Skip to content
JevDirectory.org
CommunityTools & Integrations32 starsVerified 2026-09-22

Canny

A warden for Claude Code and Codex CLI that keeps an append-only ledger of what an agent did, refuses a done claim when no check passed after the last edit, and uses optional Jev Noul judgments.

Category
Tools & Integrations
Published by
Community
Author
qkal
Added
2026-09-22
Tagscommunitytypescriptclaude-codecodexguardrails

Highlights

  • The rule is facts go to code, judgments go to Jev, and only facts can block; a done claim is refused because the ledger holds no passing check.
  • Hook events land in an append-only ledger under ~/.canny/sessions/ that stores paths and outcomes, never file contents; canny replay reproduces the verdict.
  • Jev judgments are optional: with no key the ledger, done-gate, and pattern checks work the same, and makeJudge can point at CANNY_JEV_URL.
  • The built-in verify list holds about eighty commands (pytest, vitest, jest, go test, cargo test, tsc, eslint, ruff); quoted strings are stripped.
  • The compiled CLI is committed, so install is a git clone plus one init command, and Node 22 or newer is required.

Quickstart

bash
git clone https://github.com/qkal/canny.git ~/.canny/src
node ~/.canny/src/dist/cli.js init
ln -s ~/.canny/src/dist/cli.js ~/.local/bin/canny

Watch out

MIT-licensed but not on npm. Needs Node 22+ and git; enabling Jev sends clipped diffs, project rules, and final messages to TypeSafe, and whether it improves project-wide quality has not been measured.

More like this

201GitHub stars
A local-first MCP server that gives Claude Code, Codex, Cursor, and OpenCode structured quality scores from Jev across correctness, complexity, tests, security, and other dimensions while the agent writes code.
Tools & Integrations#community#typescript#mcp
Communityjev-review
140GitHub stars
A local gateway for coding agents that asks Jev which tool to call each turn and steers the LLM when Jev is confident, while every other request goes to your usual provider untouched.
Tools & Integrations#community#typescript#gateway
Communityjev-gateway
63GitHub stars
A Jev-guided context compaction library for coding agents: instead of summarizing old context, Jev decides which tool calls and results still matter while user and assistant text is kept verbatim.
Tools & Integrations#community#typescript#compaction
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A really smart switch statement

hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by Show more

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

When a designer gets Jev

Full Jev video tutorial

The case against Jev-scored compaction

This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the Show more

tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Reply

Classifying rows in DuckDB

A playable 16-judgment demo