#650 · Primary category： AI Agents & Automation
HyperAgents
Self-referential self-improving agents that can optimize for any computable task
Project last updated：07/31/26
GitHub Stars
2.7K
Forks
359
Contributors
3
License
Other
Why we included this project
HyperAgents is a research implementation that shows what happens when you let an agent rewrite its own code to get better results. A task agent works on a concrete optimization problem while a meta agent proposes changes, runs the modified code, and keeps only the changes that actually improve things. Because it genuinely executes model-generated code in a loop, it's a live demonstration of that idea rather than a paper sketch. Expect a real setup: API keys for several providers, Python 3.12, and a container build, so treat it as a harness to adapt, not a tool that works out of the box. The non-commercial license and the repo's own warning about running untrusted generated code are both worth reading before you commit.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.