A candidate-scoring head returns distributions for gates, routes and scores without decoding prose or JSON answers. The README compares a benchmark-trained AgentJev specialist with Jev 1.13.0 evaluated zero-shot; these use different training conditions.
james_library — Benchmarks & Evaluation · Jev
topherchris420/james_library
ResearchDocumentedCheck pending
james_library: Benchmarks & Evaluation. Explore the Jev references, Rust source code and similar projects.
Repository description: R.A.I.N. Lab is an experimental scientific-agent architecture that separates fast local judgment, independent probabilistic evaluation, multi-agent deliberation, evidence, and authorization into distinct computational layers.🐙(Predates Karpathy's AutoResearch)
What you can build with it
Get started
Clone the repository and follow its README for install and usage. JevHunt has not run this project.
git clone https://github.com/topherchris420/james_library.gitProject facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Rust
- License
- MIT
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-02-12
- Last code update
- 2026-09-25
- GitHub stars
- 72
- Evidence checked
- Sep 26, 2026
- Metadata checked
- Sep 26, 2026
- Check status
- Check pending
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
- Cascade routing calls Jev only with explicit remote consent. Missing calibration,
Evidence commit: dcc6ae5b777040adf023d42b736315ced040216c
Discovered through: github-search.
How we review →Suggest a correction · Claim this listing · Submit a project