Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
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:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"tokenknows": {
"command": "npx",
"args": ["-y", "npm"],
"env": {
"TOKENKNOWS_API_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| TOKENKNOWS_API_TOKEN | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
A project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Shared, serverless, conflict-free knowledge-graph memory for AI agents
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.