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.
| Date | Stars |
|---|---|
| 2026-07-31 | 625 |
| 2026-08-06 | 659 |
| 2026-08-14 | 692 |
| 2026-08-18 | 704 |
| 2026-08-19 | 705 |
| 2026-08-20 | 707 |
| 2026-08-21 | 708 |
| 2026-08-22 | 709 |
| 2026-08-23 | 713 |
| 2026-08-24 | 715 |
| 2026-08-25 | 719 |
| 2026-08-26 | 722 |
| 2026-08-27 | 724 |
| 2026-08-28 | 725 |
| 2026-08-29 | 727 |
| 2026-08-30 | 729 |
| 2026-08-31 | 732 |
| 2026-09-01 | 733 |
| 2026-09-02 | 735 |
| 2026-09-04 | 739 |
| 2026-09-05 | 740 |
| 2026-09-06 | 742 |
| 2026-09-07 | 744 |
| 2026-09-08 | 747 |
| 2026-09-09 | 749 |
| 2026-09-10 | 754 |
| 2026-09-11 | 757 |
| 2026-09-13 | 759 |
| 2026-09-14 | 760 |
| 2026-09-15 | 764 |
| 2026-09-16 | 766 |
| 2026-09-17 | 767 |
| 2026-09-18 | 768 |
| 2026-09-20 | 769 |
| 2026-09-21 | 770 |
| 2026-09-23 | 771 |
| 2026-09-24 | 773 |
| 2026-09-25 | 775 |
| 2026-09-26 | 778 |
| 2026-09-28 | 784 |
| 2026-09-29 | 786 |
| 2026-09-30 | 789 |
| 2026-10-02 | 791 |
| 2026-10-03 | 794 |
| 2026-10-04 | 810 |
| 2026-10-05 | 813 |
| 2026-10-06 | 815 |
| 2026-10-07 | 819 |
| 2026-10-08 | 819 |
| 2026-10-09 | 822 |
| 2026-10-10 | 823 |
| 2026-10-11 | 824 |
| 2026-10-12 | 826 |
| 2026-10-13 | 828 |
| 2026-10-14 | 829 |
| 2026-10-15 | 830 |
| 2026-10-17 | 832 |
| 2026-10-18 | 833 |
| 2026-10-19 | 874 |
| 2026-10-20 | 895 |
| 2026-10-21 | 910 |
| 2026-10-22 | 922 |
| 2026-10-23 | 934 |
| 2026-10-24 | 943 |
| 2026-10-25 | 952 |
| 2026-10-26 | 956 |
| 2026-10-27 | 969 |
| 2026-10-28 | 974 |
| 2026-10-29 | 978 |
| 2026-10-30 | 982 |
| 2026-10-31 | 990 |
| 2026-11-01 | 992 |
| 2026-11-02 | 996 |
| 2026-11-03 | 998 |
| 2026-11-04 | 1000 |
Today
+2 stars today
This week
+26 stars this week
This month
+187 stars this month
Momentum
0.0
growth rate 2.67%/day
# LLM Council — A Claude Code Skill
Stop trusting Claude's first answer. Run any decision through 5 AI advisors who argue, peer-review each other anonymously, and hand you a verdict you can actually trust.
Based on [Andrej Karpathy's LLM Council](https://x.com/karpathy/status/1962263486196867115) methodology, adapted to run entirely inside Claude Code using sub-agents with different thinking styles.
---
## The Problem
Claude is incredibly agreeable. Ask it "should I launch this product?" and it'll find 5 reasons why you should. Ask "is this product a bad idea?" and it'll find 5 reasons why it is. Same product, different framing, opposite answers.
That's fine for writing emails. It's dangerous for making decisions.
## How It Works
When you say **"council this"**, the skill:
1. **Scans your workspace** for relevant context (CLAUDE.md, memory files, etc.)
2. **Frames your question** into a neutral prompt
3. **Spawns 5 advisors in parallel**, each with a different thinking style:
- **The Contrarian** — hunts for what will fail
- **The First Principles Thinker** — asks if you're solving the right problem
- **The Expansionist** — looks for upside you're missing
- **The Outsider** — responds with zero context (catches curse of knowledge)
- **The Executor** — only cares what you do Monday morning
4. **Anonymizes their responses** and runs a peer review — advisors review each other without knowing who said what
5. **Chairman synthesizes** the verdict: where the council agrees, where it clashes, blind spots it caught, a clear recommendation, and one concrete next step
6. **Generates a visual HTML report** + full markdown transcript
All in one session. About 4 minutes.
---
## Install
### Option 1 — Git clone (recommended)
```bash
git clone https://github.com/tenfoldmarc/llm-council-skill ~/.claude/skills/llm-council
```
Then open Claude Code (`claude` in Terminal).
### Option 2 — Manual
1. Create folder `~/.claude/skills/llm-council/`
2. Drop `SKILL.md` inside it
3. Restart Claude Code
---
## Use
Type any of these triggers followed by your question:
- `council this`
- `run the council`
- `pressure-test this`
- `stress-test this`
- `war room this`
- `debate this`
**Example:**
> council this: I'm thinking of pivoting from a $297 course to a $97 live workshop for my audience of non-technical solopreneurs. Is that the right move?
Give it context. The richer the input, the sharper the output.
You'll get:
- A visual HTML report that opens automatically
- A full markdown transcript saved alongside it
---
## When To Use It
**Good council questions:**
- "Should I launch a $97 workshop or a $497 course?"
- "Which of these 3 positioning angles is strongest?"
- "I'm thinking of pivoting from X to Y. Am I crazy?"
- "Here's my landing page copy. What's weak?"
- "Should I hire a VA or build an automation first?"
**Skip the council for:**
- Factual questions with one right answer
- Pure creation tasks ("write me a tweet")
- Summaries or processing tasks
- Validation-seeking when you already know the answer
The council tells you things you don't want to hear. That's the feature, not a bug.
---
## Credit
- Methodology: [Andrej Karpathy's LLM Council](https://x.com/karpathy/status/1962263486196867115)
- Adapted for Claude Code sub-agents by [@olelehmann](https://x.com/olelehmann)
- Published as an installable skill by the community
---
## License
MIT — do whatever you want with it.
Excerpt of 3,466 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4f8be54499fe3213, llm:No README, no topics, empty description; repository name 'llm-council-skill' suggests an LLM-related skill/plugin, likely for agent/assistant or agents/skills integration.
matched fp:4f8be54499fe3213, llm:No README, no topics, empty description; repository name 'llm-council-skill' suggests an LLM-related skill/plugin, likely for agent/assistant or agents/skills integration.