Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
Create self-evolving AI agents that learn and improve by merging their changes in a parallel framework.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeGradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
agentdescent has 202 stars on GitHub. It has been forked 17 times. agentdescent is written mainly in Python. It has been in active development since 2026. agentdescent is available under the MIT license. Its main topics are agent-framework, agents, ai-agents, asynchronous.
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
agentdescent is an open-source project. It is released under the MIT license.
Yes. agentdescent is free and open source — you can use, modify and self-host it.
agentdescent is available under the MIT license.
agentdescent is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/birfy-agentdescent.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.