TokenKnows — distill AI coding sessions into weekly reports, ADRs and a knowledge graph
About
Distill AI coding sessions (Claude Code / Codex / Cursor) into weekly reports, ADRs, incident reviews and a knowledge graph — local-first, evidence-linked.
Details
- License
- MIT
Explore
- Captures AI coding sessions from Claude Code, Codex, Cursor, and more.
- Distills into seven asset types including weekly reports, ADRs, and incident reviews.
- Every paragraph traces back to original PR, conversation, or commit.
- Local-first with three-layer LLM egress gate for privacy.
- Can run fully offline with Ollama and zero cloud keys.
- All collectors run locally without webhooks or tunnels.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
TokenKnows — distill AI coding sessions into weekly reports, ADRs and a knowledge graphCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
``bash
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 plugin marketplace add johnnywuj81/tokenknows
| Codex | → codex plugin add tokenknows@tokenknows (loads skills, commands and the MCP server; local-clone alternative in codex-plugin/README.md) |~/.cursor/mcp.json
| Cursor | Add the tokenknows MCP block to (uvx config example in code/tokenknows-mcp/README.md) |.vsix
| VS Code | Download the 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`.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"tokenknows \u2014 distill ai coding sessions into weekly reports, adrs and a knowledge graph": {
"tokenknows": {
"command": "python3",
"args": [
"-m",
"venv",
".venv",
"&&",
".venv/bin/pip",
"install",
"-e",
".[dev]"
]
}
}
}
}McpServers
{
"tokenknows": {
"command": "python3",
"args": [
"-m",
"venv",
".venv",
"&&",
".venv/bin/pip",
"install",
"-e",
".[dev]"
]
}
}What is TokenKnows?
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
- 📡 Captures everything — Claude Code, Codex, Cursor, VS Code, GitHub PRs/commits/issues, and local docs, all via local file watchers and API polling. No webhooks, no tunnels.
- 📝 Seven asset types — weekly reports, tech designs, ADRs, incident reviews, long-form books, reusable agent skills (SKILL.md), and an entity knowledge graph.
- 🔗 Evidence-linked — every paragraph traces back to the original PR / conversation / commit, ranked by cosine × trust × recency across ≥2 sources.
- 🔒 Local-first, zero egress by default — a three-layer LLM egress gate (instance ∧ project ∧ task) with full audit logging. Pair it with Ollama and run the whole pipeline with zero cloud keys.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
