Open sourceJupyter Notebook · ≈7.5k stars · MIT
gepa
Reflective optimization for prompts, code, and agent-related artifacts.
GEPA applies reflective optimization to prompts, code, and other artifacts. Topics include harness engineering, agent skills, coding agents, and LLM evaluation.
Activity
- Last push
- · 12d ago
- Latest release
- v0.1.4
· 4mo ago - Last 90 days
- 0 releases
- · 4mo ago
This release ships the reflection-LM protocol and batch-based parallel proposals ([RFC #329](https://github.com/gepa-ai/gepa/issues/329), Phases 1 & 4) — the largest change to GEPA's proposal machinery since the project started, contributed by @Benzhang2004 in #369 and hardened…
- · 4mo ago
This release ships everything merged to main since v0.1.1 (March 2026): two new adapters, parallel proposal generation, reflection-cost controls, a unified LM layer, dependency security bumps, and a large expansion of the docs and showcase. Highlights LangChain adapter —…
- · 4mo ago
This release ships everything merged to main since v0.1.1 (March 2026): two new adapters, parallel proposal generation, reflection-cost controls, a unified LM layer, dependency security bumps, and a large expansion of the docs and showcase. Highlights LangChain adapter —…
- · 8mo ago
Highlights Candidate Tree Visualization — GEPA now generates an interactive HTML lineage tree of all candidates explored during optimization. Nodes are color-coded by role (best, Pareto front, seed) with hover previews and click-to-pin tooltips for reading full prompt text. The…
- · 9mo ago
Introducing optimize_anything, GEPA's new API for optimizing any text parameter. Checkout the blogpost at https://gepa-ai.github.io/gepa/blog/2026/02/18/introducing-optimize-anything/ What's Changed Automated docs and website by @LakshyAAAgrawal in…
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
In research (1)
- Do LLM Agents Still Need to Be Told How to Self-Improve?Verdict: Useful
Nov 17, 2026 · Prescribed prompt-optimization baseline that the self-organized Opus-5 teacher is compared against in Figure 3.
Neighbours on the workbench
TypeScript · ≈395k stars · MIT
openclaw/openclaw
The viral open-source personal AI assistant that really does things.
Maintained by OpenClaw Foundation
v2026.11.6releasedShell · ≈329k stars · MIT
mattpocock/skills
Small, composable agent skills for real engineering work.
Maintained by Matt Pocock (AI Hero)
MDX · ≈323k stars · MIT
obra/superpowers
An agentic skills framework and software methodology that works.
Maintained by Jesse Vincent (obra)
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintained by · 1
- gepa-aiOrganisation
Similar entries · 1
- fable-methodProject
Sources
DisclosureAdded by Harness Hub's automated review of public metadata; not independently tested.
Verified Nov 17, 2026
