Skip to content

Open Jev Approvals

Approval gate for Claude Code where hooks send each tool call to Jev and a local policy returns allow or deny without changing the harness model, provider or sandbox.

Stars
3
Language
Go
License
MIT
Published by
Community
Author
alexj11324
Last verified
Oct 2026

About this project

When the agent is about to run a tool, a hook intercepts the call, TypeSafe Jev reviews it, and a local policy returns allow or deny. Third-party API setups usually cannot use the harness's own approval flow; this gate is the auto mode for that case. Jev is the reviewer. The local policy is the verdict. If Jev cannot produce one, the call is allowed — a deny needs positive evidence that the action is dangerous.

Quoted from the project's README. Read the full README.

Highlights

  • PreToolUse review combines user messages, redacted tool input and verified facts.
  • User-level env lookup and redaction keep keys and payloads out of repos and disk.
  • Decisions persist in SQLite with inspect, probe, status and doctor commands.
  • First release targets macOS and Linux with per-project hook wiring.

Watch out

A deny needs positive evidence at 0.70 or higher; Jev outages, timeouts, bad responses, missing keys or a broken audit database allow the call and record it incomplete. The threshold is uncalibrated. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

3GitHub stars
Go MCP server exposing Jev through OpenRouter or TypeSafe as five tools: decide, classify, verify, rerank and list_models. Each tool call is one paid inference request, answers are validated against the question asked, and the unchanged provider response is returned with its usage cost.
Jev Agents & MCP#community#jevbest#catalog-import
51GitHub stars
Local LinkedIn recruiting workspace on Browser Use's Jev Ultrafast: Jev screens titles, drives navigation, and assesses profile excerpts against your brief while a live browser stays visible; matches and evidence export as JSON.
Jev Agents & MCP#community#jevbest#catalog-import
47GitHub stars
MCP server that screens files, public webpages, or inline text against a query and returns compact relevance probabilities, so the main agent opens only promising items.
Jev Agents & MCP#community#jevbest#catalog-import
48GitHub stars
Agent harness for work that outlives one chat, with resumable turns, routed state machines, and observational memory across sessions and processes.
Jev Agents & MCP#community#jevbest#catalog-import
Assistant framework that stores specs, memory, and specialist agents as plain markdown files in your repo for Claude Code, Codex, Opencode, and similar runtimes.
Jev Agents & MCP#community#jevbest#catalog-import
33GitHub stars
Codex Skill plus stdlib-only Python CLI that recommends which installed skill to read next for a task, allowing no-skill or uncertain answers and never executing candidates.
Jev Agents & MCP#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai