Stars
An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27 "sandboxes" scored.
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
EOS (Entrepreneurial Operating System) skills for Claude Code. Run your business on EOS with AI.
Open-source local-first AI agent for desktop work. No account, no telemetry: use local models with Ollama/Rapid-MLX or bring your own provider key.
Adaptive Test-time Learning and Autonomous Specialization
Dead-simple Bun CLI that runs Codex and Claude Code in a loop.
Build Real-Time Knowledge Graphs for AI Agents
A plain-text memory system for AI agents. Clone it, point your agent at it, start remembering.
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases
Specification and documentation for Agent Skills
Single-file memory layer for AI agents, sub mili-second RAG on Apple Silicon. Metal Optimized On-Device. No Server. No API. One File. Pure Swift
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on …
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
Stepped is a Rails engine for orchestrating complex workflows as a tree of actions
An agentic skills framework & software development methodology that works.
a graph explorer of the Epstein emails