Collection
Autonomous AI Coding Agents
AI agents that go beyond autocomplete — they plan, write, test, and iterate on code with minimal supervision.
Autonomous coding agents represent the next leap beyond AI-assisted coding. Instead of suggesting completions, these tools take a task specification and handle the full implementation cycle: planning, coding, running tests, and iterating on failures.
The tools in this collection have all demonstrated the ability to handle multi-step engineering tasks without human intervention at each step. They vary significantly in the complexity of tasks they handle reliably.
Tools
Included in this collection
OpenHands
AI-driven development agent for software engineering tasks.
SWE Agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
GPT Pilot
The first real AI developer
Goose
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
AgenticSeek
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin993886460 (Beware of...