jevbooks

← All projects

system1-core

suzyski/system1-core

Dual-engine reflexive co-processor for AI agents: routing, gating, compression, verification.

Agent Decisions0.66Runner-up: Classification & RoutingFunnel
Automated README summary

Automatically summarized from the README on 17 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

System 1 Core is a Python co-processor that sits in front of autonomous coding agents (Claude Code, Cursor, Codex) to make fast, deterministic sub-second decisions on routing, safety, context compression, and output verification.

How it uses Jev

Jev powers the decision engines: gate_action classifies command risk (e.g. high_risk_destructive), route_skill matches runbooks, and verify_output scores goal satisfaction (e.g. fully_satisfied). Results are returned as top_label and scores dicts that code checks to raise errors or assert completion.

Primitives:choicescore

Technique worth stealing

Gate destructive actions and verify task completion with a fast typed classifier before the heavy LLM reasons.

Try it

Install via install.sh or pyproject.toml, then call system1 route/gate/compress/verify or the Python API.

View on GitHub

Start using Jev: API key and your first request →

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 projectunclear0.54
  • Shows a System One patternFound in material0.82
  • Describes handling uncertaintynot found in the excerpt0.09
  • Reports measured numbersnot found in the excerpt0.28
  • Is a runnable toolFound in material0.69
  • Top-10 learning shortlist signalnot found in the excerpt0.16
  • Is a replica of the modelnot found in the excerpt0.34
  • Solves a common problem (0–2)score on a 0–2 scale1.60 / 2
  • About JevFound in material0.94
Signals
Jev is core to the project0.54Shows a System One pattern0.82Describes handling uncertainty0.09Reports measured numbers0.28Is a runnable tool0.69Top-10 learning shortlist signal0.16Is a replica of the model0.3400.51Solves a common problem (0–2)1.60 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.84Viewfinder0.2200.51

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 17 Oct 2026.