TianyuCodings/JevHarness
LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
English | 简体中文 Let an LLM write a task-specific harness for Jev. Run it, inspect its decisions, and optionally improve it using rewards and complete execution traces. A harness turns task observations into useful features, constructs Jev questions and criteria, and combines the structured answers into actions. The authoring LLM can change the code, questions, graph, and memory. Once the harness is fixed, execution uses that code and its Jev calls; it does not need the authoring LLM on every decision. Reason deeply during development. Freeze the strategy. Let Jev make fast, fuzzy decisions. A strong LLM brings broad intelligence and deep reasoning, but generating that reasoning for every action adds latency and cost. Jev provides fast, lightweight judgment with more limited capacity for open-ended reasoning. JevHarness combines these strengths: let the LLM write a task-specific harness, then optionally improve it using rewards and complete execution traces. The harness preserves…
Read the full README ↗ · Preview checked 2026-11-09T09:43:53.265Z
Inside the original README — Document outline
- JevHarness
- Install in Claude Code
- Start with the example
- Latency
- How it works
- Build your own task
- Runtime and credentials
- Repository map
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.
Repository facts
- Owner
- TianyuCodings
- Primary language
- Python
- Stars
- 337
- Forks
- 17
- Open issues + pull requests
- 2
- License
- Not reported — inspect the license file
- Archived
- No
- Default branch
- main
- Created
- 2026-09-21T08:59:46.000Z
- Last push
- 2026-09-21T10:39:01.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-28T12:04:05.369Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer