agent

Community-driven project to build an open autonomous AI software engineer.

Autonomous coding agent for VS Code—plan/act modes, terminal execution, MCP, bring-your-own model.

All-in-one assistant/extension with real-time web access for on-page research and actions.

Realtime assistant with native tool use and search; designed for deep work and multi-step tasks.

AI software engineer that plans multi-step tasks, runs tests, and creates pull requests.

Autonomous agent that builds production-ready apps from chat with long runtimes and self-testing loops.

Asynchronous coding agent using Gemini—clones repos, plans changes, makes diffs and pull requests.

Terminal-based pair-programming agent that plans and edits code across repos with multi-step flows.

Local agent that runs code (Python/JS/Shell) from natural language—terminal-first workflow.

An AI agent with its own browser that can click, type, and complete web tasks autonomously.

Open-source deep-research agent built on LangGraph; configurable models, tools, and MCP servers.

Agentic coding in the browser; generate apps from prompts and deploy instantly.

General-purpose, multi-step agent that plans and acts using a toolbox to finish tasks end-to-end.