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.

malevrigns/agent-jev

View on GitHub ↗

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.

agent-jev grew +29.4% in the last 30 days, ranks 15th of 29 in On-Device / Small Models, actively maintained, last commit 2 days ago.

Star trajectory

31 days tracked
2026-09-25396 stars today2026-10-26
Momentum

+29.4% in 30d, above the On-Device / Small Models median of +1.7%.

Maintenance

Last commit 2 days ago, fresher than the median of 11d.

How it compares in On-Device / Small Models

agent-jev
396
stars
+29.4% 30d
commit 2 days ago
On-Device / Small Models median
396
stars
+1.7% 30d
commit ~11d ago
Leader · needle
14.3k
stars
+13.2% 30d
commit 6 days ago

Ranked 15th of 29 by stars.

Language
Python
License
Apache License 2.0
Contributors
5
Forks
40
Watchers
1
Open issues
0
Releases
1
Created
2026-09-21
Stars this week
+5

You've seen where agent-jev stands today.

Get the moves before everyone else: the 5 On-Device / Small Models repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain agent-jev?

Claim this page to add your own call-to-action.

Claim this page