Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
| Date | Stars |
|---|---|
| 2026-07-31 | 3294 |
| 2026-08-10 | 3339 |
| 2026-08-18 | 3387 |
| 2026-08-19 | 3393 |
| 2026-08-20 | 3399 |
| 2026-08-21 | 3403 |
| 2026-08-22 | 3424 |
| 2026-08-23 | 3438 |
| 2026-08-24 | 3442 |
| 2026-08-25 | 3453 |
| 2026-08-26 | 3455 |
| 2026-08-27 | 3461 |
| 2026-08-28 | 3465 |
| 2026-08-29 | 3469 |
| 2026-08-30 | 3469 |
| 2026-08-31 | 3472 |
| 2026-09-01 | 3474 |
| 2026-09-02 | 3476 |
| 2026-09-03 | 3478 |
| 2026-09-04 | 3486 |
| 2026-09-05 | 3490 |
| 2026-09-06 | 3491 |
| 2026-09-07 | 3495 |
| 2026-09-08 | 3497 |
| 2026-09-09 | 3499 |
| 2026-09-10 | 3505 |
| 2026-09-11 | 3509 |
| 2026-09-12 | 3512 |
| 2026-09-13 | 3516 |
| 2026-09-14 | 3523 |
| 2026-09-15 | 3524 |
| 2026-09-16 | 3527 |
| 2026-09-17 | 3528 |
| 2026-09-18 | 3533 |
| 2026-09-19 | 3541 |
| 2026-09-20 | 3543 |
| 2026-09-21 | 3547 |
| 2026-09-22 | 3555 |
| 2026-09-23 | 3567 |
| 2026-09-24 | 3571 |
| 2026-09-25 | 3575 |
| 2026-09-26 | 3578 |
| 2026-09-27 | 3581 |
| 2026-09-28 | 3582 |
| 2026-09-29 | 3588 |
| 2026-09-30 | 3592 |
| 2026-10-01 | 3593 |
| 2026-10-02 | 3595 |
| 2026-10-03 | 3596 |
| 2026-10-04 | 3597 |
| 2026-10-05 | 3600 |
| 2026-10-06 | 3601 |
| 2026-10-07 | 3604 |
| 2026-10-08 | 3609 |
| 2026-10-09 | 3612 |
| 2026-10-10 | 3614 |
| 2026-10-11 | 3614 |
| 2026-10-12 | 3616 |
| 2026-10-13 | 3621 |
| 2026-10-14 | 3625 |
| 2026-10-15 | 3627 |
| 2026-10-16 | 3629 |
| 2026-10-17 | 3628 |
| 2026-10-18 | 3632 |
| 2026-10-19 | 3636 |
| 2026-10-20 | 3643 |
| 2026-10-21 | 3644 |
| 2026-10-22 | 3647 |
| 2026-10-23 | 3649 |
| 2026-10-24 | 3649 |
| 2026-10-25 | 3650 |
| 2026-10-26 | 3654 |
| 2026-10-27 | 3657 |
| 2026-10-28 | 3662 |
| 2026-10-29 | 3663 |
| 2026-10-30 | 3668 |
| 2026-10-31 | 3667 |
| 2026-11-01 | 3669 |
| 2026-11-02 | 3671 |
| 2026-11-03 | 3672 |
| 2026-11-04 | 3671 |
Today
-1 stars today
This week
+9 stars this week
This month
+71 stars this month
Momentum
9.0
growth rate 0.25%/day
# LLM Wiki Agent [](LICENSE) **A coding agent skill.** Drop source documents into `raw/` and tell the agent to ingest them — it reads them, extracts knowledge, and builds a persistent interlinked wiki. Every new source makes the wiki richer. You never write it. > Most knowledge tools make you search your own notes. This one reads everything you've collected and writes a structured wiki that compounds over time — cross-references already built, contradictions already flagged, synthesis already done. ``` ingest raw/papers/attention-is-all-you-need.md ``` ``` wiki/ ├── index.md catalog of all pages — updated on every ingest ├── log.md append-only record of every operation ├── overview.md living synthesis across all sources ├── sources/ one summary page per source document ├── entities/ people, companies, projects — auto-created ├── concepts/ ideas, frameworks, methods — auto-created └── syntheses/ query answers filed back as wiki pages graph/ ├── graph.json persistent node/edge data (SHA256-cached) └── graph.html interactive vis.js visualization — open in any browser ``` ## Related Projects - [Open-Generative-AI](https://github.com/Anil-matcha/Open-Generative-AI) — Add AI image & video generation to your knowledge base pipeline - [Open-AI-Design-Agent](https://github.com/Anil-matcha/Open-AI-Design-Agent) — Autonomous AI design agent — pair with wiki agent for research + visual output - [AI-Voice-Agent](https://github.com/Anil-matcha/AI-Voice-Agent) — Self-hosted AI voice agent for real-time voice conversations, sales calls, and customer support - [awesome-jev-by-typesafe](https://github.com/Anil-matcha/awesome-jev-by-typesafe) — typed semantic retrieval, citation checks, and confidence-aware routing for agent knowledge workflows ## Install **Requires:** [Claude Code](https://claude.ai/code), [Codex](https://openai.com/codex), [Gemini CLI](https://github.com/google-gemini/gemini-cli), or any agent that reads a config file. ```bash git clone https://github.com/SamurAIGPT/llm-wiki-agent.git cd llm-wiki-agent ``` Open in your agent — no API key or Python setup needed: ```bash claude # reads CLAUDE.md + .claude/commands/ (slash commands available) codex # reads AGENTS.md opencode # reads AGENTS.md gemini # reads GEMINI.md ``` ## Usage All agents understand natural language and shorthand triggers: ``` ingest raw/papers/my-paper.md # ingest a markdown source ingest report.pdf # auto-converts to .md, then ingests ingest slides.pptx notes.docx # batch, mixed formats query: what are the main themes? # synthesize answer from wiki pages lint # find orphans, contradictions, gaps build graph # build graph.html from all wikilinks ``` Plain English works too: ``` "Ingest this paper: raw/papers/llama2.md" "What does the wiki say about attention mechanisms?" "Check for contradictions across sources" "Build the knowledge graph and tell me the most connected nodes" ``` **Claude Code** also provides `/wiki-ingest`, `/wiki-query`, `/wiki-lint`, `/wiki-graph` as slash commands (via `.claude/commands/`). These are Claude Code-specific — other agents use the natural language triggers above, which work identically. Works with markdown, PDF, DOCX, PPTX, XLSX, HTML, TXT, CSV, JSON, XML, RST, EPUB, and more. Non-markdown files are auto-converted via [markitdown](https://github.com/microsoft/markitdown) at ingest time — no separate step needed. ## What You Get **Persistent wiki** — structured markdown pages that accumulate across sessions. Unlike chat, nothing is lost. **Entity pages** — auto-created for every person, company, or project mentioned across sources. Updated each time a new source references them. **Concept pages** — auto-created for every key idea
Excerpt of 13,140 characters
Read on GitHub
Anil Chandra Naidu Matcha
42
29
T. L.
17
5
3
Vadootv
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:114b25d9f0319609, topic:rag, topic:knowledge-graph, desc:knowledge base