💻 Dev

A tool for training multi-step agents to perform real-world tasks using GRPO.

goose is an open-source general-purpose AI agent that supports code, workflows, and various tasks.

oh-my-claudecode is a multi-agent orchestration tool for Claude Code with zero learning curve.

Open-source infrastructure for training and evaluating AI agents capable of controlling full desktop environments.

Claude Code is a terminal-based coding tool that helps you write code faster using natural language commands.

LocalAI is an open-source AI engine that supports running various models on any hardware.

A command-line tool for browser automation in AI agents.

Continue is an open-source AI code inspection tool that enforces checks in CI.

GitHub MCP Server connects AI tools directly to the GitHub platform through natural language interactions.

Sim is an open-source platform for building, deploying, and orchestrating AI agents.

An open-source AI orchestration framework for building production-ready LLM applications.

Stagehand is an AI framework for browser automation that supports both natural language and code control.

AI agent skill for persistent Markdown planning in the style of Manus.

Hindsight is an agent memory system that enables agents to learn and improve over time.

A tool enabling AI agents to use web browsers.

rLLM is an open-source framework for training reinforcement learning AI agents.

Provides voice and visual notifications for games like Warcraft III for AI coding assistants.

Solace Agent Mesh is a framework for building and orchestrating multi-agent AI systems.

GitHub Agentic Workflows allows writing workflows in natural language and running them in GitHub Actions.

Lemonade is a local AI server that enables running optimized LLMs on your own GPU and NPU.

RubyLLM is a unified Ruby framework supporting multiple AI providers for building chatbots, AI agents, and more.

fast-agent is a flexible LLM interaction tool for coding, development, and evaluation.

vocode-core is an open-source library for building voice-based LLM applications.

Acontext is an open-source skill memory layer for AI agents, automatically capturing and storing the learning outcomes of agents.