Merekomendasikan proyek GitHub dengan menganalisis riwayat lokal, file memory, dan aturan instruksi coding agent Anda.
Juga dikenal sebagai pth2002/repofit
- Stars
- 7
- Tools
- —
- Unduhan, 30 hari
- 421
- Versi terbaru
- 0.1.2
- Commit terakhir
- 12 Nov 2026
- Lisensi
- MIT
Apa itu repofit MCP?
Merekomendasikan proyek GitHub dengan menganalisis riwayat lokal, file memory, dan aturan instruksi coding agent Anda.
Ringkasan dibuat dari README proyek
Tentang repofit MCP server
repofit memungkinkan Anda menemukan repositori GitHub yang relevan dengan menganalisis riwayat coding pribadi Anda. Alih-alih mencari melalui daftar trending yang bersifat umum, tool ini memeriksa file memory lokal, aturan instruksi, dan riwayat chat dari agent seperti Claude Code, Cursor, dan Codex untuk menyarankan tool yang benar-benar akan Anda gunakan. Tool ini bekerja secara lokal di mesin Anda, yang berarti data Anda tetap privat dan kecerdasannya berasal dari model yang sudah digunakan oleh agent Anda.
Developer dapat menghubungkannya ke berbagai client termasuk Claude Desktop, Windsurf, Cline, dan Gemini CLI dengan menambahkannya ke MCP configuration Anda. Server ini membaca file seperti CLAUDE.md, AGENTS.md, dan .cursorrules untuk membangun profil kebutuhan Anda. Tool ini memberikan rekomendasi spesifik yang menyertakan bukti, menunjukkan secara tepat sesi atau percakapan masa lalu mana yang memicu saran tersebut. Selain itu, tool ini membantu menjaga efisiensi dengan mengidentifikasi MCP server atau skill yang sudah terinstall namun tidak pernah Anda panggil sama sekali.
Apa yang bisa Anda lakukan dengannya
- 1Dapatkan rekomendasi tool yang personalMinta coding agent Anda untuk menyarankan proyek GitHub berdasarkan pola pengembangan spesifik dan keluhan Anda di masa lalu.
- 2Verifikasi kesesuaian repositoriPeriksa apakah repositori GitHub tertentu selaras dengan kebutuhan coding dan riwayat Anda saat ini.
- 3Identifikasi developer tool yang tidak terpakaiTemukan skill atau MCP server terinstall mana yang memakan context tanpa pernah benar-benar digunakan dalam sesi Anda.
- 4Audit sumber data agentPindai mesin lokal Anda untuk melihat agent mana saja yang terinstall dan data spesifik apa yang mereka simpan.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal repofit MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal repofit MCP di Claude Code
$ claude mcp add repofit -- uvx repofitInstal repofit MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"repofit": {
"command": "uvx",
"args": [
"repofit"
]
}
}
}Instal repofit MCP di VS Code
.vscode/mcp.json
{
"servers": {
"repofit": {
"type": "stdio",
"command": "uvx",
"args": [
"repofit"
]
}
}
}Instal repofit MCP di VS Code CLI
$ code --add-mcp '{"name":"repofit","type":"stdio","command":"uvx","args":["repofit"]}'Instal repofit MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"repofit": {
"command": "uvx",
"args": [
"repofit"
]
}
}
}Instal repofit MCP di Codex
$ codex mcp add repofit -- uvx repofitInstal repofit MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.repofit] command = "uvx" args = ["repofit"]
Instal repofit MCP di Gemini CLI
$ gemini mcp add -s user repofit uvx -- repofitInstal repofit MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"repofit": {
"command": "uvx",
"args": [
"repofit"
]
}
}
}Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkaupth2002/repofit is public and reachablegithub.com/pth2002/repofit ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyarepofit names pth2002/repofit as sourcepypi.org/project/repofit/ ↗Lolos
- Provenance build (atestasi Sigstore)No build attestation published for this releaseTidak diperiksa
- Lisensi open source (OSI)MITspdx.org/licenses/MIT.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-12github.com/pth2002/repofit ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from repofitLolos
- Tidak ada advisory kritis pada paket atau dependensinyathe package checked; no critical advisoryosv.dev ↗Lolos
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubStop scrolling trending. Ask the agent that has watched you work.
Every week another wave of repositories hits ten thousand stars, and every "tools you should try" list is written for everyone at once. Meanwhile your coding agents have been taking notes on you for months: what you build, what keeps breaking, what you complained about at 2 a.m. repofit reads those notes on your own machine, from Claude Code, Codex, Cursor and a dozen more, and turns them into picks you have not heard of and will actually use. Every pick shows you the moment in your own history that earned it.
Try it in one line
uvx repofit unused
No install, no account, no API key and no model. It reads the session logs your agents already keep and lists
the MCP servers and skills you installed but never called. Each one still costs context on every request.
Without uv, run pipx run repofit unused.
Read 17 sessions from Claude Code, Codex, Gemini CLI. Nothing left this machine.
7 of 9 installed MCP servers and skills were never called:
Claude Code · 12 sessions
MCP server sqlite
skills canvas-design, docx, pptx
Codex · 4 sessions
MCP server puppeteer
skills slack-gif-creator, xlsx
Each one still costs context on every request. Remove the ones you do not need.
Not checked: 1 tool in Gemini CLI. Its logs do not say which server or skill each call went
to, or hold no sessions yet.
Want GitHub projects picked from the same history? Connect `repofit mcp` to your agent:
https://github.com/pth2002/repofit
Output on a sample history.
https://github.com/user-attachments/assets/c7ac0bcf-74ed-4a09-9295-b6d06e6d67c1
Install
pipx install repofit
Then point the agents you use at repofit mcp. Most of them read the same MCP config:
{ "mcpServers": { "repofit": { "command": "repofit", "args": ["mcp"] } } }
That line goes in ~/.cursor/mcp.json for Cursor, ~/.gemini/settings.json for Gemini CLI,
~/.qwen/settings.json for Qwen Code, and the MCP settings of Cline, Windsurf or Claude Desktop. Codex reads
TOML, and Claude Code adds servers from the command line:
# ~/.codex/config.toml
[mcp_servers.repofit]
command = "repofit"
args = ["mcp"]
claude mcp add repofit -- repofit mcp
repofit runs inside your agent, so your agent's own model does the thinking: no API key, no account, nothing
to host. To skip the install step, use uv and make the command uvx repofit mcp.
Just ask
Open a new session in any agent you connected and talk to it like a colleague who has read your history:
- "Use repofit to recommend some GitHub projects for me."
- "Does github.com/owner/name fit me?"
- "Is there a good tool for turning PDFs into Markdown?"
- "Which of my installed skills do I never use?"
The agent shows you the picks in the chat, and the same list stays one command away:
The picks come from a sample history. The text is exactly what the CLI prints.
Every pick has a receipt. No "because you starred X": the seen in line points at the session where the need
showed up and quotes what you said. If repofit cannot point at your history, it does not make the pick.
The list at the bottom matters more than it sounds. Every skill and MCP server you installed and forgot still costs context on every single request, and repofit names the ones none of your sessions ever called.
How it picks
Each agent stores its history differently, and the formats change every few months, so repofit ships one adapter per agent. The profile is written from a redacted, numbered evidence pack, and any claim that cites evidence that does not exist is thrown out by the code, not left to the model's good manners. Retrieval runs one query per task you actually do, with project names and search phrases the model adds, so it finds the library a task depends on even when you never typed its name. The ranker is told to skip the household names you already know. The candidate pool is rebuilt every Monday from the GitHub API: active repositories above 3,000 stars, new ones above 1,000, the agent ecosystem above 300, plus GitHub trending.
Your history stays yours
- Everything runs on your machine. repofit reads the files your agents already keep and writes its own to
~/.repofit. - You choose the depth: installed tools only, plus memory and instruction files (the default), or plus your own messages and tool calls.
- Before any model sees a line, API keys, tokens, passwords, emails, phone numbers and random-looking strings
(yes, including the password you once pasted after
ssh) are stripped, and your home folder becomes~. - With MCP, the text goes to the model your agent already uses. From the command line it goes only to the provider you name, after you confirm.
- Your notes and other people's READMEs can hide instructions. repofit hands everything over as data, and the agent is told never to follow what it finds inside.
Supported agents
| Agent | Sessions | Memory and instructions | Installed tools |
|---|---|---|---|
| Claude Code | yes | CLAUDE.md, project memory |
skills, plugins, MCP servers |
| Codex | yes, CLI and desktop | AGENTS.md, memories/ |
skills, plugins, MCP servers |
| Cursor | yes | user rules, pending memories | MCP servers, extensions |
| Hermes Agent | yes | USER.md, MEMORY.md |
skills, MCP servers |
| Gemini CLI, Qwen Code | yes | GEMINI.md, QWEN.md |
MCP servers, extensions |
| Cline, Roo Code, Kilo Code | yes | .clinerules |
MCP servers |
| Continue | yes | rules/ |
MCP servers |
| VS Code Copilot | yes | copilot-instructions.md |
MCP servers, extensions |
| Kimi CLI, Aider | yes | ||
| OpenCode | counted | AGENTS.md |
MCP servers |
| Windsurf, Claude Desktop, WorkBuddy, Trae | no local sessions | memories where present | MCP servers |
Project instruction files (AGENTS.md, CLAUDE.md, .cursorrules and friends) are read too. Run
repofit scan to see what it finds on your machine. If your agent hides its data somewhere else, open an
issue with the path and it gets an adapter.
Install with pipx install repofit, or put uvx in front of each command.
repofit unused # installed MCP servers and skills no session ever called
repofit scan # which agents are installed and what each one stores
repofit profile build --level L2 --provider deepseek
repofit recommend --provider deepseek --lang zh
Providers: deepseek, openai, ollama, anthropic, or any OpenAI-compatible endpoint with
--provider compatible --base-url ... --model .... Keys come from DEEPSEEK_API_KEY, OPENAI_API_KEY or
ANTHROPIC_API_KEY, and repofit shows how much text it will send before it sends anything.
No provider at all? Each model step prints a prompt to paste into any chat and imports the answer:
repofit profile prompt --level L2 > prompt.md # then: repofit profile apply answer.json
repofit profile expand --prompt # then: repofit profile expand --apply answer.json
repofit recommend --prompt --lang en # then: repofit recommend --apply answer.json
repofit recommend --no-llm # keyword retrieval only, nothing leaves your machine
Development
git clone https://github.com/pth2002/repofit && cd repofit
python -m pip install -e . pytest
python -m pytest
repofit index build # rebuild the candidate pool yourself; needs a GitHub token
License
MIT
Pertanyaan tentang repofit MCP
Bagaimana cara menambahkan repofit MCP ke Claude Code?
Jalankan claude mcp add repofit -- uvx repofit di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan repofit MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Bagaimana cara repofit merekomendasikan proyek?
Tool ini membaca file memory, rules, dan pesan dari berbagai coding agent di mesin Anda untuk membangun profil, lalu mengambil repositori yang relevan dari GitHub.
Apakah repofit memerlukan API key?
Saat digunakan melalui MCP client, tool ini menggunakan model yang sudah ada pada agent Anda dan tidak memerlukan API key atau akun tambahan.