An MCP proxy and hooks adapter that screens an agent's tool calls before they run and the tool results before the agent reads them, with thresholds in a policy file.
agent-chaperone/agent-chaperone
Organization repository on GitHub
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
Repo stats from the GitHub API, cached Sep 2026.Homepage
agent-chaperone logWatch out
Apache-2.0. Screening sends arguments and results to the configured model. policy_violation, off_task, and description_steers are not in the published scores. The README says adaptive attacks written against the tool will get through.
Posts, threads, and videos about this entry from around the web.
Hacker News: Show HN: Agent Chaperone screens tool calls and results with Jev before the agent sees them.
sepehrsafari5 pointsShow HN: Agent Chaperone – Screen AI agent tool calls and results with JevRead the thread on Hacker NewsX: Agent Handoff Gate: agents verify what they hand off
I built Agent Handoff Gate with typesafe Jev An experimental protocol for AI agents to verify worker evidence before handing results back to the lead. Less blind trust, fewer useless review loops. github.com/zsoXi/agent-ha…
X: Jev as an LLM guardrail inside Agentgateway
TypeSafe’s new Jev model is fast 🔥 and Agentgateway keeps up! In minutes, I had Jev running as a prompt guard through Agentgateway, with distributed tracing and cost tracking. Check out the example below Example: github.com/agentgateway/a… Intro to Jev: typesafe.ai/blog/introduci…
X: Vercel's fx safety reviewer, measured at 18× faster
@vercel 's fx uses Jev to review every command. @rauchg says it's up to 18x faster than GPT Luna and more accurate. @JoshARosen built Foreman, where Jev watches coding agents for drift, missed tests and getting stuck. @shantanugoel's Hermes agent installed an "ask Jev" skill on Show more
itsmostafa/system-one-connectorGo
FrancoisChastel/jev-codeTypeScript
eugeniughelbur/jev-engineeringPythonPosts from builders shipping with Jev right now.
An open 151M-parameter decision engine
TypeSafe AI came out of stealth with Jev, and access is behind a waitlist. I built an open source version Verdict (Open-jev) you can run right now in a browser tab: And its a real post trained model..(link in comments) It is a post trained 151M parameters model. ModernBERT-base Show more
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
Agent Handoff Gate: agents verify what they hand off
I built Agent Handoff Gate with typesafe Jev An experimental protocol for AI agents to verify worker evidence before handing results back to the lead. Less blind trust, fewer useless review loops. github.com/zsoXi/agent-ha…
A local Telegram analyzer with Jev as the classifier
I vibe-coded this simple, open-source and local Telegram content analyzer using Jev as a classifier. Jev Classifier • jevclassifier.vercel.app Export your channel data as JSON and it will analyze each post's intent, quality, sentiment, and reaction tone and if it's a DM/Group Show more
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
A Krunker-inspired FPS, decided by Jev
Maybe I’m just washed, but Jev is beating me at my own game. Built a Krunker-inspired FPS where you 1v1 Jev. Try it out yourself: jev-arcade.vercel.app/duel
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
Pixel art out of 256 multiple-choice questions
I turned @typesafeai Jev model into a pixel art model. 256 multiple choice questions, one per pixel, plus refinement passes. These were the best results out of the bunch I tested. Code: github.com/Wizhill05/type…
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
An Elixir port of the official SDK
[Announcing] TypeSafe SDK - Jev, the first System One model from TypeSafe forum.elixirforum.com/t/76700 #ElixirLang #MyElixirStatus
