Automated README summary
Automatically summarized from the README on 28 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Jermes is a Hermes Agent plugin that offloads small, bounded decisions from the expensive reasoning model to Jev, TypeSafe AI's System One model. It trims context, gates risky tool calls, selects skills, filters memory, and more, saving cost while keeping answers correct.
How it uses Jev
Jev makes decisions like which old context to keep, whether a tool call is dangerous, which skill to load, whether a memory write is durable, and if the agent is looping. Plain code asks Jev with typed questions and uses returned probabilities with thresholds to act, ask, or leave Hermes alone.
Primitives:choicescorenoul
Technique worth stealing
Use Jev to make bounded decisions with calibrated probabilities, then apply code thresholds to act, ask, or do nothing.
Try it
Install Hermes Agent, then run: hermes plugins install MersivMedia/jermes --enable
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 material0.74
- Shows a System One patternnot found in the excerpt0.26
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersFound in material0.98
- Is a runnable toolunclear0.60
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelunclear0.44
- Solves a common problem (0–2)score on a 0–2 scale1.17 / 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 28 Sept 2026.