Starred repositories
🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)
A symbolic benchmark for verifiable chain-of-thought financial reasoning. Includes executable templates, 58 topics across 12 domains, and ChainEval metrics.
Benchmark for Agentic Powerpoint Editing Tasks
CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.
ClawAegis is a lightweight plugin providing full-lifecycle runtime protection for OpenClaw.
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.
A community curated collection of AI agent failure modes and battle-tested solutions.
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line …
📄 A Claude skill for comprehensive academic paper analysis — deep reports, mind maps, peer review, and promo scripts.
Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically
AgentFlow: In-the-Flow Agentic System Optimization
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
A lightweight, lightning-fast, in-process vector database
A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
A powerful AI coding agent. Built for the terminal.
Cache Me, Catch You: Cache Related Security Threats in LLM Serving Frameworks (NDSS 2026)