Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
TOKENKNOWS_API_BASE, TOKENKNOWS_API_TOKEN, TOKENKNOWS_DEFAULT_PROJECT, TOKENKNOWS_WEB_BASE标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"tokenknows": {
"command": "uvx",
"args": [
"tokenknows-mcp"
],
"env": {
"TOKENKNOWS_API_BASE": "your-value",
"TOKENKNOWS_API_TOKEN": "your-value",
"TOKENKNOWS_DEFAULT_PROJECT": "your-value",
"TOKENKNOWS_WEB_BASE": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add tokenknows --env TOKENKNOWS_API_BASE=your-value --env TOKENKNOWS_API_TOKEN=your-value --env TOKENKNOWS_DEFAULT_PROJECT=your-value --env TOKENKNOWS_WEB_BASE=your-value -- uvx tokenknows-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"tokenknows": {
"command": "uvx",
"args": [
"tokenknows-mcp"
],
"env": {
"TOKENKNOWS_API_BASE": "your-value",
"TOKENKNOWS_API_TOKEN": "your-value",
"TOKENKNOWS_DEFAULT_PROJECT": "your-value",
"TOKENKNOWS_WEB_BASE": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tokenknows": {
"type": "stdio",
"command": "uvx",
"args": [
"tokenknows-mcp"
],
"env": {
"TOKENKNOWS_API_BASE": "your-value",
"TOKENKNOWS_API_TOKEN": "your-value",
"TOKENKNOWS_DEFAULT_PROJECT": "your-value",
"TOKENKNOWS_WEB_BASE": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
TOKENKNOWS_API_BASE envTOKENKNOWS_DEFAULT_PROJECT envTOKENKNOWS_WEB_BASE env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 johnnywuj81 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:TOKENKNOWS_API_TOKEN
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.3.0)于5个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
TokenKnows
Distill AI coding sessions into living knowledge — weekly reports, ADRs, incident reviews, books, agent skills, and a knowledge graph.
English | 简体中文
You spend hours pair-programming with Claude Code, Codex, and Cursor. The decisions, bug hunts, and design trade-offs from those sessions evaporate the moment the terminal closes. TokenKnows captures them automatically and distills them into structured, evidence-linked knowledge assets:
capture (6 collectors) → distill (5-stage LLM pipeline) → assets (7 document types) → review / redact / publish
cosine × trust × recency across ≥2 sources.| Workbench | Document page |
|---|---|
| Evidence drawer | Publish receipt + version diff |
▶ Full walkthrough: engineering_handoff/walkthrough.mp4 (5 min, Chinese narration + subtitles)
All 12 screens
| 1 Workbench | 2 Event drawer | 3 Document list | 4 Document page |
|---|---|---|---|
| 5 Evidence drawer | 6 Regenerate dialog | 7 Review | 8 Redaction |
| 9 Publish dialog | 10 Publish receipt + diff | 11 LLM egress | 12 Admin |
Prerequisite: the TokenKnows backend at http://localhost:8001 and the web UI at `http://localhost:5173` (see Quick start), plus uv (the plugin pulls the MCP server from PyPI via uvx). All plugin env vars have working local defaults — export TOKENKNOWS_API_BASE / TOKENKNOWS_API_TOKEN / TOKENKNOWS_DEFAULT_PROJECT / TOKENKNOWS_WEB_BASE only for non-default setups. Register/login in the web UI and create an API token under Project Settings → MCP 接入 when your backend requires auth.
| Platform | How |
|---|---|
| Claude Code | /plugin marketplace add johnnywuj81/tokenknows → /plugin install tokenknows@tokenknows — full walkthrough in tokenknows-plugin/README.md (5-minute quickstart) |
| Codex | codex plugin marketplace add johnnywuj81/tokenknows → codex plugin add tokenknows@tokenknows (loads skills, commands and the MCP server; local-clone alternative in codex-plugin/README.md) |
| Cursor | Add the tokenknows MCP block to ~/.cursor/mcp.json (uvx config example in code/tokenknows-mcp/README.md) |
| VS Code | Download the .vsix from Releases → code --install-extension tokenknows-vscode-*.vsix |
The plugin gives your AI tool MCP tools (submit_session_events, distill_document, list_assets, get_asset, get_asset_chapters, search_entity) plus slash commands like /tokenknows:weekly and /tokenknows:adr.
# 1. (Optional but recommended) Ollama — fully local inference, zero cloud keys
ollama serve & ollama pull minimax-m2:cloud # or gpt-oss:20b, qwen2.5, ...
cd code/tokenknows-api python3 -m venv .venv && .venv/bin/pip install -e ".[dev]" cp .env.local.example .env.local # defaults to Ollama; edit to add cloud providers .venv/bin/uvicorn app.main:app --host 127.0.0.1 --port 8001
cd code/tokenknows-web npm install npm run dev
./engineering_handoff/demo-seed.sh
Platform support: macOS — full experience (collectors auto-start via launchd). Linux — backend, frontend, and collectors all run manually (python3 plugins/ /sync.py --watch); the launchd scripts don't apply. Windows — untested; WSL2 recommended.
All local — no ngrok, no public webhooks. On macOS they restart on crash and on reboot (launchd).
| Collector | Source | Mode |
|---|---|---|
| claude-code | ~/.claude/projects/*.jsonl | 30s polling, incremental offsets |
| codex | ~/.codex/sessions/**/rollout-*.jsonl | 30s polling, incremental offsets |
| cursor | Cursor's state.vscdb (read-only SQLite) | 60s polling |
| github | GitHub REST API · PRs / issues / commits | 5min polling (gh auth token) |
| vscode | VS Code extension onDidSaveTextDocument | buffered, 10s flush |
| local-docs | ~/Documents .md .txt .pdf (watchdog) | realtime, 2s debounce |
./scripts/launchd/install.sh # macOS: install all 5 Python collectors as LaunchAgents
launchctl list | grep com.tokenknows tail -f ~/Library/Logs/tokenknows/*.log
Every event carries a trust score (0.6 × source_authority + 0.4 × extraction_confidence); the evidence stage ranks citations by 0.6 × cosine + 0.25 × trust + 0.15 × recency and enforces ≥2 distinct sources.
Collectors feed an event store (SQLite). A five-stage pipeline (collect → outline → content → evidence → assess) turns events into assets. The LLM Gateway unifies four providers (Anthropic / OpenAI / MiniMax / Ollama) with per-task routing and fallback chains — and refuses any cloud call unless all three egress switches are on.
| Workflow | Runner | Trigger |
|---|---|---|
ci.yml | ubuntu-latest (GitHub-hosted) | push to main + every PR |
ci-macos.yml | self-hosted macOS ARM64 | maintainer pushes to main only — never runs external PR code |
Details: PRD §6.7 data residency & egress control (Chinese).
| Topic | Doc |
|---|---|
| Product requirements, user journeys | PRD (zh) |
| Technical design, API, schema | TDD (zh) |
| Macro architecture & milestones | Architecture (zh) |
| Per-screen engineering decisions | TaskTechDesign (zh) |
| Pixel-level UI mockups | mockups/ — open in a browser |
Most in-depth docs are in Chinese (the project's working language). Code comments are predominantly Chinese too; issues and PRs in English or Chinese are both welcome.
CONTRIBUTING · Roadmap · Code of Conduct · Security policy · Issues
MIT © 2026 johnnywuj81