# autonomous-agent

Open-source async coding agent you can run in your own sandbox

Open-source framework from LangChain AI for building your organization's internal coding agent — the same pattern Stripe's Minions, Ramp's Inspect, and Coinbase's Cloudbot follow. Built on LangGraph and Deep Agents, Open SWE runs each task in an isolated cloud sandbox (Modal, Daytona, Runloop, or LangSmith), invokes from Slack, Linear, or GitHub, orchestrates subagents, and opens pull requests autonomously — customizable end-to-end for your codebase and conventions.

Autonomous coding agents that ship while you sleep

Twill is an autonomous coding agent platform that implements features, fixes bugs, and ships pull requests without manual intervention. Uses structured workflow of research, planning, human review, implementation in isolated sandbox, AI code review, then merge. Supports custom agent configurations with multiple LLM providers, isolated dev environments for verification, and integrations with GitHub, Linear, Sentry, Notion, and cloud platforms for end-to-end engineering automation.

Cloud browser infrastructure for AI agents

Anchor Browser provides secure cloud-managed browser infrastructure for computer-use agents. Deploy humanized Chromium instances that access any website while maintaining bot-detection evasion and authentication support. Features OmniConnect for authentication lifecycle management, Web Action Cache for deterministic workflows, and built-in VPN infrastructure. Includes free tier and paid plans supporting millions of concurrent browser sessions for scalable agent automation.

Lightweight OS for running AI agents in-process

agentOS is a portable open-source operating system for AI agents that delivers ~6ms cold starts at 32x lower cost than traditional sandboxes. Powered by WebAssembly and V8 isolates, it runs agents like Claude Code and Codex directly inside your process with granular permissions and host-managed tool access for S3, GitHub, and databases. Available as a simple npm package with no special infrastructure or vendor lock-in required.

Unified desktop manager for AI CLI tools

CC Switch is a cross-platform desktop app that unifies management of Claude Code, Codex, OpenCode, OpenClaw, and Gemini CLI from a single interface. It replaces manual config file editing with visual provider management featuring 50+ built-in presets, one-click switching, unified MCP and Skills management, and system tray quick access. Its SQLite backend ensures atomic writes that protect configuration integrity across all supported tools.

Full-lifecycle AI agent optimization and monitoring

CozeLoop is an open-source AI agent optimization platform from ByteDance's Coze ecosystem providing full-lifecycle management from development to production monitoring. It enables developers to debug agent prompts, evaluate agent performance across test cases, optimize reasoning processes, and monitor deployed agents in real-time. Built on Go and React with SDKs for Go, Python, and Node.js, CozeLoop is designed for enterprise-grade AI agent development and operation.

Code management platform for AI coding agents

Entire is an AI-native code management platform designed for teams managing fleets of AI coding agents. Founded by former GitHub CEO Thomas Dohmke, it records the reasoning and instructions behind AI-generated code alongside the code itself, making agent-written software easier to review, audit, and maintain. Launches with Checkpoints, an open-source CLI tool that logs prompts and token usage for Claude Code and Google Gemini CLI, with more agent integrations planned.

Open-source platform for managing AI coding agents as teammates

Multica is an open-source managed agents platform that lets you assign coding tasks to AI agents like Claude Code and Codex as if they were team members. It provides a unified dashboard for task assignment, execution monitoring, and skill reuse across local and cloud compute environments. With multi-workspace support, team-level isolation, and reusable skill compounding, Multica turns autonomous coding agents into organized, trackable development resources.

AI agent that builds other AI agents

Archon is an open-source AI meta-agent created by Cole Medin that autonomously builds, refines, and optimizes other AI agents. Now evolving into Archon OS, it serves as a knowledge and task management backbone for AI coding assistants. The system uses an agentic coding workflow with framework knowledge bases for Pydantic AI, LangGraph, and other agent frameworks, enabling developers to describe what they need and let Archon generate the agent code, test it, and iterate until it works.

Parallel coding agent environment by Imbue for complex projects

Sculptor by Imbue is a parallel coding agent environment that enables multiple AI agents to work simultaneously on different parts of a codebase. It provides sandboxed execution environments where agents can write, test, and iterate on code independently before merging changes. Designed for large-scale software projects where single-agent approaches hit context and coordination limits.

AI coding agent by JetBrains for autonomous task execution

Junie is JetBrains' AI coding agent that handles engineering tasks autonomously within JetBrains IDEs and from the terminal. It plans multi-step workflows, executes code changes, runs tests, and verifies results using full project context. Supports BYOK with Anthropic, OpenAI, Google, and others. Achieves 60.8% on SWE-bench Verified. Available as IDE plugin and CLI.

Email API service that gives AI agents their own inboxes and identities

AgentMail is a YC S25 startup that provides email infrastructure specifically designed for AI agents. It gives each agent its own email address and inbox, enabling agents to send, receive, and manage email conversations independently. With $6 million in seed funding from General Catalyst and Paul Graham, and over 500 B2B customers, AgentMail solves the identity and communication gap that arises when organizations deploy autonomous agents that need to interact via email.

ByteDance's open-source LLM coding agent with multi-provider support

Trae Agent is ByteDance's open-source software engineering agent that autonomously resolves GitHub issues, fixes bugs, and implements features using any LLM provider. It supports OpenAI, Anthropic, Doubao, Azure, Ollama, and Gemini backends, making it one of the most provider-flexible coding agents available. With over 11,000 GitHub stars and a modular research-friendly architecture, it offers a strong alternative to Western-centric coding agents.

Human-in-the-loop approval and oversight layer for AI coding agents

HumanLayer is a YC-backed platform that adds human approval, oversight, and escalation workflows to AI coding agents. Instead of letting agents execute autonomously, HumanLayer provides checkpoints where humans review and approve agent actions before they touch real codebases and infrastructure. It bridges the gap between autonomous AI coding and enterprise-safe deployment by making human oversight programmable.

ByteDance's open-source multimodal desktop agent with vision-based GUI automation

UI-TARS Desktop is ByteDance's open-source multimodal AI agent that automates desktop and browser interactions using computer vision rather than DOM selectors or accessibility APIs. Powered by the UI-TARS vision model, it can understand and operate any graphical interface by looking at screenshots, making it capable of automating applications that traditional browser automation tools cannot reach, including native desktop apps and complex web UIs.

Rust-based agent OS with built-in security, WASM sandboxing, and multi-agent runtime

OpenFang is an open-source agent operating system built in Rust that provides a secure multi-agent runtime with WASM sandboxing, auditability layers, and multi-channel communication. It goes beyond typical orchestration SDKs by treating agent security and operational isolation as first-class concerns, making it suitable for teams deploying agents in environments where trust boundaries and audit trails matter.

Behavioral control layer for reliable customer-facing AI agents

Parlant is an open-source framework that adds behavioral governance to conversational AI agents. Instead of relying on prompt engineering alone, it lets teams define explicit policies, conversation guidelines, and behavioral rules that agents follow predictably across multi-turn interactions. Parlant sits between the LLM and the user-facing interface, enforcing consistent agent behavior for customer support, sales, and service automation use cases.

Multi-agent orchestration layer for OpenAI Codex CLI

Oh My Codex (OMX) transforms OpenAI Codex CLI into a coordinated multi-agent system. It layers workflow orchestration, persistent memory, team-based parallel execution via tmux worktrees, and a live HUD dashboard on top of standard Codex. OMX provides 30+ role-specialized agents and 40+ workflow skills covering planning, execution, verification, TDD, security review, and autonomous research loops.

Transparent AI agent framework with 100+ skills and real-time visibility

Agent Zero is an open-source general-purpose AI agent framework with 16,700+ GitHub stars that uses the computer itself as a tool. Unlike structured orchestration frameworks, it provides full transparency where every thought, action, and tool call is visible and editable in real time, supporting 100+ extensible skills.

Scalable browser infrastructure for AI agents

Hyperbrowser is a YC S24-backed cloud browser platform purpose-built for AI agent automation at scale. It provides managed browser instances with built-in CAPTCHA solving, residential proxy rotation, and anti-bot bypass, serving as the infrastructure layer that tools like browser-use, Stagehand, and Skyvern run on top of for reliable web interaction.

Secure sandboxed runtime for AI agent execution

NVIDIA OpenShell provides kernel-level isolation for AI agent workloads with Landlock, seccomp, and network namespace sandboxing. Announced at GTC 2026 with 17 enterprise partners including Adobe, Atlassian, SAP, and Salesforce, it offers declarative YAML policy enforcement, L7 HTTP inspection, and GPU passthrough — purpose-built to contain the blast radius when autonomous coding agents interact with filesystems and networks.

Autonomous AI pentester for web apps and APIs

Shannon is an autonomous AI-powered penetration testing tool that achieves a 96.15% success rate on the XBOW benchmark — significantly above the industry average. Using a multi-agent pipeline built on Anthropic's Agent SDK and Playwright, it performs reconnaissance, vulnerability analysis, exploitation, and reporting on web applications and APIs, having discovered 7 zero-day vulnerabilities in production software.

Multi-agent orchestration plugin for Claude Code

Oh My ClaudeCode (OMC) is a plugin for Claude Code that adds multi-agent orchestration with 32 specialized agents, smart model routing between Haiku and Opus, and five execution modes including fully autonomous Autopilot and parallel Ultrapilot. It provides 40+ skills, a real-time HUD statusline, and lifecycle hooks — transforming Claude Code into a coordinated AI development team with zero configuration required.

Open-source personal AI agent for messaging apps

OpenClaw is a free, open-source AI agent framework that turns any LLM into an autonomous personal assistant accessible through messaging apps like WhatsApp, Telegram, Discord, and Signal. Running entirely on your local machine via a Node.js gateway, it connects AI models to system tools, browsers, files, and APIs for multi-step task execution with persistent memory across sessions.