Organization repository on GitHub
Acta: A Decision-Centric Runtime for Agents
- Forks
- 6
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Runnable agent harness that moves pick, score and yes-no loop choices to Jev or Laya in milliseconds while reserving the language model for writing, compiling DECISION.md into executable questions.
Organization repository on GitHub
Acta: A Decision-Centric Runtime for Agents
Repo stats from the GitHub API, cached Oct 2026.
Every fork in your agent loop is a full LLM call. Not one of them is generation. Should I act? Which tool? Which file? Is this safe? Did it work? Am I done? Can I ship this? A conventional agent answers each of those by writing a sentence and parsing it back. But each is a pick, a score or a yes/no answer: one forward pass over a fixed candidate set, 10–40 ms, no tokens generated. JevLoop routes them to a decision model (Jev / Laya) and keeps the LLM for the one thing only it can do: writing.
Quoted from the project's README. Read the full README.
Watch out
The default offline judge is a flagged rule table showing loop shape rather than decision quality, and published package metadata does not match this tree so prefer git. Real backends and costs need separate measurement. Copy reviewed against the repository README on 2026-10-04, not from running it.
Forks and copies of this project in the directory. This entry is the canonical one.
Posts from builders shipping with Jev right now.