All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Elixir development skills with optional Mix checks and Expert language server integration

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

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.

Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

Lightweight coding agent written in Rust, optimized for memory footprint and performance

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

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.)

Official Qt AI engineering skills for Claude Code, Codex, Copilot, Gemini,and other AI coding tools

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Metis is a coding agent that boosts AI/LLM coding performance by 50%

Keeping your agents out of trouble with sandboxed coding agent automation

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML

Help your agents create better skills

The World's First Virtual Terminal for AI Agents

A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

The open standard for agent coordination

Open-source observability & evaluation platform for AI agents and coding agents. Trace LLMs, tools, prompts, costs & agent workflows with OpenTelemetry.

Agentic dev environment for DevPods, Codespaces & Rackspace Spot — one-command setup of Ruflo orchestration (215+ MCP tools, 60+ agents upstream).

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

A lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.