Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
OpenCodeProxyHub is a self-hosted AI API gateway (TypeScript + Fastify, React console) that exposes OpenCode free models through OpenAI-compatible and Anthropic-compatible interfaces, plus a TypeSafe System One endpoint, for clients like opencode and OpenAI/Claude SDKs.
How it uses Jev
The README lists jev-1.13 as a TypeSafe System One decision model served at POST /v1/systemone, noting it is not a chat model and accepts state plus typed questions returning calibrated probabilities. It does not describe which decisions Jev makes or how results are consumed in code.
Primitives:choicescorenoul
Try it
docker compose up -d, then open http://127.0.0.1:6446/app and unlock with ADMIN_PASSWORD.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.04
- Shows a System One patternnot found in the excerpt0.04
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.07
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 2
- About JevFound in material0.94
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 28 Oct 2026.