Reef adds GEPA prompt optimization and Meta-Harness evolution for self-improving agents
pliang279 · x · 2026-09-23
- Reef, the open-source continual-learning infra for self-improving agents (4.1k stars on GitHub), now supports GEPA for prompt optimization and Meta-Harness for evolving entire agent harnesses (prompts, rules, skills).
- Both run on Reef's own harness-evolution backend, which maintains algorithmic state tracking past attempts, their relationships, and performance.
- It works across various harnesses via adapters — bring your tasks and an evaluator, and Reef evolves your prompts or your whole harness.
More from coding & agent
- Framer launches Skills: teach your design agent reusable workflows, design systems and CMS rules — soleio · 2026-09-23
- TesterArmy raises $1.2M pre-seed to build AI agents that test coding-agent-built apps — fernandorojo · 2026-09-23
- Anthropic launches Claude Opus 5.5: matches Fable 5.1 on most tasks at 40% lower cost — jyangballin · 2026-09-23
- Shopify ditches React Native for native apps, and RedMonk says agents made rewrites feasible again — rseroter · 2026-09-23
- Hamel Husain & Shreya Shankar Share Their Playbook for Building AI Eval Systems — HamelHusain · 2026-09-23
- Two personal AIs tried to schedule coffee: agent interop needs a protocol — signulll · 2026-09-23