Agent Registry

A coding agent for low-cost models that runs commands inside native sandboxing, switches providers/models and harnesses from the terminal, and can test web and native apps through a built-in QA skill.

Aider lets you pair program with LLMs in your terminal to start a new project or build on an existing codebase, connecting to almost any LLM (cloud or local), mapping your codebase, integrating with git, and supporting features like voice-to-code, image/web-page context, and automatic linting and testing.

MetaGPT assigns different roles (product managers, architects, project managers, engineers) to GPTs to collaborate on complex tasks. It takes a one-line requirement as input and outputs user stories, competitive analysis, requirements, data structures, APIs, and documents.

OpenHands Agent Canvas is a self-hosted developer control center that runs coding agents and automations across local, remote, and cloud backends, letting you start conversations and automate everyday tasks like generating reports to Slack or decomposing GitHub issues into tasks.

JARVIS (HuggingGPT) is a collaborative system that uses an LLM as a controller to connect numerous expert AI models from Hugging Face Hub, planning tasks, selecting models, executing them, and generating responses to solve complex AI tasks from user requests.

AIHawk is an AI web agent that automatically applies to jobs on behalf of job seekers.

Pipali is an AI co-worker that runs on your computer and safely interacts with files and the web to complete real work — researching across documents and the web, creating deliverables (docs, spreadsheets, email, events, personal apps), and automating routine workflows.

Agent TARS is a general multimodal AI agent that brings the power of GUI Agent and Vision into your terminal, computer, browser, and product, providing a workflow closer to human-like task completion through multimodal LLMs and integration with real-world MCP tools. It primarily ships with a CLI and Web UI. The TARS stack also includes UI-TARS Desktop, a desktop application providing a native GUI Agent based on the UI-TARS model.

An agent that enables multimodal models to operate a computer by viewing the screen and deciding on a series of mouse and keyboard actions to reach an objective, using the same inputs and outputs as a human operator.

OWL is a multi-agent collaboration system for general assistance in real-world task automation, enabling AI agents to collaborate through dynamic interactions across diverse domains. It achieves a 69.09 average score on the GAIA benchmark.

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. It refines its research direction over time, dives deeper into topics, and produces comprehensive markdown reports with findings and sources.

DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source agent that orchestrates sub-agents, memory, and sandboxes to perform a wide range of tasks, powered by extensible skills.

STORM is an LLM system that writes Wikipedia-like articles from scratch based on Internet search. Co-STORM extends it to enable human–AI collaborative knowledge curation through a collaborative discourse protocol and a dynamically updated mind map.

A "junior developer" agent that scaffolds an entire codebase from a product spec, and can also be imported as building blocks to embed code generation inside your own app.

GPT Pilot is an AI developer that writes most of the code for a full, production-ready app step by step — building features, debugging them, and asking for review — while a developer oversees the implementation. It is the core technology behind the Pythagora VS Code extension.

An open-source pair programmer that interactively edits code across multiple files, explores codebases, writes configs and tests, fixes bugs, and explores architecture, accessing only files in the directory it is started from.

Devika is an agentic AI software engineer that understands high-level human instructions, breaks them into steps, researches relevant information, and writes code to achieve the given objective using large language models, planning and reasoning algorithms, and web browsing.

An agent that generates and improves software from natural language instructions: it lets you specify software in natural language, watches as an AI writes and executes the code, and can implement improvements on request.

ChemCrow accurately solves reasoning-intensive chemical tasks by using a collection of chemical tools including RDKit, paper-qa, and chemistry databases like Pubchem and chem-space.

An AI browser agent that gives a model a real browser/computer action space, persistent tools, and recovery loops to automate web tasks like form-filling, grocery-shopping, and personal-assistant tasks.