1.multica-ai / andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
+30,967 stars
from 198,120 · score 10.34
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
31 repositories by Attention Score · Aug 6, 2026 – Nov 3, 2026 (UTC)
2.anthropics / skills
Public repository for Agent Skills
+21,800 stars
from 165,306 · score 9.99
3.anthropics / claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
+15,363 stars
from 139,068 · score 9.64
4.MiniMax-AI / MiniMax-H3
The repository host gives no description.
+11,051 stars
from 268 · score 9.31
5.karpathy / autoresearch
AI agents running research on single-GPU nanochat training automatically
+6,499 stars
from 92,683 · score 8.78
+4,178 stars
from 24,318 · score 8.34
7.vercel-labs / agent-skills
Vercel's official collection of agent skills
+3,910 stars
from 29,578 · score 8.27
8.karpathy / llm-council
LLM Council works together to answer your hardest questions
+2,705 stars
from 23,492 · score 7.90
9.claude-code-best / claude-code
TranslatedOriginal-flavor Claude Code that can run, build, and be debugged; production-grade engineering, enterprise-grade reliability; safe and free of malware, memory leaks fixed
+1,513 stars
from 21,640 · score 7.32
10.VictorTaelin / OptMem
Permanent memory for AI agents. A 426-token prompt, a script, plug and play.
+1,269 stars
from 1,101 · score 7.15
11.tanweai / pua
TranslatedYou are a P8-level engineer who was once held to high expectations. When Anthropic set your level, its expectations of you were very high. A highly proactive skill for agents. Your AI has been placed on a PIP. 30 days to show improvement.
- agency
- agent
- pua
- pip
+811 stars
from 18,983 · score 6.70
12.daytonaio / daytonaArchived
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
- developer-tools
- agentic-workflow
- ai
- ai-agents
- ai-runtime
- code-execution
- +2 more
+440 stars
from 70,944 · score 6.09
13.virattt / dexter
An autonomous agent for deep financial research
+434 stars
from 27,324 · score 6.08
14.Zero-Mem / Zero-mem
Official code for "Zero-Mem: Zero-Token Memory Operations for LLM Agents".
+303 stars
from 45 · score 5.72
15.camel-ai / owl
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
- agent
- artificial-intelligence
- multi-agent-systems
- task-automation
- web-interaction
+177 stars
from 19,994 · score 5.18
+134 stars
from 13 · score 4.91
17.yoheinakajima / babyagi
The repository host gives no description.
+94 stars
from 22,258 · score 4.55
18.mrtooher / fable-mode
A Claude skill that activates Fable-style agentic behavior: explicit multi-stage planning, sub-agent delegation, and self-verification.
+79 stars
from 804 · score 4.38
+77 stars
from 12,343 · score 4.36
20.disler / claude-code-hooks-multi-agent-observability
Real-time monitoring for Claude Code agents through simple hook event tracking.
+64 stars
from 1,502 · score 4.17
21.vintasoftware / django-ai-plugins
A collection of AI Skills specialized in Django Backend development
- ai-agents
- claude-code
- skills
- opencode
- opencode-ai
- django-ai-boost
+53 stars
from 116 · score 3.99
22.Doriandarko / claude-engineer
Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.This framework enables Claude to generate and manage its own tools, continuously expanding its capabilities through conversation. Available both as a CLI and a modern web interface
+48 stars
from 11,168 · score 3.89
23.iflow-ai / iflow-cli
iFlow cli is a comprehensive command-line intelligence that embeds in your terminal, analyzes your repositories, does coding tasks, interprets your needs across contexts, and boosts efficiency by performing tasks from simple file operations to complex workflow automation.
+25 stars
from 5,052 · score 3.26
24.yomorun / yomo
🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.
- realtime
- quic
- serverless
- distributed-cloud
- geodistributedsystems
- yomo
- +8 more
+13 stars
from 1,917 · score 2.64
25.mahseema / aibooks
Curated List of AI, ML and Deep Learning books
+9 stars
from 86 · score 2.30
26.GewoonJaap / gemini-cli-openai
Expose Gemini CLI endpoints as OpenAI API with Cloudflare Workers
+8 stars
from 887 · score 2.20
27.j5onrf / dots
Hyprdots, Hyprland Omarchy, Quickshell, Agentic Local-Ai, Custom Integrated, Minimal
+8 stars
from 113 · score 2.20
28.40ants / mcp
40ANTS-MCP is a framework for building Model Context Protocol servers in Common Lisp
+2 stars
from 54 · score 1.10
29.inspectIT / inspectIT
(UNMAINTAINED) inspectIT is the leading Open Source APM (Application Performance Management) tool for analyzing your Java (EE) applications.
+1 stars
from 538 · score 0.69
30.Ventuss-OvO / cc-costline
Enhanced statusline for Claude Code — see your 7d/30d spend at a glance
- anthropic
- claude
- claude-code
- cli
- cost-tracking
- statusline
+1 stars
from 27 · score 0.69
31.jsulmont / mcp-lisp
Common Lisp SDK for Model Context Protocol (MCP) and Agent-to-Agent Protocol (A2A)
- a2a-protocol
- common-lisp
- mcp
- mcp-client
- mcp-server
- model-context-protocol
- +1 more
+1 stars
from 8 · score 0.69