SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
TypeScript multi-agent framework that runs in your own environment: consequential actions wait for approval and every run leaves a verifiable record. Describe the goal, not the graph. 13 built-in providers (Claude, OpenAI, Gemini, DeepSeek and more) plus any OpenAI-compatible endpoint, local models included.
The World's First Virtual Terminal for AI Agents
OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.
Local first, desktop companion platform with animated pets, plugin SDK and coding-agent integrations.
Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 commands, 19 CLI tools, 2 MCP servers, autonomous hunt loops, exploit chain builder.
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.
The Rust SDK for building coding agents. Tools, streaming, graph, sub-agent orchestration, MCP — as composable functions
Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.
Deterministic safety solutions for probabilistic AI agents
The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already in place.
AI said it finished. Flyto2 shows the proof.
Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.
Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.
OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.
Control 1 or more machines using computer use tools that integrates with your agents
Vercel AI SDK community provider for Claude Agent SDK
C# coding-agent harness (.NET 10, Microsoft Agent Framework) — sessions, tools, permissions, providers, MCP, plugins
Composable agent runtime with enforced isolation boundaries
Computer-Use SDK for E2E QA Testing
A Lisp with first-class LLM primitives, implemented in Rust