evoke

What Jev does in evoke

The project describes itself this way: Software, by reflex. A sentence becomes a call of a small program, chosen by Jev, TypeSafe AI's classifier, and run only when it is sure enough. Reflexes are recipes anyone can write, share and improve. A CLI you talk to, a package manager for reflexes from git, and a TypeScript SDK. 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

• automation
• classification
• classifier
• classifier-model
• cli
• dependency-management
• dependency-manager
• evoke
• jev
• jev-ai
• jev-api
• jev-model
• jev-package-manager
• natural-language

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.

Also listed in: CLI & Pipelines.

Related Jev projects in Agent tooling

1. pi-verdictjesset/pi-verdictA minimal permission gate for Pi in the style of Claude Code's auto mode.★ 10
   TypeScript
2. typesafe-skill-routerDECRUX9812/typesafe-skill-routerAn opt-in Hermes Agent plugin that asks Jev to suggest one relevant skill before a model call.★ 13
   Python
3. hermes-jev-approvalsanpicasso/hermes-jev-approvalsAn experimental Hermes command-approval provider for the auxiliary.approval task only.★ 13
   Python
4. jev-browser-bridgelexmount/jev-browser-bridgePlug any CDP browser into Jev — cloud, local or self-hosted, including browsers that never draw a page.★ 9
   Python
5. jev (BorisLeMeec)BorisLeMeec/jevA Go Claude Code plugin using Jev to find files, answer bounded questions across code and handle large reads.★ 14
   Go
6. public-browserSilbercue/public-browserLets Claude Code and Cursor drive Chrome. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -24% tool calls, +48% speed, 30/30. Direct CDP, a11y-tree refs, server-side plan executor. MIT, no paid tier.★ 14
   TypeScript

See all 172 Agent tooling projects →

Where we found it

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