Automated README summary
Automatically summarized from the README on 15 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Foreman is a Python asyncio runtime that supervises coding agents (Codex, OpenCode, Hermes, Deep Agents) working on free-form software jobs. It independently assesses completion, requirements, tests, worker health, and human escalation.
How it uses Jev
Jev answers typed checks like implementation_complete, tests_sufficient, worker_stuck, and needs_human using bounded factory evidence (job, diffs, output tails, git status, events). Probabilities feed Python policy that decides continue, steer, stop, retry, verify, or finish.
Primitives:choicescorenoul
Technique worth stealing
Separate slow generative coding from fast semantic supervision via pluggable responsibilities and batched typed decision-model checks.
Try it
FOREMAN_WORKER_BACKEND=opencode foreman run --repo ./my-project --job "Add request retries"
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 excerpt0.18
- Shows a System One patternunclear0.43
- Describes handling uncertaintynot found in the excerpt0.19
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalnot found in the excerpt0.36
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.87 / 2
- About JevFound in material0.95
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 15 Oct 2026.