Bike4Mind
Your bicycle for the mind in the age of AI.
An open-core AI knowledge platform — a multi-model workspace where notebooks, autonomous agents, and a RAG knowledge engine work together to augment any cognitive task.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y @bike4mind/[email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add bike4mind-cli -- npx -y @bike4mind/cli@4.0.0在終端機中執行。
{ "mcpServers": { "bike4mind-cli": { "command": "npx", "args": [ "-y", "@bike4mind/[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
Bike4Mind is an AI-powered knowledge platform that wires a superset of AI technologies together behind one workspace. Bring your own models, keep your data, and let agents do the heavy lifting.
Try the hosted service at app.bike4mind.com, or self-host the open core on your own infrastructure (below).
Bike4Mind is open core. The engine is public and self-hostable; the multi-tenant hosted service is our business.
@bike4mind/* packages.See CONTRIBUTING.md for the exact open/closed boundary.
Hosted (fastest): sign in at app.bike4mind.com — nothing to install.
Self-host: run the open core on your own hardware with Docker — no AWS account or cloud provider required. See the Self-Host Quickstart. In short:
# 1. Copy the env template, then generate JWT_SECRET / SESSION_SECRET /
# SECRET_ENCRYPTION_KEY (see SELF_HOST.md) and add your model keys
cp .env.selfhost.example .env.selfhost
# 2. Bring up the stack (app + MongoDB + object storage + queues + mail catcher)
docker compose -f compose.selfhost.yaml --env-file .env.selfhost up -d
Bike4Mind then runs at http://localhost:3000; sign-in code emails land in the bundled Mailpit at http://localhost:8025. The self-host image is published to ghcr.io/bike4mind/bike4mind-selfhost.
Bike4Mind is a pnpm + Turborepo monorepo (Node 24).
pnpm i -r # install
pnpm turbo:core:build # build the @bike4mind/* core packages
pnpm turbo:typecheck # type check
pnpm turbo:test # run tests
Project layout: apps/client (Next.js SPA + pages API backend), packages/cli (interactive CLI + ReAct agent), b4m-core/* (the @bike4mind/* engine packages), packages/database (Mongoose models + migrations). Realtime WebSocket fanout ships as a separate @bike4mind/subscriber-fanout image. See CONTRIBUTING.md for the full guide.
Building an app that signs users in with Bike4Mind and bills AI usage to their accounts? See Building an app on Bike4Mind.
Contributions are welcome — fork → topic branch → PR → squash-merge. All contributors sign a lightweight CLA on their first PR (you keep your copyright). Start with CONTRIBUTING.md and our Code of Conduct. Questions and self-hosting help go in Discussions.
Please report vulnerabilities privately — see SECURITY.md. Do not open public issues for security problems.
Bike4Mind is licensed under the Business Source License 1.1 with a broad Additional Use Grant:
For alternative licensing, contact [email protected].
© 2026 Bike4Mind, Inc.
{ "mcpServers": { "bike4mind-cli": { "command": "npx", "args": [ "-y", "@bike4mind/[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
@bike4mind/cli 透過 stdio 在本機執行。
上次檢查時間:2026-11-15。 Interactive CLI tool for Bike4Mind with ReAct agents