Automated README summary
Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Home Assistant conversation agent for Assist voice pipelines. It resolves device commands and questions about the home using a System One decision model, running either on TypeSafe's hosted API or locally via Ollama, so nothing has to leave the home.
How it uses Jev
Jev answers typed questions about the home state to pick the device, action and parameters for each command or query. The integration checks these calibrated answers in ordinary Python; doubtful ones ask or fall back instead of guessing. An optional LLM only writes text.
Primitives:choicescorenoul
Technique worth stealing
Gate every decision on a calibrated typed answer checked in code, and ask or fall back when confidence is low rather than letting a model guess.
Try it
Install via HACS as TypeSafe Conversation, restart Home Assistant, add the integration, and set it as the conversation agent.
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 excerpt0.35
- Shows a System One patternFound in material0.93
- Describes handling uncertaintyunclear0.44
- Reports measured numbersFound in material0.75
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.08
- Is a replica of the modelnot found in the excerpt0.19
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 2
- About JevFound in material0.93
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 22 Oct 2026.