💻 Dev

Langroid is a lightweight and extensible Python framework for building LLM-based multi-agent applications.

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.

Free AI code completion plugin for local or API hosting, compatible with Visual Studio Code.

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

An open-source terminal AI assistant and Python framework supporting tool calling, sandbox execution, multi-agent teams, and more.

Run open-weight LLMs locally with offline support and OpenAI API compatibility.

Nimbalyst is an open-source visual workspace that supports running and collaborating with multiple coding agents in parallel.

An open-source, PyTorch-like runtime for multi-agent and multi-session environments.

Jarvis Registry is an enterprise-grade MCP and A2A proxy gateway platform that provides secure, controlled access to enterprise tools.

A multi-agent-based knowledge engine for code repositories, supporting various AI IDEs.

Multi-agent system that runs AI coding tasks in parallel using tmux.

AIDE ML is an LLM-based machine learning engineering agent that automates AI research and development.

Happier is a cross-device client supporting multiple AI coding tools with end-to-end encryption.

AutoCVE is a multi-agent-based automated CVE discovery platform for source code auditing, vulnerability validation, and report generation.

CodeGraphContext is an MCP server and CLI tool that indexes local code into a graph database, providing context for AI assistants.

Open-source AI chatbot development kit by Vercel, supporting multiple frontend frameworks.

ShowUI is an open-source, end-to-end, lightweight vision-language-action model designed for GUI agents.

Harmonist is a portable AI agent orchestration framework that enforces code changes via mechanical protocols.

BoxLite is a lightweight computational substrate designed for AI agents, running both locally and in the cloud.

Autensa is an autonomous product engine that conducts market research, generates features, and submits code via AI agents.

A quadrotor control environment for single and multi-agent reinforcement learning.

Observal is a unified proxy registration and analytics platform supporting multiple IDEs.