io.github.ChristopherDavenport/github-twinsearch

github-twin

Verified · 23 days ago

Personal RAG over your GitHub history (commits, code, reviews), served to Claude Code over MCP.

Install

claude mcp add github-twin -- uvx github-twin

Requires: GITHUB_TOKEN, ANTHROPIC_API_KEY, GEMINI_API_KEY, GT_PATHS__DATA_DIR

Our take

This server offers personal RAG over a user's GitHub activity, including commits, code, and reviews, exposed through MCP. It is for developers who want an agent to answer questions from their own engineering history rather than from a generic codebase snapshot. The use case is clear and plausible, but the lack of visible traction suggests an early-stage personal-productivity tool rather than a widely validated platform.

reviewed by hand · 2026-07-21

Something wrong or dead here? Report it

Verification record

last verified
23 days ago
github stars
0
last commit
5 mo ago
archived
no
license
MIT
in registry since
2026-05-29

github.com/ChristopherDavenport/github-twin

mcp-server-searchsearch

mcp-server-search

Verified · 11 days ago

MCP server for web search operations

hand-reviewed40k starschecked 11 days ago

repomixsearch

Repomix

Verified · 2 mo ago

Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search

hand-reviewed28k stars67k dl/wkchecked 2 mo ago

screenpipe-mcpsearch

screenpipe

Verified · 2 mo ago

Search your local screen recordings, audio transcripts, and computer activity from screenpipe.

hand-reviewed22k stars2.8k dl/wkchecked 2 mo ago

xerjsearch

XERJ

Verified · 24 days ago

The search engine for AI agents: cited answers from your local code, docs, specs and logs.

hand-reviewed15k starschecked 24 days ago

sui-kapasearch

Sui Knowledge Base (kapa.ai)

Verified · 13 days ago

Semantic search across Sui documentation and knowledge sources, powered by kapa.ai

hand-reviewed7.8k starschecked 13 days ago

firecrawl-mcp-serversearch

Firecrawl MCP Server

Verified · 28 days ago

Firecrawl, the context API for AI agents: search, scrape, interact with the web, plus paper search.

hand-reviewed7.7k starschecked 28 days ago