59 results
Coding tools and autonomous agents
by Browserbase·Aug 2024
Open-source AI browser automation framework combining natural language with code for reliable web automations via act(), agent(), and extract() APIs. 23k GitHub stars.
by Augment·Apr 2024
AI coding assistant with deep codebase understanding, designed for enterprise teams. Integrates with VS Code and JetBrains with full repo context.
by Cosine·Oct 2024
Autonomous AI software engineer by Cosine that takes tasks from description to working code changes, powered by the custom-trained Lumen coding model.
by esengine·Jun 2025
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability for long-running sessions. 26.3k GitHub stars.
by browser-use·Nov 2024
Open-source Python library for making AI agents interact with websites through natural browser automation. Supports vision and multi-tab browsing.
by Anthropic·Aug 2025
Anthropic's Claude browser extension for Chrome enabling agentic browsing inside a tab; launched as a research preview limited to 1,000 Max-plan users.
by OpenAI·May 2025
OpenAI's web-based coding agent that runs tasks in per-repo cloud sandboxes via chatgpt.com/codex; launched as a research preview powered by the codex-1 model.
by Google·May 2025
Google Labs asynchronous coding agent that clones repos into a cloud VM, executes multi-step tasks, and returns diffs and PRs while you work elsewhere.
by Hmbown·Mar 2025
Open-source terminal coding agent (TUI+CLI) for any model — open models first. Rust-based, reads code, makes edits, runs commands, plans multi-step tasks. 39.5k GitHub stars.
by AG2AI·Aug 2023
Open-source multi-agent conversation framework enabling cooperative AI agents with autonomous and human-in-the-loop workflows. Reached v1.0 July 2026.
by CrewAI·Dec 2023
Framework for orchestrating role-playing autonomous AI agents that collaborate on complex tasks. 55k GitHub stars, MIT licensed, 212 releases.
by Factory·Jun 2024
Agent-native software development platform with autonomous Droids that plan, write, test, and ship code across IDE or terminal workflows.
by Block·Jan 2025
Open-source AI agent by Block (Square) that runs locally for coding, research, writing, and automation. 45k+ GitHub stars, Rust-based with extensible toolkit.
by OpenAI·Feb 2026
OpenAI's macOS desktop coding agent app for orchestrating multiple parallel agents on long-running tasks, distinct from Codex CLI and IDE extension.
by GitHub·May 2025
Async GitHub agent assignable to issues; spins up a sandboxed Actions environment, edits code across a repo, and returns work as a draft pull request.
by SST·May 2025
Open-source TUI/CLI coding agent maintained by the SST team; runs in a terminal, supports 75+ LLM providers via Models.dev, and offers session sharing.
by Amp Frontier·May 2025
CLI-first frontier coding agent from Sourcegraph with remote agent execution (Orbs), plugin extensibility, and model-agnostic design. Pay-as-you-go pricing.
by Continue·May 2023
Open-source AI code assistant IDE extension supporting VS Code and JetBrains. Connects to any LLM for autocomplete, chat, and inline editing.
by Void·Nov 2024
YC-backed open-source AI code editor forked from VS Code, offering privacy-first alternative to Cursor with BYOK and local LLM support.
by ByteDance·Jan 2025
ByteDance's AI-native IDE with built-in coding agent, chat, and inline code generation. Free alternative to Cursor targeting the global developer market.
by Mistral AI·Dec 2025
Mistral's terminal-native coding CLI agent, introduced alongside Devstral 2; open-source, supports plugins, skills, hooks, and MCP servers for end-to-end code automation.
by OpenAI·Aug 2025
OpenAI's Codex extension for VS Code, Cursor, and Windsurf providing an in-editor coding-agent UI with mode/reasoning-effort switching and sign-in with ChatGPT.
by GitHub·Apr 2024
Task-centric AI workspace that turns a GitHub issue into a spec, plan, and multi-file edits, delivered as a reviewable pull request in the browser.
by All Hands AI·Mar 2024
Open-source autonomous coding agent (formerly OpenDevin) running in a sandboxed Docker environment; edits files, runs shell/browser tools, and calls LLMs.