Automated README summary
Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A reliability and memory plane around OpenClaw agents: claims every Slack message, routes it to the right work, runs it as a durable Temporal workflow, judges replies with a separate evaluator, and keeps deep searchable memory. Runs Aura, a personal Slack assistant, in production.
How it uses Jev
Jev answers typed questions about each incoming Slack message, given a hybrid evidence pack (full-text and vector search over running tasks, finished tasks, memory, plus recent dialogue). Below Jev's thresholds an LLM analyst decides. The outcome routes the message: attach to running work, follow-up, new task, clarifying question, or acknowledgement.
Primitives:choicescorenoul
Technique worth stealing
Use Jev as a typed router over a retrieval evidence pack, with an LLM analyst as fallback below confidence thresholds.
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 projectunclear0.50
- Shows a System One patternFound in material0.73
- Describes handling uncertaintyFound in material0.85
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.67 / 2
- About JevFound in material0.98
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 24 Oct 2026.