JevRev
Project premised on offloading cheap routing decisions from an LLM to a decision model while the LLM writes, tests and revises.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
JevRev is listed with a single summary: an LLM can imagine, write, test and revise, but it should not have to make every cheap routing decision by itself. That suggests a workflow where a Jev-style decision model handles routine routing or gating steps in a write, test and revise loop, leaving generation to the LLM.
No README was available, so the specific decisions, interfaces and maturity are not confirmed. The licence is listed as MIT.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which route should this step take in the write-test-revise loop?(inferred) | — |
How it works
- LLM produces or revises work
- Decision model handles cheap routing decisions between steps
- Loop continues until done
Strengths
- Aims to reduce LLM calls spent on routing
Caveats
- No README available to verify functionality
- Maturity unknown
At a glance
- Type
- Project
- License
- MIT
Use cases and integrations
How curated lists describe it
Your LLM can imagine, write, test, and revise. It should not have to make every cheap routing decision by itself.
logicrw/awesome-jev-projects
Frequently asked questions
What is JevRev?
A project that offloads cheap routing decisions from an LLM to a decision model, per its listing.
How do I run it?
No documentation was available.
What licence does it use?
MIT, according to the listing.
Related projects
One skill and MCP server for Claude Code, Codex and Hermes where Jev gates large-model turns, routes models and guards Git steps.
MCP serverbetaPythonRuns Claude Code on Opus 5.5 with Jev re-picking reasoning effort after every tool batch, via per-message effort so the cache survives.
ProxybetaTypeScriptTerminal coding agent where an LLM reads, edits and runs code, and Jev makes a few optional side decisions.
ProjectbetaTypeScriptSelf-improving multi-platform agent harness with an optional Jev companion for typed judgments and per-session model routing.
ServicebetaTypeScriptSupervisor-Lead-Peer roles for a team of Paseo coding agents, with opt-in Jev routing recorded as a receipt in shadow mode.
PluginbetaMulti-agent Codex factory: Jev decides task shape, decomposition and routing, and failures are classified, not blindly retried.
ProjectprototypePython