aionedge.JevForge
Open research: an end-to-end stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, local serving, and a preliminary RLCD baseline.
- GitHub stars
- 16 as of 2026-09-22
- Forks
- 5
- Language
- Python
- License
- Check upstream
- Created
- 2026-09-19
- Last updated on GitHub
- 2026-09-23
What Jev does in JevForge
The project describes itself this way: Open research: an end-to-end stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, local serving, and a preliminary RLCD baseline. In the Community additions category, Jev typically decides a single well-defined judgment, such as a label, a score or a yes/no check.
Verification
Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.
How Community additions projects use Jev
Projects added from community lists and direct submissions. Many are small, single-purpose experiments, which makes them some of the easiest places to see how a Jev question is framed in real code.
Related Jev projects in Community additions
- jev-reflex-autonomy-labkhordoo/jev-reflex-autonomy-labDrone autonomy: a multi-drone lab where Jev supplies the reflex decisions, with an optional slower strategy layer guiding them.★ 16
TypeScript - feelingsBoundaryML/feelingsBAML language support for an AI if-statement: `.feels()` as a real, typed method backed by a decision model.★ 15
BAML - lorenziniNanako0129/lorenziniClaude Code skills that wait for CodeRabbit, Copilot or Codex to finish reviewing a pull request, then judge whether the verdict actually permits a merge.★ 17
Shell - jevvyPanAchy/jevvyPlugins for coding agents, starting with one that auto-approves shell permission requests it judges harmless and passes everything uncertain to the normal flow.★ 15
TypeScript - JarvisCorePrescott-Data/jarviscore-frameworkAgent frameworks: Python multi-agent runtime that ships Jev natively from 1.12, where agents ask typed `Choice`, `Score` and `Noul` questions through a decision client separate from the text model, the Kernel picks a specialist subagent by `Choice`, and each retrieved RAG passage is withheld from the generating model when its prompt-injection `Noul` exceeds 0.70.★ 15
Python - dsh-jevbuberlo/dsh-jevDecision layer for DeepSeek Harness whose failure policy rejects the value `allow` at configuration time, from plain JavaScript as well as TypeScript. Its verify script installs the built tarballs into a fresh consumer before testing them.★ 15
TypeScript