compact-adviser

What Jev does in compact-adviser

The project describes itself this way: Agent plugin that uses Jev to judge when a coding session should compact its context. In the Agent tooling category, Jev typically decides which tool, skill or model to use next, whether a step is finished, and whether an action is risky enough to stop.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

Topics

• claude-code
• claude-code-plugin
• compaction
• pi
• pi-extension
• typesafe

How Agent tooling projects use Jev

Agent tooling is where Jev sees the most experimentation. These projects sit inside coding agents and assistants such as Claude Code, Codex and Pi, and hand the many small, repetitive choices an agent makes to a fast decision model, leaving the large model free for reasoning and writing.

Related Jev projects in Agent tooling

1. jev-review (NiazMorshed2007)NiazMorshed2007/jev-reviewA local MCP code-quality reviewer returning structured scores to coding Agents.★ 203
   TypeScript
2. jev-prunertamaratran/jev-prunerA Claude Code output-pruning plugin filtering selected Bash output before it reaches the main model.★ 140
   TypeScript
3. pi-jev (y0usaf)y0usaf/pi-jevA Pi extension that flags tool risks before execution and checks output for secrets and failure types.★ 140
   TypeScript
4. pi-wardenDevMortimer/pi-wardenAdds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.★ 135
   TypeScript
5. jev-codex-router0xNatoshi/jev-codex-routerUses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.★ 222
   JavaScript
6. jev-semgrepuehaj/jev-semgrepA semantic grep that scores each line with Jev against a meaning, including AND/OR/NOT and cross-language queries.★ 130
   JavaScript

See all 172 Agent tooling projects →

Where we found it

• heyjunpenn/awesome-jev
• MrJev/awesome-jev