humanlayer

humanlayer

The best way to get AI coding agents to solve hard problems in complex codebases.

Stars: 4502

Visit
 screenshot

HumanLayer is a Python toolkit designed to enable AI agents to interact with humans in tool-based and asynchronous workflows. By incorporating humans-in-the-loop, agentic tools can access more powerful and meaningful tasks. The toolkit provides features like requiring human approval for function calls, human as a tool for contacting humans, omni-channel contact capabilities, granular routing, and support for various LLMs and orchestration frameworks. HumanLayer aims to ensure human oversight of high-stakes function calls, making AI agents more reliable and safe in executing impactful tasks.

README:

Wordmark Logo of HumanLayer

Close your editor forever.

CodeLayer is an open source IDE that lets you orchestrate AI coding agents.

It comes with battle-tested workflows that enable AI to solve hard problems in large, complex codebases.

Built on Claude Code. Open source. Scale from your laptop to your entire team.

GitHub Repo stars License: Apache-2

Join Waitlist | Discord


"Our entire company is using CodeLayer now. We're shipping one banger PR after the other. It is so f-ing good. Unbelievable dude."

– René Brandel, Founder @ Casco (YC X25)


  • Superhuman for Claude Code - Keyboard-first workflows designed for builders who value speed and control.

  • Advanced Context Engineering - Scale AI-first dev to your entire team, without devolving into a chaotic slop-fest.

  • M U L T I C L A U D E - Run Claude Code sessions in parallel. Worktrees? Done. Remote cloud workers? You got it.


"This has improved my productivity (and token consumption) by at least 50%. Taking a superhuman style approach just makes soo much sense. Also, its so freaking cool to look back at all the work you've done in a day."

– Tyler Brown, Founder @ Revlo.ai


From the team that brought you "Context Engineering"

Leading experts on getting the most out of today's models.

This talk, given at YC on August 20th, 2025 lays out the groundwork for using AI to solve hard problems in complex codebases.

A set of principles for building reliable and scalable LLM applications, inspired by the original 12-Factor App methodology.

The original repo that coined the term "context engineering" back in April 2025.

A weekly conversation about how we can all get the most juice out of todays models with @hellovai & @dexhorthy


For Teams

Invest in outcomes, not tools.

Want to scale AI-first development to your entire org? Get tailored workflows, custom integrations, and cutting-edge advice.

HumanLayer's expert engineers will ship in the trenches with you and your team until everyone is a 100x engineer.

📧 Shoot us an email at [email protected], mention your team size and current AI development stack.


Quick Start

# Coming soon - join the waitlist for early access
npx humanlayer join-waitlist --email ...

Legacy Documentation

Looking for the HumanLayer SDK documentation? See humanlayer.md

Contributing

CodeLayer and the HumanLayer SDK are open-source and we welcome contributions in the form of issues, documentation, pull requests, and more. See CONTRIBUTING.md for more details.

License

The HumanLayer SDK and CodeLayer sources in this repo are licensed under the Apache 2 License.


Star History Chart

For Tasks:

Click tags to check more tools for each tasks

For Jobs:

Alternative AI tools for humanlayer

Similar Open Source Tools

For similar tasks

For similar jobs