yoshi

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed.

What it does

Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy. Agent plumbing where probabilities beat regex on model output. Fork the pattern, not the prose.

Tags in the wild: agent tooling, agents. The repo has install steps, env vars, and recent commits if you are deciding whether to depend on it.

Related products

Hand-picked neighbors with rich profiles or overlapping tags.

IntegrationsTypeScript5,253

DemoFeatured

eve

Vercel's agent framework with Jev wired into the experimental evaluate path, so scoring stays typed.

integrationsagentseval

Details Demo

Browser and computer usePython4,799

DemoFeatured

Jev Ultrafast

Jev picks the browser op and DOM target in one shot; a tiny LLM only shows up when something needs typing.

by @gregpr07

browser computer usebrowser-useagents

Details Demo

Agent toolingTypeScript2,735

Featured

fast-jev-compaction

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dro

agent toolingcompactionagents

Details

Agent toolingPython506

Demo

foreman

Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task.

agent-toolingagentssupervisor

Details Demo