长篇深度研究报告的调研/写作助手，一句话自动跑完完整报告输出高质量 PDF 报告
A sophisticated RAG (Retrieval-Augmented Generation) Telegram bot that transforms articles and documents into interactive knowledge bases. Upload PDFs/URLs and get AI-powered answers with source citations.
Local-first MCP memory server for AI agents, with source citations and OKF/Markdown knowledge bases.
MCP search and evidence tool for AI agents with query rewriting, source zoom-in, sourced answers, and runtime metrics.
A simple RAG toolkit.
Rust MCP server for source-cited search over a local Zoltan Pozsar macro/liquidity corpus.
Memtruth SDK: evidence, parse, corpus contracts, chunking, projection, and diagnostics for AI applications.
Local-first AI knowledge system with agent skills, source-grounded retrieval, and evaluation experiments.
Evidence grounded document Q&A built with Python, FastAPI, LangChain, and PostgreSQL/pgvector, featuring traceable citations and reproducible retrieval evaluation.
RAG-powered document assistant — upload PDFs, chat with them using BM25 retrieval + LLM, and get answers with verified source citations. Built with Next.js 16, Prisma, and a custom retrieval pipeline.
Docsy MCP for ChatGPT, Claude Code, Codex & Cursor — version-specific developer docs with source links. Public plugin releases.
快速梳理 | An agent skill that decomposes any project (code/docs/PDF/Excel/PPT) into a sourced overview + goal-driven learning path, then teaches you — every rule validated by stranger-agent testing (see evals/)
Official Docsy TypeScript SDK, CLI & Gemini extension — version-aware documentation with source citations. Audited release-only source.
Explore Python and TypeScript repositories through symbols, dependency graphs, cited source views and change-impact analysis.
Search a private document library with hybrid retrieval, source citations and incremental updates. Local RAG app with an extractive browser demo.
Evidence-backed job search tracking and interview prep with source URLs, voice notes, reminders, and daily intelligence.
AI-assisted PDF/DOCX packet structuring workflow with source citations, semantic retrieval, deterministic validation, and reviewer-facing run sheets.
Detects cited code snippets that have moved or changed.
Provider-neutral attribution, source-footer, and royalty settlement system for AI outputs.
Turn a local problem into a source-cited advocacy website with a guided research and editorial workflow.
To associate your repository with the source-citations topic, visit your repo's landing page and select "manage topics."