Back to directory

llmwiki

A tool that converts a developer's Claude Code, Codex CLI, Copilot, Cursor, and Gemini CLI session transcripts into a searchable, interlinked local knowledge base, following Andrej Karpathy's LLM Wiki pattern.

llmwiki

llmwiki turns the dormant session transcripts that coding agents write to disk into a searchable, interlinked knowledge base, built locally in two commands. It renders every session as clean, redacted Markdown, adds an activity heatmap, tool-usage charts, token usage, model information, project comparisons, and topic pages, and serves the result as a static site.

It can optionally enrich pages with LLM-generated semantic summaries, using a local Ollama backend or a stub mode, through a synthesis step that runs separately from the sync and build steps. It also produces AI-consumable exports, including a JSON-LD graph and per-page text and JSON files, so other AI agents can query the wiki directly.

It is written in Python and installs and runs through setup, build, and serve scripts; contributions must keep real session data out of version control.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.