GitHub · Python
ThinkFlowLab/agentdescent
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.
- Stars
- 221
- Forks
- 29
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: agent-framework, agents, ai-agents, asynchronous, evolutionary-algorithms, gradient-descent, llm, llm-agents, optimizer, parallel
Latest data point: Nov 20, 2026 · 221 stars · 29 forks