10 open-source repos that rewrite prompts and evolve agent workflows
victor_explore · x · 2026-10-28
A curated GitHub compilation (stars checked Oct 2026) of 10 open-source projects for automatic prompt optimization and self-evolving agent workflows: rewriting prompts, scoring versions on test sets, and learning from failed runs.
The lineup: DSPy (Stanford NLP, 39k stars, program-not-prompt), Opik (Comet ML, 22k stars, LLM observability/eval/tracing), Agent Lightning (Microsoft, 19k stars, critiques and rewrites agent prompts), GEPA (7k stars, reflection + Pareto-efficient evolutionary search), AdalFlow (4k stars, PyTorch-like LLM workflow tuning), PromptWizard (Microsoft, 4k stars, self-refining prompts), TextGrad (4k stars, LLM critiques edit prompts via textual gradients), EvoAgentX (3k stars, self-evolving agents), Ax (3k stars, DSPy-style optimizers for TypeScript and more), and Agentic Context Engine (3k stars, agents learn lessons from mistakes).
More from coding & agent
- A fleet of agents tackles packing and kernel optimization to test a new trainer — cephaloform · 2026-10-28
- User splits work between Claude and Meta Muse: one thinks, one runs errands — gnimiy · 2026-10-28
- A Comprehensive Guide to Building Agentic AI Systems, from Architectures to Guardrails — goyalshaliniuk · 2026-10-28
- Delta, JPMorgan, Amazon are blocking AI agents — permission is AI's next big fight — Arindam_1729 · 2026-10-28
- Magpie adds animation to show data masking doesn't degrade agent behavior — dotey · 2026-10-28
- Google open-sources Elephant-Goldfish: design-review skills for AI coding agents — sven_ai · 2026-10-28