malevrigns/agent-jev
AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Weights: https://huggingface.co/aimeigaoshou/agent-jev · Website: https://malevrigns.github.io/agent-jev/ The job · Primitives · Forward pass · Results · Latency · Run it · HTTP · Repository AgentJev-0.6B does not write. You hand it a state and questions you have already phrased. One forward pass returns a probability for every option. The number of decoded tokens is zero. Use it as a framework-independent decision service wherever an agent loop needs a gate, a route, or a score. Integrate through the HTTP API or the Python client; the Claude Code hook is one optional example. Leave prose generation to a larger model. ▶ Watch the 82-second demo · MP4, 1920×1080, 8.9 MB · Original ambient soundtrack, no voice-over; Chinese and English captions are burned in, so it works on mute. Every probability and timing in it is a recorded run on one RTX 5060. A coding agent, a triage bot, or a workflow spends most…
Read the full README ↗ · Preview checked 2026-11-05T00:19:23.325Z
Inside the original README — Document outline
- The job
- Primitives
- One forward pass
- Typed Decisions
- By workflow
- By primitive
- How to read the table
- Coding gates
- Latency & throughput
- Run it
- Client
- HTTP
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
Repository facts
- Owner
- malevrigns
- Primary language
- Python
- Stars
- 317
- Forks
- 30
- Open issues + pull requests
- 6
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-09-21T16:24:42.000Z
- Last push
- 2026-09-23T09:16:37.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-09-28T12:04:05.369Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer