[Trend Scout] Pratiyush/llm-wiki

[github-actions]

🔭 Trend Scout: Pratiyush/llm-wiki

Auto-generated by trend-scout.py — review and edit as needed.

📌 What problem it solves

LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.

📅 Timeline

Field	Value
Created	2026-04-08
Last pushed	2026-04-27
Stars	173
Forks	24
Open issues	13
License	MIT
Language	Python
Topics	ai, claude-code, cli, codex-cli, copilot, cursor, developer-tools, gemini-cli, karpathy, knowledge-base, llm, llm-wiki, markdown, mcp, obsidian, open-source, python, session-history, static-site, wiki

✅ Strengths

• Solid community traction (173 ⭐)
• Moderate fork activity (24 forks)
• Well-tagged: ai, claude-code, cli, codex-cli, copilot, cursor
• Primary language: Python
• Actively maintained (pushed within 30 days)

⚠️ Weaknesses / Risks

• No significant risks identified from available metadata

💡 What this repo can learn

• Claude Code session patterns: this repo's Claude Code integration approach could improve claude-adapter.py's JSONL parsing — e.g., handling new session event types or extracting richer metadata from Claude Code tool-use blocks
• CLI verb patterns: a clear add/search/update/delete verb model (like memory-tool add / search / dream) could streamline the UX of query-session.py and learn.py, making them easier to invoke from hooks or scripts
• Knowledge portability: the export/backup flow here could complement sync-knowledge.py for cross-machine knowledge portability
• Editor integration (cursor): watch-sessions.py could be extended to detect and parse cursor session formats natively, broadening the range of AI sessions indexed into knowledge.db
• MCP tool-server surface: the MCP server interface here could expose query-session.py and briefing.py as directly callable MCP tools — e.g., a Copilot agent could invoke the briefing lookup in-process rather than shelling out to a subprocess, reducing latency in hook-driven workflows

README excerpt

# llmwiki

> **LLM-powered knowledge base from your Claude Code, Codex CLI, Cursor, Gemini CLI, and Obsidian sessions.**
> Built on [Andrej Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f).

## 👉 Live demo: **[pratiyush.github.io/llm-wiki](https://pratiyush.github.io/llm-wiki/)**

Rebuilt on every `master` push from the synthetic sessions in [`examples/demo-sessions/`](examples/demo-sessions). No personal data. Shows every feature of the real tool (activity heatmap, tool charts, token usage, model info cards, vs-comparisons, project topics) running against safe reference data.

[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/)
[![Version](https://img.shields.io/badge/version-v1.3.71-10B981.svg)](CHANGELOG.md)
[![Tests](https://img.shields.io/badge/tests-2363%20passing-10B981.svg)](tests/)
[![CI](https://github.com/Pratiyush/llm-wiki/actions/workflows/ci.yml/badge.svg?branch=master)](https://github.com/Pratiyush/llm-wiki/actions/workflows/ci.yml)
[![Link check](https://github.com/Pratiyush/llm-wiki/actions/workflows/link-check.yml/badge.svg?branch=master)](https://github.com/Pratiyush/llm-wiki/actions/workflows/link-check.yml)
[![Wiki checks](https://github.com/Pratiyush/llm-wiki/actions/workflows/wiki-checks.yml/badge.svg?branch=master)](https://github.com/Pratiyush/llm-wiki/actions/workflows/wiki-checks.yml)
[

*(truncated)*

---

Scouted on 2026-04-27 · View on GitHub

[magicpro97]

Closing this aggregate scout issue after triage.

What checked out:

• CLI verb patterns are already covered by query-session.py and learn.py flag surfaces
• Knowledge portability is already covered by sync-knowledge.py (--sources, --auto, --dry-run)
• Claude Code session patterns is too generic here to justify a standalone issue without a concrete missing event type

What remains mildly interesting:

• MCP tool-server exposure is the only clearly new idea here, but that should be tracked as a focused feature request if we decide to pursue it, not as a mixed scout bundle issue.