🔓Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant contex…
// ragthedotmack/⟨JavaScript⟩★ 95,595◷ Apache-2.0[ claude ]
RAG & Knowledge for Claude
Retrieval, embeddings, vector search, and knowledge bases that ground Claude in your data.
⇄ compare all 139 rag & knowledge side by side// rag (87)
🔓
🔓Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, memory and security gates.
// ragagentlas-ai/⟨Python⟩★ 1,542◷ Apache-2.0[ claude ]
🔓Offline Claude export viewer. Search, analyze, and export your Claude.ai data locally.
// ragcrownleo/⟨HTML⟩★ 209◷ GPL-3.0[ claude ]
🔓Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
// ragvolcengine/⟨Python⟩★ 39,212◷ AGPL-3.0[ claude ]
🔓Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Herm…
// ragAVIDS2/⟨TypeScript⟩★ 830◷ Apache-2.0[ claude ]
🔓Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
// ragheadroomlabs-ai/⟨Python⟩★ 74,459◷ Apache-2.0[ claude ]
🔓Sub2API is an open-source relay platform that unifies Claude, OpenAI, Gemini, and Antigravity subscriptions into a single endpoint. It supports account shari…
// ragWei-Shaw/⟨Go⟩★ 42,796◷ LGPL-3.0[ claude ]
🔓mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
// ragtobi/⟨TypeScript⟩★ 30,140◷ MIT[ claude ]
🔓
🔓The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separa…
// ragraullenchai/⟨Python⟩★ 3,871◷ Apache-2.0[ claude ]
🔓五运六气 AI Agent 技能包 — 中医运气学说推算引擎。干支推算 + 六气步移 + RAG五层知识库(104键) + ReAct推理工作流 + 自进化引擎。支持 Claude Code/Codex CLI/Cursor/Cline/OpenClaw 等 AI 客户端。
// ragdhicoc/⟨Python⟩★ 44◷ MIT[ claude ]
🔓GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted da…
// ragCanner/⟨Python⟩★ 17,750◷ NOASSERTION[ claude ]
🔓Scientific illustration for Codex and Claude Code: turn research papers into visual drafts using a curated image-and-prompt knowledge base, then reconstruct…
// ragexsinger-hub/⟨JavaScript⟩★ 300◷ MIT[ claude ]
🔓Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
// raglucasastorian/⟨Python⟩★ 1,654◷ Apache-2.0[ claude ]
🔓Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
// ragdoobidoo/⟨Python⟩★ 1,963◷ Apache-2.0[ claude ]
🔓Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Me…
// ragNirDiamant/⟨Jupyter Notebook⟩★ 1,081◷ Apache-2.0[ claude ]
🔓A memory layer for Claude Code that learns as you work. Persistent, per-context memory as plain markdown in your own git repo. No server, no telemetry.
// raganshulforyou/⟨Shell⟩★ 116◷ MIT[ claude ]
🔓Operating Soul for AI coding agents that captures how to think, not just rules — principle-over-rule, 7 delegation levels (Tell→Delegate), a git-gated learni…
// ragtomdwipo/⟨Shell⟩★ 24◷ MIT[ claude ]
🔓Hivemind turns your traces into reusable skills across agents
// ragactiveloopai/⟨TypeScript⟩★ 1,621◷ Apache-2.0[ claude ]
🔓
🔓Turn Claude into an MBB-grade management consultant. Case-interview coaching, strategy frameworks, market sizing, and board-ready problem-solving. 129 refere…
// ragDogInfantry/⟨HTML⟩★ 128◷ NOASSERTION[ claude ]
🔓Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Co…
// ragtigerless-labs/⟨Python⟩★ 2,283[ claude ]
🔓Runtime for coding-agent harnesses. Run Claude Code, Codex, OpenCode, Pi, and Grok in one terminal; hop live between them; search or resume any local session.
// raghetpatel-11/⟨Rust⟩★ 31◷ MIT[ claude ]
🔓md+git knowledge base: FTS5 search (bm25+trigram/fuzzy), HTML+graph, code-ontology linter, Claude Code plugin
// ragvakovalskii/⟨Python⟩★ 80◷ MIT[ claude ]
🔓Mine your Claude Code and Codex logs into a local you.md agent profile.
// ragohad6k/⟨Python⟩★ 292◷ MIT[ claude ]
🔓Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
// ragHUANGCHIHHUNGLeo/⟨Python⟩★ 2,186◷ MIT[ claude ]
🔓A free Claude skill for sharper consulting thinking ;case interview prep, strategy frameworks, and business problem-solving. Contributions welcome.
// ragDogInfantry/⟨HTML⟩★ 129◷ NOASSERTION[ claude ]
🔓Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency gra…
// raggiancarloerra/⟨TypeScript⟩★ 3,317◷ AGPL-3.0[ claude ]
🔓All-in-one AI 研究工作台：把 Codex / Claude Code / Cursor 变成有长期记忆的研究系统。wiki 摄入、研究闭环、快速筛选、假设追踪、播客、日报六大能力，零 API key 可跑基座。
// ragBenboerba620/⟨Python⟩★ 75◷ MIT[ claude ]
🔓Find out which of your agent rules actually fire. An agentic coding harness for Claude Code and Codex: one checkout of rules, skills, subagents, slash comman…
// ragJakeSelby/⟨Python⟩★ 24◷ MIT[ claude ]