Lists (17)
Starred repositories
The terminal your agents live in — a native macOS terminal for the agent era
A context-compression plugin for month-long single sessions (billions of tokens) and small context windows (a 100K context is enough), billion-context is all you need .
An open source design system that's fully customizable and agent ready
AI 短剧 · 漫剧 Skill（技能包）精选：剧本、改编、分镜、Seedance / 可灵 / MiniMax 视频提示词，千问、豆包、龙虾 OpenClaw、WorkBuddy、Claude Code、Codex 等智能体可用 | Curated agent skills for AI short drama, micro drama / microdrama, vertical dra…
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
Track 42,331+ AI benchmark, eval, dataset, and data-quality records from 40 public sources, with linked evidence and daily updates.
Open-source Grok Bot alternative for teams. Always-on bots that run on your Claude Code or Codex subscription, in chats your whole team can join.
AgentKernelArena is a platform for evaluating and training AI agents for GPU kernel optimization, combining realistic tasks, correctness validation, and performance-based rewards for reinforcement …
Codex-style goal tracking and continuation for pi.
Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context retrieval, and more explainable AI for L…
Open-source implementation of AlphaEvolve
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, M…
Craft Anything: understand how any software works, and craft your own.
Towards a More Autonomous Agent System
A massive ancient Greek world built entirely in code with three.js. Zero assets, made with Claude Code (Opus 5.5)
A Unified Framework for Efficient RSI Research
Host-side HTML sandbox for agent UIs: isolation, egress hardening, and adapters for MCP Apps, inline widgets and artifact pages
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.
Experience-Driven Black-Box Cost Control for Coding Agents
One 8 KB skill that replaces REA (Reverse Engineer Anything): plain CLI tools, no MCP. Benchmarked: 38% faster, 35% cheaper.
OpenAnt from Knostic is the leading open source LLM-based vulnerability discovery and remediation product, helping defenders proactively find and patch verified security flaws while minimizing both…
CyberGym-E2E is a large-scale benchmark built from real-world vulnerabilities in widely used open-source projects to evaluate AI agents' end-to-end cybersecurity capabilities, from discovering vuln…
🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI …