+0(vRd@ zTm2mbf|M9Ov9zph5XaD=f-fVynw5(MAN-t_V+MUwtd7MSu|;Wiq-5}65kGAYBx#KwxSD{A52IAB4gPPL^B@zXt6?}ZDFS;T%eYRrtG~pr57nq9X_C#q>mk} zRa06}VgK@((IR(RG|By$ud;qHB80*GxI!Jo@(82Y+Md|rWo_^!8IPGcXOLL_jfL8J z_t-BAP4#ofjNvyTf(1%wJZzlFHE}GXZY{Dba*kVa6XNGD+2+^Typ+1|?;W<(L+Ql| zGgKy@c>_8jrVm9_JH#5wE!aDsx2|&f+oR7fUIErB=-8^#Ev^}xuD6K=bR1|kD(Ii* zwZJLZT9i2dXlV4Xs7bE?6NIO(ZAP4uUWn*!;kn7&oLLeN;YXRSvA2IYyBKDSf#W*G z{SBjRL06T5%6{VG6OznTA$R9Cxy418ar&g9fZ6VOU|%bCb7p%HHQ|F&bbD?qmXAjn zH~wpQ=_vnFwqbFuJu-#@t{R6tWW>YXJV+6~VUeL?{hU8sr?S7|Fb|No|DnHuO%v$N9 z44!PeG~2^aeI*6R#wsAPo8){!w!SJ{IHWPGdE#g~lGI=T1|?vp)J0}3q&27W@+MS_ zaR+x;?0hN~!TP2q_yRj*a7pjKCngAt8DmqwV;S?Hi?U9%3;GV4S=qHOdU9wzTW8=^ zDMcRCPYH@8A5-kv!pfuX9B4Vlc?)It>R$mmSB2f+pyv4=JhHfEEy5`Ix6N4D>O9>K z_*zc8R>q_95VH=y!HNav#nZ2XNPA1;#wuxPU`iQdU>psB5gu{R*Le$zlIr<8Ym*O7 zV$IF@fGLZ2iQ7I9#W}?D&7+RG%fDhKMQD*7Gd1K~Olw&5%vmox`{$PtuVGYBP`=dS zlLp2e8hid4VgOTF>O%@|uuw#0Tn$)iu-+T;K$Q2!C_+}iHfKV7qB@H-q%_x3naUdm z-s4QzYcmLeiglN?Fut0+Wk0m{wQUuC>ZRJ zCr2U{cL*52B%q-;dHnc zVm9#5bL{L>uc_b>>k$#1Z?kRP=pDzMN=h0L*nxSFt^0|Hgf9fZfzHUJwX;+j+U4u!;K z7-j&LUnw5<>s|WuUlN8D6X-1-W*8n5gDn~qmX~Yd*^6hzzMmwC2@}Q*85*6Se)xXC z{$e0X{Ckc5+4}RIjYT8LyF$G2vA=E9>Cy=wg@ZO|#`4*ERPi%Y*$a)L{t%ckq_`r6 zbMIQZpjpCE52le55PAJ4E?M(408UW+*`GHrBS>#mp+H|BeR(Npt$@-5*^Xap)SqD8 zVV{ILsfeBnm@4`q2d(lB7=dGAaoy>S2iU7D!CSe%5UB}IE=Tq>zeoIu`rb0E@;A>} z-WkEN_a@r{hlQ85*Yte6b126M<;i0zBgt;w$dQu>j%RC0uH6-W~9dh84)DK)Op zQiKes5-rDBi$UkQxvl9ZmRk<8i_=HNqoFWdE^1VZ1iq7zDGx@mR1Gh{SJ0>z$p5m$ z!X}0ntN1X~|H4M1N%lUxLRlF!e80H6ZG52WY5uZW+4EZpp?GzYhaZ6{bMmRJr97l_ zJfiiFke$7rl1QA74GxZQV0XRyELHi7F!yBxC|8+`L6@CCX*78wX8C`~_GFQP4^Pnm zAu-t*8-W$>%^qcOTj4Q8fif2$JG90NB3R< z^RV5}q`xTM+s5DWJn$P${IeJirN*!9K)6G*U)+1kGVe{4sK0Hr!EYPw|3Z|>Y4A?5 zKKsTd#w8y~OJzMrnp^YAN>Q_&e03RqSO>WoGW^roGWL*rHpE|kUuB){qwufBW01!Z zV*!C8jTjmIi-}C>j_y~Q+muvQ@T`Oc7^ypmDD@uilc;5}VtFQQ1dAyzVmRiBzAG&1KW zIpg2De6mr_;~1vf)t9i9jYAUik?o(O7}@E$W7f3?OT)txiV8B+jZI#lzyhZAtoiUc z!{N1~S_bL@ORc&+Y#8NMf6|c|*}=PJu#HUvYUyOw??a{i$;n16KUfH+G+W-`8?}OO zn+Zer&WN{b{^YC1vJ|VwCw$n8aCHn<-Zu2NS;tR&&!3UgF2?%(W@P`RQ+va1u$9%B zv_&bYdcY;v8F!#eFj_hX&qI$<7f0(u6e=y7<3eT}-=v6&sHni5bPa{X{D5UsEoibG zUBx5*%R-hG5{RB*{KFM>N;;Ck_ewuf%zcz-KD))Mw*tl^|Gi76Q?{GzeM*fqB`d3X zz=oAR=)L61S}IGq5${>-xW{$7x5VcPr2W6OeEY3C?Ip|mJF&fXKieWfOm&s0D}8Ob zP`#twF+RVW>Q6r${-IuPiIm$V{NbNSjOQM^9y{Ivdb^Pd=lcd#_ZfnA)Mkyug^dCm z|MJ(46ib*S6el1rzulx$#Ln?g0a-)2{bqqklox}*89{14gVk;NEMq;GY$XKV0)=nT zO%D2$etLUo>~n3GCQs8kQw(WQ|lREHyzkn`fU1r@2o&m;R{F+u?z|oVxZK4k^}5!#gPvyVYhRGZ9-(Ul$8WS$x6AUvBJ1={Bs(W z!gq-N4;ya`G*PShe~5fSn?g*VE+o*MJ1Mbx7os;mVy(e!@5Ns`%>7_-)Q711G4R9V zv*$2_VEmarztr;gYby z!`om4jS37NyvnY;sd=%Jx?Bhdj)i#8&MjiJb9rL-;Jqp zG7tw|=8g;_g>6*gGO zGV>hmL1DE1G}g4e7e~6f&pW*D?Dgo3S4Zr`*@zr11^n@maHuo&H0QB};&YuO)2t#Z z`-(La1I1X9D*tVQ?T1wPsKqo|DXme-suK&9dWQ2wmjs|>Yn~xD$ybjy?RfV=ryS9ySTwXjLeaE=%a~_Lz%{A&QC$S(8HsfWa zd~UMrk~OsIT4c$OE~J*muG`?@y5WNz%%1cEp?k-ZcA0Fqbt)yi@K69 z0({MfkVV8CLiMuj^jn$crVaz7%8%+McBnx9Ybawl?fwcu}lu5lvDDN=>VdFZLByar;#=S z(ODcvcpfv$<0zdua5jg%%>6|zOVwxL3u65baS9^2SdOmy6yZgnPj!FRj$u}Gg2rDY z_v6Y922x7${2^NTKT1sXt{ma0*nbKhpo|$DqL{atK0w1tyVr&EXKxTK#u3Esf6?<5 z5RsW0y}=qnoM40VH{SqOWty9K2jj+Ta7njlNf^iXSj!5kQIT$Y@yNq!9W{PK*2s|K z4WsE=KA0AX0w&+zzK}#RN4z3+xtr)jQaCCyop{d3DN=wcDhKjMXhIk0PQ&DAQ9aBu+rvf8_{W|56ceV);DyTKjXy z)%{MP3L|myzWd_v@Q9iP*4ou#is?wZ1$)snSKZpk0-1%#o7uUmj|Y0CZKqfWKdiCDTqw||8sG5+Y4l8FHOgS%%yiEH1tqH2q zTIaZ0!{wkj!nOUkHT+z5-K9y+>GH`RrYqTrJX9mP-&X8L%ar1%875u?U4QStPbfft zE!Ms9N+|+bBbqGEn*z%8w6u`n@JKAQ)rfgHU2_H_98LDXXd{% zK0!+j#Tm_a;*Bx&xQ(RDjNIBIbv-U-Um5Okjq z=S>$Xgy$%$b)CKf%2B`zI^{bXGfW_H-QaogB-L%9;LuzTnX z+EoBqgB=(5xJJK)O)tjfOE2B)Or<+)-rn3)`USlLL}jSsvd3Qm{Km6F(0EZu><@bE zj7A&3eLT^I>U|T&Cwea5*+=vpWCpKyIgL^B%SsHXag?fjuR0G>&@5e0Jez?*g8dXV z36NNr(O62hQW~OH&hsi61=dpMQ2*@L2uv21cEb}VjCK^zf&fP`bsdwO{op*Mfd#=ikN^`0s!#*o7H4@7pc z*+3aF;{qp~92v@yf{ol#>Jl9f1B{j?2~%P&A2_m~#nsB%+|syee=P7+ie-)Xf>Cionu&^C82qL3ZTy&Gu6y`? zznt~sL(+7}C&5D(MD_Kehz!-1H60GT{I$rkoytz<@Zy}q??GHVPVS4!AhkCqHkb8w zaZc_X01^Tc5*i*J5dj+F?ZzD7?cN*!9r_&x8H)lYxuAjl+qp0dDXXHAvR@p9kfBj* zd`@oN6qfK8egC}fAJfbNj$3S$cD^bBFU8qCgf4fk(ryPcb*h_u@%fQ)i2q~Gb zD8OO<@%%aH1K!>wx6os`EDyh$JlfoB%(HsQyhyC>fB=*o)6h#WH@kfU%u+{C$qtko zs6xGX7s@7Vo?C1xiH^!|`H@u{YYzwZdiO-qg?w4Y8Jx%$D}yc2Ou2}7QHcM08cK;W z)R~pp;5xEqQe@ro6Wl=+yun&jA1c%J+li7iIdr@XR>Qfa!#pSEoh2?$Q(+Cf)DrA% z^~mJVc4Opy#AW}ipbR$Fx}=`*gn1Pr1>at1@uMJc43!#Zhi}6S$e`nT+#H-sk4Z6+sax9Onl}J_pO5Uno{gFOEIdv%0 zW911Zug0itY^Nr3YVME4EeFPOQpc=JS|}bp<~VcGt()_A_VTgx=hTa#^;^t<-LeW& zK|~D7b-uTY0U{aby20{<_V|$5S7pj&gwdSvL7)I_2+LiDgDvJPSY=2!33kfLppkVU zgysXtc9trZ)&WXLjdwg_!|E>@qzYj|qi~t6vLDPY4oE~!7@WWQHu{-O&^6(Q<{1%& zZx_hE0(>MqjX=U?ktC6GMZhb5X*PU_%P97YTxM^&h4NQ`d6h6t6#RmdeFK4OaWFNX zShQ_}tZaA>`Xzy+c#8#lCZFmT^gan1PHis+RI;O0b;fLt+=T`vP8!VJJ zSZu24Go#N8qh@gZpXQxIyYI^qYDp!5-O{?Z-x&=}o#9m{EG;jmz0nyRis84B=96I` zRi|-ylq^6xa&!9dKtBv8%6<-7O-|*^_{~pl`7zYAUF3$|gXjU4Cye!6Q zCAi1_vvFoWUd@=+O?QaUj00tuZk4SjPPb;KO2%^3=5l0IceKOjiGGj2^X`U;=TV5< z`D4_yrJVVmcajMZYMapVvxxq0l~;foLU;4>6cJjTF&}MnMDzhYe5l;QuaqY_rLBPB zWf|-Q)Kj*E(02ucjO80T73%4x9a-C204Q1$T{wC108%&S_A}I@B$Lg0V3QD9tcPZo z?F44z-OO(v@1PXz0n%lVqTN-7kYWoreG^jFD?t7jYcnyFA9h95FzX0hBYz{SK2OBL ze~rEQUYf`+%8#%A`;#d>MhpTVqi{7b+^5u{kAIHch|sC`X7f{s?&V!qk*ZQn!Yauf zV;-TIPSj6&tXF{YTqq+wq`-#}52yPmRpxFR2=0l0zz0n$s|nX0{n)-m()=`8N1)rK zO8Zh$G9sp4F-W0)_*`_D^}R1P{|Batkd0D?c>p~?85BrzQ!_38Ug9J#!;*k9HYNSw zd&GX;cdw_$AR9Cj$BJF zHw6j&m9Ayl$~e+*pL>uZpMh@f=|tU%DZ9F8qQO%xkZm;V61w7{I7anZcVeS8TyXY( zn&hUN`dEXlyOnp3rk#xs^Z!uT*f!WIr$F(|mmRT(Qdn{dCUGGzCK5DkE`Fj^#)$|= z%Yhx~oAE=GrcXcHnsQN<19GKFw4EUG_h4&oJ8~vd7Otx?eth?^&{W_R>0iBis*>T+!cTT6O> z+m}r0599lG?G5Bj>-i+O*og0}P3-8DJ*=ll_Yd^yn6$mOcKq_b(G5Glv+RzUr6<&n z&u#taGxbkaSRq#eBYd!YIl=wi1+9TvQ_$W&t|wM>zv>im;5+7ov+q*X;+R88pE%kl zMaZ>eDph7!(@e9;- zK$vQ{6P-d#dq{vnHxSAl+g}iKwg)_cJ6H|b#iz{JO9^OGt~w{doQP;+eKQP>0tZJb z2`8lUH3XM(H{7#RTZUNuYk9PKBesz)Gx4So=6hTO=mA+x7HW4O7MkF=6gs*jlg|Kb z3c(QA?*0;zUxf_4t8q4RN~yWKQHtsws8eF2?2>rDVrHwXId-`ux@=%GLZ4A?vywV! zx5+iQPfN^J!CHJ&XWU`Mic7%j?IXS#S+h$De_o@V{lmPGS3sW6ZwoOBdoGEePGAS0 z3u|7_6pJQL@oTBn9mj@@2$Ju#kukq|$XZs?z7d-WHxSqls{xE?cKO_Lr&+>OKMeg! z0rxfON=zmSo?st*EhN2|nyos=cMhWH5s8z$TuT(-;PDTmJf$vlUA6kk0Te%!_>NL7 z(U~%IQdSJnkQRfOm=h59VF+^L!>?Tm3Y5sgUgdO3Iid1_Vc}ojBMUt2CWc*hPT*J? zBzo;wt$|izsNS0;dh5X6OnfO9^a=BLjr$ev<-~9q8AiwblP5<9)aK0fquHt=hVTH5 zUG|-RKinMAV)`xEBF73N{@HnINv&N1zez6E-fF={YEI#koE%nlX`D0rQ3n-ICB~bR zNMa@R5-QI7fiDLHu<9k`ocBcvZ_^7S3GSxEPaNNFdg*@CAjLpd0R9nysjOlAQBqAf zSFgExNa9^{JGXZvO0Pv%-4%fq76WYs&p<#l_(`);lAQ$UGr*N%hlXX{vRhrBPYRk} zYH`Xa82rdNuMpB#Sa0)#OMK9FxDmop?3^KTe?=ioO1eAWRKFT_M=gN4@f8pzTB44H z>-tf1+g{g~UC{h0#>gQ8LgH+s1QwfO#Y#<)7DDfsU3Ka?5l8F|K4R9k`E6wOxjr;W*CyyP#To;l!Es5_#m3wc~)^UJSPo-6F`GA*&;z!Dlui(CaPoW$RA z*gp?8R3dm+vkLQmg6Z+zVW=eRNE*Q-%hT%8visi4!g*ZOS~uM725wSnOOtZjwD_0Y z=c}RxBtQb|*BXdx*#DXfLQl5iBfe4&(pCItD}hXtMe*t#8?ZaVoUBj?E^3l)>s0-? z>!+5nk&|3W>K$<85WVjYf|z2iJMe|-dsMR@S@{Y^!3m2{<#}g?WI+F6&OGa(%CCuO zOM|q~xzzBn8Oh{#>_6M6I=3{1Ds%UcRykE;%C(FFkC?_+H>$nZZfB=*LTR~O77C`+ zS2@?qZ3xbl$#UD9)W_py``%lVU)EpY$b3BO6kgr&v0NznDvW7!Y|F8T?TL1FXnzgwe{!?-F}j=AgYL zn5{Kfd{mjcj+iOSLkd>16KBD5i**ro$K%oC`*<<(7L#0}#RlOXGMMQ}W4?P-H{Snl z?RM!**e>V2IWi+DSwP8(AOy+>2tv^+nk4{m6g*I4jdamsxwiFR0R|05xPkm--V{#| zE6HWjYh3Q;JWBd7Llx0vlSe4h(tSMz$(0XQNvzptJRytbR>OVjHsn$DJPclNO2%)7 za`xvL;zL!hc02swQSgUJ53#J9VjR_|T@_H!V8e0u#Z!M930j*a5}_w124b9C%W~9v zrvP_O*mei+hiv$sULE(HMZz~9jsz71YOe%F3F{{0)wbQ7PP~g|FBhRNT!Rk3a3ppk z-q5dv{gkg*UYsVlZ@GKb89Miullyy>{-OfKTr)Qy@z@Nm(OHXYGZkj2<(Z-<%GDj= zAxU!f@L!%heK=AF%e$^TDjNzChCjj?nWZf*1Z>`cT=_^`=TRwP<^mukp^Y1=r#6bj z68s7^(9#2s*tvv$j4~j8mtgmel5<@wvOe7Dskx3QJJgyDKlrhkuuAODum5OzTE+Tt z1`I2%SYBiR3+i>`hMMEZb<$*y&n{`OvZ8YV$#>he2=GNEhC-h-RU!LOyxeR?@A#~@ zvHXsHS_tNkeFeCCeT2n|mYVPIZ8%lXNgj;-#(j<7KR|l*6$WjZNf$LX`2Li}IiUdCk z>(xqQ+kGplZV|uT?qU8=6u#=b6jILT;i+Kzq1_v@k9LL#hJq~#9;By zI$RHZ?*9x@`Z(gzFX$&%yhk%a1RJDYF8{b18?z;-gP~b#aVA+}-6A+UwJ~q<-2*XU zCHT-gK)D*EE4AG+z6(X%0`~vH>czk>{&TV0FZ2sE=iqDlm8`;OCZ&KT)~nqU?ENYm zMXa8FDG4>JNRBAKFKux|;kkSH!4ORu98V3PBn|SQ41q5ZcD&7==UeRVxF;hEBu&lk z>CbOwGM=i|P;tK!3?iT`^79T^x}Dl!yHjmTjxoQ1ZOqZ9H~8Uq%~jGwMvpx+HC@wq z9R3eNbl<;-KOgsy488)|U5y?{?n;37lv6W}p#M?VcZN05b?rt#dZ?j;v4f#jjP6#@{;coV2*sFrHVW+ z@TcTm1JHiiU)6G#)M1}uH<#{w%83_Q)~2|d!ts1c`44~$lv;5CWRcaW>Ew6Up3{N3 z4)UpOdxfmAXeJtQ)mgtamq}`OiiAc^+MGA4JyZ;$Nden#ypt-=P+zp=8!|qL5KsGU z%ZA!APqj8v3Pp^@xATQgCaSVY90vV-(<_7nc!E9}?(rplXLsf_Csy1Cc!yIyMci)Y zdUiia3>crxQT(CUhuNcurZQhQ_Z3m|FLeqo-|-0|(}D#ZoTGE)V+>-|+K^lqh=_uC zS-ZxlWd$6Qa?t>_>cpcm7tILi_V=tUtA%{lyV7!cDM5$AL$-6l4zZ;BgWQgaRkOTI z`=vksyPckoP7x3>=2x_|2(_C_;p}>+Y5dQN7Vvp&7oUpnc%rK=O(7tJcgYPe@Mc*; zec9nECQo>XGd908-<34rEwU&QUcKx}`QELpIIKG)9k_mZY>9m4eKN7J~g zXDo)#RZ;?-mn2@|PY(@J#%L4hn6Z@#<@|=!DqX%1o@8tWdxOmXHHRt7kEB?NsfB9;cI{TT!i8!Irh2$djpYnZo$XU3=GCmRLX^Fs(Q9;=w@Ra23V{ljVK|tP zofzSqez~UquEQ&4D`GJD7s({T2I%6~z*am-n5fF%brhjF7G-{@r+g5u&aUbook zKu9mV=^OFn>4V|THIYt;F_4x>>k1Qn!o>NdB!OFE(-chQMqEp}iX#~X3^M$BltxG0 zaLFv-&1)bgNGXu3%23VFherw#uX++9{hlP;MoKG4?RTOjZ9l=%ZD&YwvAZCuP0u{V z>ts^Ti8ZXJzj24fD2#xG3c-4gZ_`Ra1WC7z<6Gd?%X2J#@>IeQZ#`AvdFsQ2JPu&I zrB=DYxN14+5DQg^$SAIM!y~_}rGg8A9>!R1+1nGvx3!CS;bYi13GXp$$Ub)iX45v1 z{XRRwKiui+{R607#};WM zCL}YEKSv_RWwaslNLQnTe^}khmrB(JZk-G12#h(>sE&kBCQq~h_E{r+X1UZ~Ii$J3 zF4I?7l?(iCl1G-W<`n)rIg{J#I8a~ac8WQ?YsQ0%IG?~ea{Ok!6tI8M(GFL79`XCW z)Tj4h`?N_3kr9?O2wy7p*E0gxT{n|h@U*H2RvA)#K6NF|sqBI6MMsS!LiN(zln>$V z2Jp<-HXog3G`#Ascc|Jz8V z{uQnuCls_zDn|e>(w!-)I)kktL_2C4vx9Q7|3 z&J9nvP_|}!_3`8*G4tU*+DV}0Jlg%F;lE8H_?Uq%LXv7dQC&tc~IHcQ^#-g%_pJD@FLz(T_Mz)IH>0-D$7r~WZaaCkWbfnF-b zV9NdebD+PDR>%N9PtHKENb9Zc>si89@r7DjjL54wCA{B~w@k#(cj>;?-HftokAa?z5m=kt{zXa~oHxXFf)Sfg8*=uZ>k^b2>X!|MJ3 zY!q1DYvvx58jQQIQV|~Omv-C6?S=0Rt*2+C>Sje&xgcL!>MmzmL(Sy^qbWdw{35A**Zt zUuD;L>ro28szs!xbwmo|d*oZ_#s{wnub!`4A^g*djp!VlyP**?YhVjCXvRg&&ggU9 z+cX*rI`HU(u$sti@%0(+=c z`PTjgwz%j>GGR8A%Aama&Ip37b&^4q{Q6!4?rr3h#qwme%m!Yuw(>o zg;7p6zkbq#bt&G19BV_4q@FR3o44l_E^{`Ji)F~Jn+b|)gA=<|A~XzPi`G?Q&=f&U z4zo-4UDLxN56@HmBl}P1Hq$tyEZGIz z$f^@W?b#8`;bL9Ldk$)$!yS1Ct%IygLERw(tNRuX2SW>u>h>Jr(!{m1J&6Ia%>85{ zFNU^xs$UbRONP$zKCF&nI1{NZ^uL&?zmtRAiJy4$CIh#LsIBDZBV{^+HmW}W19;3D z%ct-&+$yShDp=v9f!ftZB^G(w!r`l|#lR=Ud(y8&2S#NSs+1Vl&4j7TMyM)j9;<*1 z8kb)i!xHG~Z_et93zOaer&q9ay}lh#rbHpHL~Wc!FrXyTct$kBb2q+4XK>tC;`ufD`EbSU|Mn5IA@`XV^bK}*_i2WtSZHi5-l?4U z^9rRK%Wo9V;t)KXQk_1B)KB{E;r6{p=LJ+f7s~|C&v9ewy~A$zMOjskLm@|Cfb=8r>cLC1?5Z zjTpmNsfSchooPahqwqJf22T(RD%3Qzw;!tx6hSA^QN-$24tljZ1|9JIMWO z1uj^NeV+oG*I8?wqVu&HhK#G49`#jqxd4anGZ^bvNyjw#L*>e@d}B@0OQ!T0AaelL zJc!hE12erS)^stNqh!^3O+xeJoG}vH6fKL5*OVeHD<<Q0hL!NA;9{IXgYSmqcrJ5BTWD>!6{=`|?il`~9%HY9`=M-iZ z?ZnpsmpxY>wT{-nOFhhjp6g==%LXC;DK;8K?%+yde>n}-NP~&sMs!S{TZ?g9+o4Wb zX5{k*m+E>fD5p1VGBl^1>0O68^=;mg$m3J{jV^Th>7@=VOP|$M_SChN02O{>g8} zyOIkX;FVuuG~pm<^CU=%z!S^3V>I&h9ndRXc(`W;P9Ne}p5mWuaiVAhefv>-k^G#yY@y#@ zD}2RADw`s`5q9qrr*28t=;5~M+_*$%B}3PNqAt2LSje%Kblc-T_@ykcHs2kw{rtnp z$VW?CKfC;)*IWjzH@uVQ7)?Om`Mo{~edP9^H7nc?m4uZ()?a?dQ=x00^youdDRkE&fQ*(RZ5Il;vA zq@p~|df`6+BV{|nv?*!c7ykJUgxUTmvfr76iFF7kJ?|6VYeZe-@CDqWlV}#A^{{`; zE$vghna`Y%NoEIPyw)8TY|tz*?f_lWu;^|2=I|7aD*a&nSsu}v5;$WfTw0R$8n)SA zlkV5CNz808kobJR%$}>1SkX&QL}L4IcRsmt=LMa96cRbqDPHvI%j2KT!EHg-)VIFS z4cFiJ&U#68>k$9?k#}l8*n@5l|ClgCb|TMSksdrfw*3R({~r$)Ox$7A{oNS6w}^w; zPVyJ$qn&HlV%Ig-{nts4{j(PAzsWC%{xi};;#8`h!ybyasjaYfZH)11*-~LtB&q)~ zb(uHtYf($?rkV7zj^9ss4D0(wcIy)Ut$sLLK1#(P6znQRa@=Mt*}>=m)#VmBiph5e zhtjtBrS5_RaTv;jju%SU?A=N#L(TV7N^!OJtMh}rgiZbYWo@AJyysVLldmjMHaI~n z>Od8RlRII@iy2uYbfcK#@&!T{5>%^60II4ms?8pDM!OnFd+ql0rd9F%i|yxz3468O zSP7GAvR^b!kt0cd*?lT=ripf|@Jzh6h;z75k#Sj8_)D}I!YI_Mq-GrnaIX`O?Y`K* z`tMfkpk2LRF(K7Pa*0$HXW!WP9Y5Vx#hJIj{{%jLuFyn!od#zR5s3iOY?ooX)Mm?Vbz%-Dp#kOA4UT70PV+9U z^Dl5}jF>pyg!J}o<2@TR9JQ8a5S6G(UhF1KwzUK6jK|CuzLpB0?9bHu(F`S^_JH&V z;4C9zd?>GKWLf;H>Vntl(8X7ru&cZK2k@vf{i`I-7hDzzDS7?++~@K>S5T}bItPZ< zzmNU8i=#e97|WT-aJw!;<@Ws5enI~LQ2!omzbDB$_l75!)9-As%`~l20i(x?Z1`5Q zfl>D0OMX>NG!Dh0fh;E}8bfzu(_PB^2J&7E>+cmSECC+iiiTn!z+J9{rQ?))h#vXj zq~HJDI(~Wy1|Op}0;pX@fmKDeK5>3(2EO(Z9J9=P*q=YfZKw1Gqu- zR`>pPu4IY2m_hXh?+mQGJ-zOS$@1cU!5UVA(LPQ+aiXZt=&<_(&{Vf$nbmq)4Iz$x z@cE6(stCSqYn^4qW&~VPq+{?uYsRV`j?}8Oium3v?{NW4R-2``ozE$;}(9Cr?!HIzm4kxnDa2CRf z>+!h62^a6nmM#RD!$@ecCUmtPK%0EW7ffKo$u`1bm8W(b%^&zW|G%g6gr9pDFXP#~ z(7oa7D~L8CU##2D!+*BM*qY#F8ox^uV2b9Fd~>6uTBlILh)XK-SsfiaMLnLf%*T6@ zk1ckBRLtkdeV0t11U(SgV75KE5vrhPp--1haB=f?xqT`5mIC^7~l%U3=5 z^O+fbc1qK-ZV9H8wKcCwtJ-*c=-5a*gZ(tT5hm-v+wkL3gS1dO6qi`6V>l5Z0L+gI zn^h3BORz9)4bbI)wFIWAkv@)yVOh-H7o#L77JJ_&e_yGK?8YBJJt-5MYFM?Ku*9(K z9pHkrN^znR~0 zdKdS^Kpo0^rm~Wu&jD zh#2Q0MdVFqxI2>AiAUElYlrWqz|>^PYO4Oqw5QbuL!6B9c)RehLRlly3KAPX0Kahr zISIa+!8>WOzSPE4Z_5|Y1XyG^eCw+c0IPBR@42oLzkb+=nz-1yH@;wh1$^fK*(0cB zZy084W4T3Kc$ya{DpT}A%h%oZ#SG~7*rTX-X8gPgJjhUb{7ZQpr5-qTmIO++<73Ap zb`;*%60^~w=Y&aM>g!f-dyxS&+StT5YkiC>cP)SKEc_<08=SeHJu-0}7;e`8h z>Uda`e|heZbkwBSB{I{)(|Cp|%*IiG_L2nl(a4#66Ow1k8!=V)*o;iXG%N(BpHR!Z z5=WtRRuLqT#BgAuZeSeQ)<}XXy_>IkUVpxO}+%vuf11dQ-p3k@S2S8SO6Jm!Vxow)AT`*5qo! zC`ctVrs!(z`nnG+vW{NH$2T)(x&Cr}RIrhxs%1|4iX6*$7oGJgH=W5wIE*J2tY@K*zK%8DIJa}cvg)#kk2vnWQ_Ro(uP3CjxoQ%IEZVkfu`x%63$k)Lub_`l#z2K%ulwt+<@mB=WT5<6t8 z@_PJxI0mpUJWR_wit@9`CcuN)EgiA#em2@NK#w|$4PgbfiPm^5l7Nz4V z?(iYbCT7GW*&Me%mfFWW^UbT%YvbuM-YGPc-AtREibZ!O`XE)tKxK4|K?SxRsO~|2-%yfma)x#<83@W?+i)HH#rbu z;@#p&Mw%Z%*ui`@AGbQ?kku6A%^fMjK<~6L%H!9n$PSweRe+Cd7f}dcIHq_ zbAy3?+BZV?fVPDyFP3-x|B8fxKU4!7&f?fBu8OW9%$QS;P;lj}K5{0loTa-OqdD~b zC4!hG>WZHELSQ%p;ypQVl93855cmW55ma#UQi4Qu+tI4UVQ%4pl$`lHe|i%0GF z%L_02NBY%GyUA|i;pu>%v+WnXM(|iJ*RB3%d=cDK1ZNn_mVM&7LtziTNUX;__ zU;8SE=XO`ikaDq((r8_|b=#{1#PrnLneC|O$O}=9ZnDLQ<3+c(&Pgi=+tmt3MeG^6 zK`;Q(@;B_qK*ys~sRt24|5z^70DXm>P8)H%&m;uM&|j3VEV%G)Kh%EbN+HNu;%-%U zp`$bs6C-)Z3!3|Out(-24Z3&BesTxpdS*0aW4F~>;GnO_5>tC;koh8xK5CLv=h!|L z<^<#je;E=LiMz4;B1$L=Y&GeQiE`PMb zsg@Nd{B+#%#HB5D>QHSKl_UBpy2}H>JM9plenjhicVu+dCrG*4i}(kd_g9daQpGv?DHjL)&Sf2*g)CL z;SCa$nYGyWDS8?Evv6rXdG#>gJ3Jq92#fmh-zYry#aG3rvdBJMSm>%Nz6(yEQC+(+fQvo+@;1v9PMr;lgpm^$OBt?E5|_pX2Q0HHUOEFitw*4PG1^;Q>;=`9WPKNr(`0x7lft_U zV*cjJWMZRo{j3o Date: Mon, 19 Oct 2026 22:52:57 +0000 Subject: [PATCH 2/3] Pi Babysit: address PR #9232 feedback --- .../best-dust-alternatives-2026/index.mdx | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/apps/sim/content/library/best-dust-alternatives-2026/index.mdx b/apps/sim/content/library/best-dust-alternatives-2026/index.mdx index 89ac0dba8cd..f8b1bdeb4e0 100644 --- a/apps/sim/content/library/best-dust-alternatives-2026/index.mdx +++ b/apps/sim/content/library/best-dust-alternatives-2026/index.mdx @@ -7,7 +7,7 @@ date: 2026-10-19 updated: 2026-10-19 authors: - andrew -readingTime: 8 +readingTime: 7 tags: [AI Agents, Workflow Automation, AI Tools, Sim] ogImage: /library/best-dust-alternatives-2026/cover.jpg draft: false @@ -17,18 +17,18 @@ faq: - q: "Can Sim handle the knowledge Q&A we use Dust for?" a: "Yes. Sim knowledge bases let agents retrieve relevant document passages, and you can use them inside workflows. If you need automatic knowledge-base updates, KB Live Sync starts on Max." - q: "Which tools can we self-host?" - a: "Anyone can run Sim's Apache 2.0 core for free, subject to the enterprise exception at https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE. Enterprise features require an active Enterprise subscription for production use. n8n supports self-hosting under a source-available license at https://docs.n8n.io/n8n-community-license. Glean offers a Customer Hosted deployment in your GCP or AWS account that Glean still operates, as described at https://docs.glean.com/get-started/prepare/about-deployment. Dust's pricing page at https://dust.tt/home/pricing lists hosted plans with single-tenant deployment on Enterprise, though its source code is public under the MIT license at https://github.com/dust-tt/dust/blob/main/LICENSE. Gumloop offers hosted plans at https://www.gumloop.com/pricing; contact the vendor about deployment options. Relevance AI's docs at https://relevanceai.com/docs/sdk/authentication describe hosted regional deployments." + a: "Anyone can run Sim's Apache 2.0 core for free, subject to the enterprise exception. Enterprise features require an active Enterprise subscription for production use. n8n supports self-hosting under a source-available license. Glean offers a Customer Hosted deployment in your GCP or AWS account that Glean still operates. Dust's pricing page lists hosted plans with single-tenant deployment on Enterprise, though its source code is public under the MIT license. Gumloop offers hosted plans; contact the vendor about deployment options. Relevance AI's docs describe hosted regional deployments." - q: "What does \"workflow depth\" mean here?" a: "Workflow depth describes how much control you have over the steps an agent takes after receiving a request. For example, Sim lets you branch on conditions, repeat steps, run steps in parallel, and pause for human input." --- ## TL;DR -- **Sim** fits Dust users who need [multi-step agent workflows](https://docs.sim.ai/introduction) with explicit branching, human review, and knowledge retrieval in one tool. -- **n8n** fits technical users who want [self-hosted automation](https://github.com/n8n-io/n8n) with visual workflows and custom code, under a source-available license. +- **Sim** fits teams using Dust that need [multi-step agent workflows](https://docs.sim.ai/workflows) with explicit branching, human review, and knowledge retrieval in one tool. +- **n8n** fits technical teams that want [self-hosted automation](https://github.com/n8n-io/n8n) with visual workflows and custom code, under a source-available license. - **Gumloop** fits teams that want agents that use connected tools and [run from schedules, app events, or webhooks](https://docs.gumloop.com/core-concepts/agent_triggers). - **Relevance AI** fits enterprise teams that want an [AI workforce with agents and tools](https://relevanceai.com/pricing) rather than building each workflow from scratch. -- **Zapier Agents** fits users who already rely on Zapier and want agents that [act across 9,000+ apps](https://zapier.com/agents). +- **Zapier Agents** fits teams that already rely on Zapier and want agents that [act across 9,000+ apps](https://zapier.com/agents). - **Glean** fits teams comparing enterprise search and knowledge assistants with Dust, rather than prioritizing workflow automation. ## Why teams outgrow Dust for workflow automation @@ -48,10 +48,10 @@ The comparison below weighs pricing, hosting options, workflow depth, knowledge | Sim | [Free; Pro $25/user/month](https://www.sim.ai/pricing) | [Apache 2.0 core](https://github.com/simstudioai/sim) can be self-hosted; [enterprise exception](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE) | Visual blocks for branching, loops, parallel runs, human review, and code | [Knowledge bases](https://docs.sim.ai/knowledgebase); KB Live Sync on Max | [273](https://www.sim.ai/integrations) | | n8n | [€20/month billed annually](https://n8n.io/pricing/) | [Self-hosted options](https://github.com/n8n-io/n8n) under a [source-available license](https://docs.n8n.io/n8n-community-license) | Visual workflows with custom code | AI and integration nodes | Every integration is included in its [listed plans](https://n8n.io/pricing/) | | Gumloop | [See current plans](https://www.gumloop.com/pricing) | Hosted; consult Gumloop for enterprise deployment options | Agents run from schedules, app events, and webhooks | Connected company data | Connected tools and an API | -| Relevance AI | [Custom Enterprise pricing](https://relevanceai.com/pricing) | [Hosted regional projects](https://relevanceai.com/docs/sdk/authentication) | Agents, tools, and Workforces | [RAG-powered knowledge](https://relevanceai.com/docs/get-started/core-concepts/knowledge) | [2,000+](https://relevanceai.com/pricing) | +| Relevance AI | [Custom Enterprise pricing](https://relevanceai.com/pricing) | [Hosted regional projects](https://relevanceai.com/docs/sdk/authentication) | Agents, tools, and Workforces | [Knowledge bases that retrieve relevant information](https://relevanceai.com/docs/get-started/core-concepts/knowledge) | [2,000+](https://relevanceai.com/pricing) | | Zapier Agents | [See current plans](https://zapier.com/pricing) | Managed cloud | Agents act through connected apps | [Company knowledge](https://zapier.com/agents) | [9,000+ apps](https://zapier.com/agents) | | Glean | Contact sales | [Glean Hosted or Customer Hosted](https://docs.glean.com/get-started/prepare/about-deployment) | [Agent orchestration](https://www.glean.com/ai-agents/agent-orchestration) | Enterprise search | [275+ connectors](https://www.glean.com/platform/connectors) | -| Dust | [Free and paid Business plans](https://dust.tt/home/pricing) | Hosted; single-tenant deployment on Enterprise | Agent tools, multi-agent workflows, and triggers | Connectors to 20+ data sources | Slack, Notion, GitHub, Drive, other sources, and MCP | +| Dust | [Free and paid Business plans](https://dust.tt/home/pricing) | Hosted; single-tenant deployment on Enterprise | Agent tools, multi-agent workflows, and triggers | Connectors to 20+ data sources | Slack, Notion, GitHub, Drive, other sources, and external tools through Model Context Protocol (MCP) | ### Sim @@ -67,7 +67,7 @@ Sim, the open-source AI workspace, combines a visual workflow builder with [know Sim gives you direct control over how an agent proceeds. [Agent](https://docs.sim.ai/workflows/blocks/agent), [Condition](https://docs.sim.ai/workflows/blocks/condition), and [Router](https://docs.sim.ai/workflows/blocks/router) blocks let you define different paths. [Loop](https://docs.sim.ai/workflows/blocks/loop) and [Parallel](https://docs.sim.ai/workflows/blocks/parallel) blocks handle repeated or concurrent work. A [Human in the Loop](https://docs.sim.ai/workflows/blocks/human-in-the-loop) block pauses a run for submitted input, and a downstream Condition can route on an approval field. A [Function](https://docs.sim.ai/workflows/blocks/function) block runs custom code. That structure makes a multi-step workflow easier to inspect than a single agent carrying a long set of instructions. For more design context, see [AI agent orchestration frameworks explained](https://www.sim.ai/library/ai-agent-orchestration-frameworks-explained). -[Sim's Apache 2.0 core](https://github.com/simstudioai/sim) can be [self-hosted](https://docs.sim.ai/platform/self-hosting) with Docker Compose or Kubernetes, with [enterprise-licensed features excluded](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Its knowledge bases cover the retrieval use case you may already rely on Dust for, and Sim connects to [273 integrations](https://www.sim.ai/integrations). Sim can also [deploy workflows as an MCP server](https://docs.sim.ai/workflows/deployment/mcp), so MCP clients can call them as tools. +[Sim's Apache 2.0 core](https://github.com/simstudioai/sim) can be [self-hosted](https://docs.sim.ai/platform/self-hosting) with Docker Compose or Kubernetes, with [enterprise-licensed features excluded](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Its knowledge bases cover the retrieval use case you may already rely on Dust for, and Sim connects to [273 integrations](https://www.sim.ai/integrations). Sim can also [deploy workflows as a Model Context Protocol (MCP) server](https://docs.sim.ai/workflows/deployment/mcp), so compatible AI clients can call them as tools. **Cons** @@ -95,7 +95,7 @@ Gumloop's [pricing page](https://www.gumloop.com/pricing) provides its current h Relevance AI fits enterprise teams that want specialist agents instead of building each workflow from scratch. Its [Enterprise plan](https://relevanceai.com/pricing) centers on agents, tools, Workforces, integrations, and governance features. -Its [pricing page](https://relevanceai.com/pricing) lists an Enterprise plan at custom pricing, with 2,000+ integrations, unlimited agents and tools, SSO, RBAC, and audit logs. Agents can use [RAG-powered knowledge](https://relevanceai.com/docs/get-started/core-concepts/knowledge) to ground their responses. Relevance AI projects are deployed to a [US, Europe, or Australia region](https://relevanceai.com/docs/sdk/authentication). Ask sales for a current quote and verify the specific apps your agents need. +Its [pricing page](https://relevanceai.com/pricing) lists an Enterprise plan at custom pricing, with 2,000+ integrations, unlimited agents and tools, SSO, RBAC, and audit logs. Agents can use [knowledge bases that retrieve relevant information](https://relevanceai.com/docs/get-started/core-concepts/knowledge) to ground their responses. Relevance AI projects are deployed to a [US, Europe, or Australia region](https://relevanceai.com/docs/sdk/authentication). Ask sales for a current quote and verify the specific apps your agents need. ### Zapier Agents From 17c983025d8cb055e91af24efe451a1b2164021e Mon Sep 17 00:00:00 2001 From: Waleed Latif Date: Mon, 19 Oct 2026 16:12:33 -0700 Subject: [PATCH 3/3] docs(library): verify and correct Dust alternatives facts --- .../best-dust-alternatives-2026/index.mdx | 50 +++++++++---------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/apps/sim/content/library/best-dust-alternatives-2026/index.mdx b/apps/sim/content/library/best-dust-alternatives-2026/index.mdx index f8b1bdeb4e0..72bd3519994 100644 --- a/apps/sim/content/library/best-dust-alternatives-2026/index.mdx +++ b/apps/sim/content/library/best-dust-alternatives-2026/index.mdx @@ -15,9 +15,9 @@ faq: - q: "Can Dust run multi-step automations?" a: "Yes, within its agent model. Dust agents use tools that can take actions in third-party platforms, can call other agents, and can run on schedules or webhook triggers. The agent decides which tools to use for each request, so Dust is less suited to automations that must follow the same explicit sequence of steps every run." - q: "Can Sim handle the knowledge Q&A we use Dust for?" - a: "Yes. Sim knowledge bases let agents retrieve relevant document passages, and you can use them inside workflows. If you need automatic knowledge-base updates, KB Live Sync starts on Max." + a: "Yes. Sim knowledge bases let agents retrieve relevant document passages, and you can use them inside workflows. If you need knowledge bases that sync automatically, KB Live Sync is included on Max and Enterprise." - q: "Which tools can we self-host?" - a: "Anyone can run Sim's Apache 2.0 core for free, subject to the enterprise exception. Enterprise features require an active Enterprise subscription for production use. n8n supports self-hosting under a source-available license. Glean offers a Customer Hosted deployment in your GCP or AWS account that Glean still operates. Dust's pricing page lists hosted plans with single-tenant deployment on Enterprise, though its source code is public under the MIT license. Gumloop offers hosted plans; contact the vendor about deployment options. Relevance AI's docs describe hosted regional deployments." + a: "Anyone can self-host Sim's Apache 2.0 core for free with Docker Compose or Kubernetes. Sim's pricing table lists supported self-hosting as an Enterprise feature alongside SSO and SOC 2, and enterprise features such as SSO and audit logs require an Enterprise subscription for production use. n8n supports self-hosting under its source-available Sustainable Use License. Glean offers a Customer Hosted deployment in your own GCP or AWS account that Glean still operates. Dust's pricing page lists hosted plans with single-tenant deployment on Enterprise and no self-hosted plan. Gumloop's pricing page lists no self-hosted plan, with an optional VPC (a private network in your own cloud account) on Enterprise. Relevance AI's docs describe a multi-tenant hosted service with a US, EU/UK, or AU data region chosen at signup." - q: "What does \"workflow depth\" mean here?" a: "Workflow depth describes how much control you have over the steps an agent takes after receiving a request. For example, Sim lets you branch on conditions, repeat steps, run steps in parallel, and pause for human input." --- @@ -25,7 +25,7 @@ faq: ## TL;DR - **Sim** fits teams using Dust that need [multi-step agent workflows](https://docs.sim.ai/workflows) with explicit branching, human review, and knowledge retrieval in one tool. -- **n8n** fits technical teams that want [self-hosted automation](https://github.com/n8n-io/n8n) with visual workflows and custom code, under a source-available license. +- **n8n** fits technical teams that want [self-hosted automation](https://docs.n8n.io/deploy/host-n8n) with over 500 integrations and custom code, under a source-available license. - **Gumloop** fits teams that want agents that use connected tools and [run from schedules, app events, or webhooks](https://docs.gumloop.com/core-concepts/agent_triggers). - **Relevance AI** fits enterprise teams that want an [AI workforce with agents and tools](https://relevanceai.com/pricing) rather than building each workflow from scratch. - **Zapier Agents** fits teams that already rely on Zapier and want agents that [act across 9,000+ apps](https://zapier.com/agents). @@ -33,7 +33,7 @@ faq: ## Why teams outgrow Dust for workflow automation -Dust works well when you need agents that answer questions across company material. Its [Business plans](https://dust.tt/home/pricing) connect Slack, Notion, GitHub, Drive, and more than 20 other sources, and agents combine instructions, skills, knowledge, and tools. Dust also runs agents on [schedules and webhook triggers](https://docs.dust.tt/docs/user-documentation/agents/triggers), so its agents can do more than answer questions. +Dust works well when you need agents that answer questions across company material. Its [Business plan](https://dust.tt/home/pricing) connects Slack, Notion, GitHub, Drive, and more than 20 other sources, and agents combine instructions, skills, knowledge, and tools. Dust also runs agents on [schedules and webhook triggers](https://docs.dust.tt/docs/user-documentation/agents/triggers), so its agents can do more than answer questions. Business plan seats are Free with 500 lifetime credits, Pro at €24 per seat per month billed yearly (€30 monthly), and Max at €120 per seat per month billed yearly (€150 monthly), excluding VAT. The difference is how the steps are defined. In Dust, [the agent evaluates each request and picks a combination of tools](https://docs.dust.tt/docs/user-documentation/agents/tools) to use. Dust's tools documentation does not describe explicit branches, loops, or a step-by-step visual builder. That model suits open-ended requests, but recurring tasks that must follow the same steps every time, with controlled tool access at each step, are easier to build and audit in a workflow builder. Our guide to [AI agent workflow builders](https://www.sim.ai/library/ai-agent-workflow-builders-multi-step-tasks) explains why this distinction matters for multi-step tasks. @@ -41,17 +41,17 @@ The comparison below weighs pricing, hosting options, workflow depth, knowledge ## Comparison at a glance -**Best overall: Sim** for custom agent workflows, while Dust provides the knowledge-assistant baseline. Listed prices are starting points, not comparable usage allowances. +Sim is listed first for custom agent workflows, while Dust provides the knowledge-assistant baseline. Listed prices are starting points, not comparable usage allowances. | Tool | Starting price | Hosting and self-hosting | Workflow depth | Knowledge features | Integrations | |---|---|---|---|---|---| -| Sim | [Free; Pro $25/user/month](https://www.sim.ai/pricing) | [Apache 2.0 core](https://github.com/simstudioai/sim) can be self-hosted; [enterprise exception](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE) | Visual blocks for branching, loops, parallel runs, human review, and code | [Knowledge bases](https://docs.sim.ai/knowledgebase); KB Live Sync on Max | [273](https://www.sim.ai/integrations) | -| n8n | [€20/month billed annually](https://n8n.io/pricing/) | [Self-hosted options](https://github.com/n8n-io/n8n) under a [source-available license](https://docs.n8n.io/n8n-community-license) | Visual workflows with custom code | AI and integration nodes | Every integration is included in its [listed plans](https://n8n.io/pricing/) | -| Gumloop | [See current plans](https://www.gumloop.com/pricing) | Hosted; consult Gumloop for enterprise deployment options | Agents run from schedules, app events, and webhooks | Connected company data | Connected tools and an API | -| Relevance AI | [Custom Enterprise pricing](https://relevanceai.com/pricing) | [Hosted regional projects](https://relevanceai.com/docs/sdk/authentication) | Agents, tools, and Workforces | [Knowledge bases that retrieve relevant information](https://relevanceai.com/docs/get-started/core-concepts/knowledge) | [2,000+](https://relevanceai.com/pricing) | -| Zapier Agents | [See current plans](https://zapier.com/pricing) | Managed cloud | Agents act through connected apps | [Company knowledge](https://zapier.com/agents) | [9,000+ apps](https://zapier.com/agents) | +| Sim | [Free (1,000 one-time credits); Pro $25/user/month](https://www.sim.ai/pricing) | [Apache 2.0 core](https://github.com/simstudioai/sim) anyone can self-host; supported self-hosting listed as an Enterprise feature | Visual blocks for branching, loops, parallel runs, human review, and code | [Knowledge bases](https://docs.sim.ai/knowledgebase); KB Live Sync on Max | [273](https://www.sim.ai/integrations) | +| n8n | [€20/month billed annually (2,500 executions)](https://n8n.io/pricing/) | [Yes](https://docs.n8n.io/deploy/host-n8n), under a [source-available license](https://docs.n8n.io/n8n-community-license) | Visual workflows plus a [JavaScript and Python Code node](https://docs.n8n.io/build/code-in-n8n/using-the-code-node) | [Vector store nodes for RAG](https://docs.n8n.io/build/integrate-ai/understand-ai-components/retrieve-relevant-context) | [Over 500](https://n8n.io/) | +| Gumloop | [Pro from $37/month after a 14-day free trial](https://www.gumloop.com/pricing) | No self-hosted plan listed; VPC optional on Enterprise | Agents run from schedules, app events, and webhooks | Company Brain | Connectors plus hosted MCP servers | +| Relevance AI | [Enterprise custom](https://relevanceai.com/pricing); docs list [Pro from $19/month](https://relevanceai.com/docs/get-started/pricing) | [Hosted, multi-tenant; US, EU/UK, or AU region](https://relevanceai.com/docs/admin/security) | Agents, tools, and Workforces | [Knowledge bases that retrieve relevant information](https://relevanceai.com/docs/get-started/core-concepts/knowledge) | [2,000+](https://relevanceai.com/pricing) | +| Zapier Agents | [Free (400 activities/month); Agents Pro $50/month](https://zapier.com/pricing) | Managed cloud | Runs capped at 10 activities (Free) or 40 (paid) | [Company knowledge](https://zapier.com/agents) | [9,000+ apps](https://zapier.com/agents) | | Glean | Contact sales | [Glean Hosted or Customer Hosted](https://docs.glean.com/get-started/prepare/about-deployment) | [Agent orchestration](https://www.glean.com/ai-agents/agent-orchestration) | Enterprise search | [275+ connectors](https://www.glean.com/platform/connectors) | -| Dust | [Free and paid Business plans](https://dust.tt/home/pricing) | Hosted; single-tenant deployment on Enterprise | Agent tools, multi-agent workflows, and triggers | Connectors to 20+ data sources | Slack, Notion, GitHub, Drive, other sources, and external tools through Model Context Protocol (MCP) | +| Dust | [Free (500 lifetime credits); Pro €24/seat/month billed yearly](https://dust.tt/home/pricing) | Hosted; single-tenant deployment on Enterprise | Agent tools, multi-agent workflows, and triggers | Connectors to 20+ data sources | Slack, Notion, GitHub, Drive, 20+ more, and any tool via MCP | ### Sim @@ -61,47 +61,47 @@ Sim fits you if Dust handles your company knowledge questions but you need to bu **What it is** -Sim, the open-source AI workspace, combines a visual workflow builder with [knowledge bases](https://docs.sim.ai/knowledgebase) that agents can search for relevant document passages. You connect blocks, configure their inputs, and review each step of a run in the [run logs](https://docs.sim.ai/execution/logging), where a trace shows every block with its timing, status, inputs, and outputs. +Sim is an open-source AI workspace for teams. Its Workflows module is a visual builder, and it sits alongside Chat, Tables, Files, and [Knowledge Base](https://docs.sim.ai/knowledgebase), whose knowledge bases agents can search for relevant document passages. You connect blocks, configure their inputs, and review each step of a run in the [run logs](https://docs.sim.ai/logs-debugging/logging), where a trace shows every block with its timing, status, inputs, and outputs. **Pros** -Sim gives you direct control over how an agent proceeds. [Agent](https://docs.sim.ai/workflows/blocks/agent), [Condition](https://docs.sim.ai/workflows/blocks/condition), and [Router](https://docs.sim.ai/workflows/blocks/router) blocks let you define different paths. [Loop](https://docs.sim.ai/workflows/blocks/loop) and [Parallel](https://docs.sim.ai/workflows/blocks/parallel) blocks handle repeated or concurrent work. A [Human in the Loop](https://docs.sim.ai/workflows/blocks/human-in-the-loop) block pauses a run for submitted input, and a downstream Condition can route on an approval field. A [Function](https://docs.sim.ai/workflows/blocks/function) block runs custom code. That structure makes a multi-step workflow easier to inspect than a single agent carrying a long set of instructions. For more design context, see [AI agent orchestration frameworks explained](https://www.sim.ai/library/ai-agent-orchestration-frameworks-explained). +Sim gives you direct control over how an agent proceeds. [Agent](https://docs.sim.ai/workflows/blocks/agent), [Condition](https://docs.sim.ai/workflows/blocks/condition), and [Router](https://docs.sim.ai/workflows/blocks/router) blocks let you define different paths. [Loop](https://docs.sim.ai/workflows/blocks/loop) and [Parallel](https://docs.sim.ai/workflows/blocks/parallel) blocks handle repeated or concurrent work. A [Human in the Loop](https://docs.sim.ai/workflows/blocks/human-in-the-loop) block pauses a run until a person submits input, such as an approval, and a downstream Condition can route on that answer. A [Function](https://docs.sim.ai/workflows/blocks/function) block runs custom code. That structure makes a multi-step workflow easier to inspect than a single agent carrying a long set of instructions. For more design context, see [AI agent orchestration frameworks explained](https://www.sim.ai/library/ai-agent-orchestration-frameworks-explained). -[Sim's Apache 2.0 core](https://github.com/simstudioai/sim) can be [self-hosted](https://docs.sim.ai/platform/self-hosting) with Docker Compose or Kubernetes, with [enterprise-licensed features excluded](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Its knowledge bases cover the retrieval use case you may already rely on Dust for, and Sim connects to [273 integrations](https://www.sim.ai/integrations). Sim can also [deploy workflows as a Model Context Protocol (MCP) server](https://docs.sim.ai/workflows/deployment/mcp), so compatible AI clients can call them as tools. +[Sim's Apache 2.0 core](https://github.com/simstudioai/sim) can be [self-hosted](https://docs.sim.ai/platform/self-hosting) with Docker Compose or Kubernetes, with [enterprise-licensed features excluded](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Its knowledge bases cover the retrieval use case you may already rely on Dust for, and Sim connects to [273 integrations](https://www.sim.ai/integrations). Sim can also [deploy workflows as an MCP server](https://docs.sim.ai/workflows/deployment/mcp) (MCP, the Model Context Protocol, lets AI apps call tools), so compatible AI clients can call them as tools. **Cons** -You have to design the workflow paths yourself, which takes more setup than a straightforward knowledge assistant. Enterprise features such as SSO, SCIM, audit logs, and access control use the [separate Sim Enterprise License](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE), which requires an active Sim Enterprise subscription for production use. +You have to design the workflow paths yourself, which takes more setup than a straightforward knowledge assistant. Enterprise features such as SSO (single sign-on), SCIM user provisioning, audit logs, and access control use the [separate Sim Enterprise License](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE), which requires an active Sim Enterprise subscription for production use. **Pricing** -Sim's [cloud plans](https://www.sim.ai/pricing) are Free, Pro at $25 per user per month, Max at $100 per user per month, and Enterprise at custom pricing. KB Live Sync starts on Max, while SSO requires Enterprise. Anyone can self-host [Sim's Apache 2.0 core](https://github.com/simstudioai/sim) for free, subject to the [enterprise exception](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Supported self-hosting is listed with Enterprise services on the pricing table, but local models through Ollama, vLLM, LM Studio, or LiteLLM work on any self-hosted Sim deployment. +Sim's [cloud plans](https://www.sim.ai/pricing) are Free with 1,000 one-time credits (worth $5) and 30 days of log retention; Pro at $25 per user per month with 6,000 credits plus a 2,000-credit weekly refresh; Max at $100 per user per month with 25,000 credits plus a 4,000-credit weekly refresh; and Enterprise at custom pricing. Paid plans keep logs without a time limit. KB Live Sync starts on Max, while SSO requires Enterprise. Anyone can self-host [Sim's Apache 2.0 core](https://github.com/simstudioai/sim) for free. The pricing table lists Self Hosting, meaning supported self-hosting, as an Enterprise feature alongside SSO and SOC 2, and enterprise features require an [Enterprise subscription for production use](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Any self-hosted Sim deployment can run [local models](https://docs.sim.ai/platform/self-hosting) through Ollama, vLLM, LM Studio, or LiteLLM. ### n8n -n8n fits technical teams that want to self-host automations and connect apps, even if building and maintaining workflows takes more work. Its [repository describes both self-hosted and cloud deployment](https://github.com/n8n-io/n8n), along with visual building and custom code. +n8n fits technical teams that want to self-host automations and connect a wide range of apps, even if building and maintaining workflows takes more work. [n8n says it offers over 500 integrations](https://n8n.io/), and you can [host n8n on your own infrastructure](https://docs.n8n.io/deploy/host-n8n) rather than use its cloud service. For logic that the visual nodes do not cover, the [Code node](https://docs.n8n.io/build/code-in-n8n/using-the-code-node) runs JavaScript or Python. -n8n's source code is public, but its [Sustainable Use License](https://github.com/n8n-io/n8n/blob/master/LICENSE.md) limits permitted use and distribution. n8n [describes its licenses as fair-code](https://docs.n8n.io/n8n-community-license) rather than open source. By comparison, [Sim's core uses Apache 2.0](https://github.com/simstudioai/sim), with a [separate license for enterprise code](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Our [Apache 2.0 versus fair-code guide](https://www.sim.ai/library/apache-2-0-vs-fair-code) explores the practical difference. +n8n's source code is public, but its [Sustainable Use License](https://github.com/n8n-io/n8n/blob/master/LICENSE.md) limits permitted use and distribution. n8n [describes its licenses as fair-code and source-available](https://docs.n8n.io/n8n-community-license) and does not call itself open source. By comparison, [Sim's core uses Apache 2.0](https://github.com/simstudioai/sim), with a [separate license for enterprise code](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE). Our [Apache 2.0 versus fair-code guide](https://www.sim.ai/library/apache-2-0-vs-fair-code) explores the practical difference. -For cloud use, n8n charges [by monthly workflow executions, regardless of complexity](https://n8n.io/pricing/). Its pricing page lists Starter at €20 per month and Pro at €50 per month, both billed annually; Business starts at €667 per month billed annually, and Enterprise pricing is custom. If you self-host, you also run the infrastructure. +For cloud use, n8n charges [by monthly workflow executions, regardless of complexity](https://n8n.io/pricing/). Its pricing page lists Starter at €20 per month for 2,500 executions and Pro at €50 per month for 10,000, both billed annually. Business costs €667 per month billed annually for 40,000 executions and is currently self-hosted only, and Enterprise pricing is custom. If you self-host, you also run the infrastructure. ### Gumloop -Gumloop fits teams that want a hosted platform for AI agents that work across their tools. Its [pricing page](https://www.gumloop.com/pricing) presents its hosted offering. [Agent triggers](https://docs.gumloop.com/core-concepts/agent_triggers) can run on a schedule, from an app event, or through a webhook, while its [API](https://docs.gumloop.com/api-reference/getting-started) can trigger automations programmatically. +Gumloop fits teams that want a hosted platform for AI agents that work across their tools. Its [pricing page](https://www.gumloop.com/pricing) lists the older workflow builder as "Workflows (Legacy)", so new work centers on agents. [Agent triggers](https://docs.gumloop.com/core-concepts/agent_triggers) can run on a schedule, from an app event, or through a webhook, while its [API](https://docs.gumloop.com/api-reference/getting-started) can trigger automations programmatically. -Gumloop's [pricing page](https://www.gumloop.com/pricing) provides its current hosted plans. Compare the included usage, connected tools, and enterprise deployment options against your expected run volume before choosing a plan. +Pro starts at $37 per month after a 14-day free trial and includes 20,000 credits per month, unlimited agents, BYOK (bring your own model API keys), and one hosted MCP server. Enterprise pricing is custom. The [pricing page](https://www.gumloop.com/pricing) lists no self-hosted plan, though Enterprise offers an optional VPC, a private network in your own cloud account. ### Relevance AI Relevance AI fits enterprise teams that want specialist agents instead of building each workflow from scratch. Its [Enterprise plan](https://relevanceai.com/pricing) centers on agents, tools, Workforces, integrations, and governance features. -Its [pricing page](https://relevanceai.com/pricing) lists an Enterprise plan at custom pricing, with 2,000+ integrations, unlimited agents and tools, SSO, RBAC, and audit logs. Agents can use [knowledge bases that retrieve relevant information](https://relevanceai.com/docs/get-started/core-concepts/knowledge) to ground their responses. Relevance AI projects are deployed to a [US, Europe, or Australia region](https://relevanceai.com/docs/sdk/authentication). Ask sales for a current quote and verify the specific apps your agents need. +Relevance AI's two official pricing pages disagree. Its [pricing page](https://relevanceai.com/pricing) lists only an Enterprise plan at custom pricing, with 2,000+ integrations, unlimited agents and tools, SSO, RBAC (role-based access control), and audit logs. Its [pricing documentation](https://relevanceai.com/docs/get-started/pricing) lists Pro from $19 per month billed annually ($29 monthly) and Team from $234 per month billed annually ($349 monthly), and says the Free plan is retired. Agents can use [knowledge bases that retrieve relevant information](https://relevanceai.com/docs/get-started/core-concepts/knowledge), a RAG (retrieval-augmented generation) system, to ground their responses. Relevance AI runs on a [multi-tenant architecture](https://relevanceai.com/docs/admin/security) with a US, EU/UK, or AU data region chosen at signup, and its docs do not describe a self-hosted option. Confirm the current plan with Relevance AI and verify the specific apps your agents need. ### Zapier Agents -Zapier Agents fits you if you already use Zapier and want AI agents to act through your existing app connections. Its main draw is access to [more than 9,000 apps](https://zapier.com/agents), and you can equip agents with company knowledge. If you need long, custom agent workflows, validate the required sequence with your own use case before choosing it. +Zapier Agents fits you if you already use Zapier and want AI agents to act through your existing app connections. Its main draw is access to [more than 9,000 apps](https://zapier.com/agents), and you can equip agents with company knowledge. If you need long, custom agent workflows, check the run limits before choosing it. -Zapier changes product packaging over time, so use its [current pricing page](https://zapier.com/pricing) to compare plans and limits. Focus on whether an agent can reliably complete your whole task and whether the connected apps expose the actions it needs. +Agents use a separate billing unit called activities, which [does not affect your Zapier task usage](https://zapier.com/pricing). The Free plan includes 400 activities per month, and Agents Pro includes 1,500 for $50 per month or $400 per year. A single agent run is capped at 10 activities on the Free plan or 40 on a paid plan, and at the cap the agent asks before continuing. Those caps can constrain a long multi-step run even when you have activities left for the month. ### Glean @@ -115,7 +115,7 @@ If you mainly need answers from company documents, Dust may still fit. Consider For lightweight automation, choose Zapier Agents if you already use Zapier's app connections, or Gumloop if you want a hosted agent platform with triggers and schedules. If you need custom workflows that branch, loop, and involve multiple agents, Sim lets you combine those steps with [knowledge retrieval](https://docs.sim.ai/knowledgebase). That makes it a closer fit when Dust answers your questions but cannot easily carry out the work that follows. You can also compare broader licensing and deployment choices in our guide to [open-source AI agent platforms](https://www.sim.ai/library/open-source-ai-agent-platforms). -Workflow depth and self-hosting may settle the choice. Compare Sim with n8n if you want to run workflows on your own infrastructure. [Sim's Apache 2.0 core](https://github.com/simstudioai/sim) can be self-hosted by anyone, with the [enterprise exception](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE), while n8n uses a source-available license. +Workflow depth and self-hosting may settle the choice. Compare Sim with n8n if you want to run workflows on your own infrastructure. Anyone can self-host [Sim's Apache 2.0 core](https://github.com/simstudioai/sim), while its enterprise features need an [Enterprise subscription for production use](https://github.com/simstudioai/sim/blob/main/apps/sim/ee/LICENSE); n8n uses a source-available license. ## Conclusion