Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Médula is a concurrency kernel for multiple Claude Code agents working on a single repository. It decides before each write whether to proceed, wait, or use a slow path, and ships a reproducible lab measuring coordination across six modes.
How it uses Jev
Before every write, Médula builds an intent from the agent's task and file/diff/command, then asks Jev for a collision probability. Below the low threshold it proceeds, above the high threshold it waits, and in between it routes to a slow path (Sonnet, then Opus).
Primitives:score
Technique worth stealing
Use a fast probabilistic decider to gate writes, escalating uncertain cases to a slower LLM bound by acceptance criteria.
Try it
git clone https://github.com/JoaquinRuiz/medula.git && cd medula && uv sync && (cd demo-app && uv sync) && (cd medula && uv sync)
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 projectFound in material0.82
- Shows a System One patternFound in material0.81
- Describes handling uncertaintyFound in material0.66
- Reports measured numbersnot found in the excerpt0.16
- Is a runnable toolunclear0.46
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale0.88 / 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 3 Oct 2026.