claudeers.

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
🔓

LLM Wiki skill for Claude Code — Karpathy LLM Wiki pattern, batteries included

// ragcclank/★ 22◷ 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⟩★ 21◷ AGPL-3.0[ claude ]
🔓

Task-induced context normalization for coding agents — a native Claude Code plugin. The task induces a projection; operators preserve the answer, not just sh…

// ragPinperepette/⟨Python⟩★ 24◷ MIT[ claude ]
🔓

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Ollama/VLLM/llama.cp…

// ragiKislay/⟨Python⟩★ 20◷ Apache-2.0[ claude ]
🔓

10 skills that cut your AI bill with proof instead of vibes. MIT, works in Claude Code, Codex, Cursor. Every skill's check is executed by CI.

// ragNeeeophytee/⟨JavaScript⟩★ 18◷ NOASSERTION[ claude ]
🔓

Searchable Markdown KB built for AI workflows. Hybrid search, typed relations, wiki links, graph views. Token-efficient CLI for agents, static publishing for…

// ragchriskd/⟨Python⟩★ 16◷ MIT[ claude ]
🔓

One-click local backup for Codex and Claude Code memories

// ragcclank/⟨Python⟩★ 17◷ MIT[ claude ]
🔓

The WorkBoard for Claude Code and humans. Watch your work come to life — never lose an idea, never lose a workflow.

// ragmalcolm1232/⟨Python⟩★ 14◷ NOASSERTION[ claude ]
🔓

Graph + local semantic context for Obsidian, with guarded remote MCP access and edits from Codex, ChatGPT, Claude, and any MCP client.

// ragjunnnnnw00/⟨TypeScript⟩★ 15◷ MIT[ claude ]
🔓

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

// raginitialneil/⟨Shell⟩★ 13◷ MIT[ claude ]
🔓

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

// ragozankasikci/⟨Python⟩★ 14◷ MIT[ claude ]
🔓

A warn-only runtime layer for Claude Code agents. Keeps feature state, scope and handoffs on disk so they survive compaction, and requires an evidence path b…

// ragRedtropig/⟨Shell⟩★ 13◷ MIT[ claude ]
🔓

Archive snapshot repo of the original concept and 0-1 invention features, please utilize the constantly updated cypher-tempre-genesis repo for running the sk…

// ragcyberphysicsai/⟨Python⟩★ 14◷ MIT[ claude ]
🔓

Linkly 金句卡 — turn knowledge-base notes into numbered zine-style quote cards. Claude Code skill: Seedream backend, halftone portraits, verbatim CJK text check…

// raglogog782-cmyk/★ 12◷ MIT[ claude ]
🔓

A Claude code skill to help you make html5 games with minimal effort

// ragSudhanshu5669/★ 12◷ MIT[ claude ]
🔓

Local-first engineering memory for Codex and Claude Code — auditable Markdown, no vector database.

// ragminiLV/⟨JavaScript⟩★ 12◷ Apache-2.0[ claude ]
🔓

Interactive Lean 4 + Mathlib formalization from a Claude Code conversation

// ragnasqret/⟨Python⟩★ 10◷ MIT[ claude ]
🔓

Moss-backed memory layer for Claude Code and Codex. Records reads, edits, executions, and decisions into an in-process session index, then surfaces relevant…

// ragAyanBhardwaj1/⟨TypeScript⟩★ 10[ claude ]
🔓

Self-hosted LLM gateway. One Go binary turns your Macs and Linux boxes into a private inference cluster — multi-machine routing, sharding via llama.cpp-RPC,…

// raghadihonarvar/⟨Go⟩★ 56◷ Apache-2.0[ claude ]

// collections in rag