claudeers.

RAG & Knowledge for Claude

Retrieval, embeddings, vector search, and knowledge bases that ground Claude in your data.

⇄ compare all 146 rag & knowledge side by side
🔓

Cut your Claude bill 59–70% by rendering bulky LLM context as dense PNG pages — 100% read accuracy, exact per-provider billing math (Anthropic/OpenAI/Gemini)…

// ragdiegosouzapw/⟨TypeScript⟩★ 155◷ MIT[ claude ]
🔓

RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC +…

// ragstuinfla/⟨JavaScript⟩★ 83◷ NOASSERTION[ claude ]
🔓

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

// ragvolcengine/⟨Python⟩★ 42,431◷ AGPL-3.0[ claude ]
🔓

Claude Code skill that turns any topic, conversation, or file into a single-file, beautifully typeset HTML document - trigger with /paper

// ragWamikmk/⟨HTML⟩★ 24[ claude ]
🔓

Unofficial source-linked AWS best practices for every AWS service, organized by Well-Architected pillar for Claude Code, OpenAI Codex, and AI coding agents.

// ragferdinandobons/⟨Python⟩★ 38◷ MIT[ claude ]
🔓

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama) with FTS5 fallb…

// ragvalpere/⟨Go⟩★ 42◷ Apache-2.0[ claude ]
🔓

AKM — universal Agent Knowledge Management. A tool-agnostic Markdown knowledge OS for AI agents: memory / brain / vault over seven layers, with a Learn Back…

// ragDECK6/⟨JavaScript⟩★ 38◷ MIT[ 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⟩★ 83◷ MIT[ claude ]
🔓

A self-evolving knowledge accumulation & hybrid retrieval system for AI coding agents (Claude Code / Codex / etc.)

// ragkevintsai1202/⟨Python⟩★ 41◷ 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⟩★ 2,287◷ MIT[ claude ]
🔓

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for producti…

// ragMemoriLabs/⟨Python⟩★ 17,448◷ NOASSERTION[ claude ]
🔓

Semantic Search & Call Graphs for AI Agents (100% Local)

// ragyoanbernabeu/⟨C⟩★ 1,954◷ MIT[ claude ]
🔓

稳定省钱的OpenAI、Claude、Gemini等的API接口-For企业和开发者。OpenAI的api proxy,支持ChatGPT的API调用,支持Anthropic claude的官方接口形式,支持Google gemini的官方接口形式,支持:gpt-5,sora。不需要openai Key, 不需要…

// ragxing61/★ 992[ claude ]
🔓

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

// ragSMJAI/⟨TypeScript⟩★ 87◷ NOASSERTION[ claude ]
🔓

Claude Code meta-skill: turn each project/machine/device into a self-improving skill (log -> reflect -> improve).

// raginitialneil/⟨Shell⟩★ 14◷ MIT[ claude ]
🔓

Offline Claude export viewer. Search, analyze, and export your Claude.ai data locally.

// ragcrownleo/⟨HTML⟩★ 222◷ GPL-3.0[ 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⟩★ 52◷ MIT[ claude ]
🔓

OKF-powered knowledge context for Claude Code — injects your project's knowledge base at every session

// ragguhcostan/⟨Python⟩★ 127◷ MIT[ claude ]
🔓

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works wit…

// ragVonderVuflya/⟨Python⟩★ 22◷ AGPL-3.0[ claude ]
🔓

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex), backed by Markdown and Milvus.

// ragzilliztech/⟨Python⟩★ 2,856◷ MIT[ claude ]
🔓

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

// ragvitali87/⟨Python⟩★ 5,363◷ MIT[ claude ]
🔓

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and…

// ragrohitg00/⟨JavaScript⟩★ 2,958[ claude ]
🔓

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verificat…

// ragwquguru/⟨Python⟩★ 3,251[ claude ]
🔓

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

// ragdatachain-ai/⟨Python⟩★ 2,832◷ Apache-2.0[ claude ]
🔓

Agent Package Manager

// ragmicrosoft/⟨Python⟩★ 4,296◷ MIT[ claude ]
🔓

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persis…

// ragSamurAIGPT/⟨Python⟩★ 3,686◷ 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⟩★ 4,145◷ Apache-2.0[ claude ]
🔓

Git. Ship. Done - Core

// ragopen-gsd/⟨JavaScript⟩★ 11,492◷ MIT[ claude ]
🔓

The open creative AI workspace

// ragnodetool-ai/⟨TypeScript⟩★ 644◷ AGPL-3.0[ claude ]
🔓

This is the public release of MIRA OS. Discrete memories decay through momentum loss, tools auto-configure when dropped into tools/ folder, and the system pr…

// ragtaylorsatula/⟨Python⟩★ 485◷ AGPL-3.0[ claude ]

// collections in rag