COMMUNITY OBSERVEDMetric claims: AUTHOR REPORTEDSOURCE AUDITED🤖 Jev Agent

JevLoop

An agent loop where the decisions cost no LLM call.

Overview & result

zjunlp shows JevLoop, built on Jev: An agent loop where the decisions cost no LLM call.

From the original post

JevLoop by @zjunlp: An agent loop where the decisions cost no LLM call.

— zjunlp

How Jev fits in the loop

  1. The agent loop is declared as decision nodes in a DECISION.md file; the reference loop has seven.
  2. Each fork (act or not, which tool, which file, is it safe, did it work, is it done) goes to a decision model as a pick, a score or a yes/no.
  3. The backend is the hosted Jev API if a key is set, otherwise a local Laya server.
  4. The LLM is called only to write: once, plus at most one revision.

How to reproduce

  1. Review the source documentation and repository at https://github.com/zjunlp/JevLoop.
  2. Configure environment with TypeSafe Jev / System One API keys.
  3. Run test prompts against the decision endpoints.

Why this build matters

Shows Jev in practical use for browser and autonomous agents.

Limitations

  • The quick-start run uses a rule table as judge; the README says it shows the shape of the loop, not decision quality.
  • With no backend available, every step escalates.
  • The README's own numbers show decisions can take a large share of wall-clock time on a local backend.

Patterns