Agents & browsers

Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev).

Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.

Full-stack agent harness with memories, long-running tasks, multi-agent relay, and a Jev-backed model-routing table.

Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

Bounded TypeSafe Jev workflows for coding agents.

TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers.

Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop.

Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task.

Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.

Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev).

TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards.

Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships.

Agentic TypeScript workflow framework with a Jev session checker wired into its workflows.

What I’m doing with #Jev from @typesafeai: Making Ergod, my multiplayer AI agent, better at the work between “let me check” and actually getting it done. Better research. Clearer comparisons. Fewer dead ends. Small decisions. Bigger capabilities. 🧵 A result can match your keywords and still miss your question. Jev helps assess what’s relevant. Alongside better page reading, Ergod can focus on useful evidence in long articles and wiki pages - with headings and tables kept in context. The follow-up is where this gets interesting. “What about the exceptions?” “Where did that figure come f

Seeing how many people are using Jev to control browsers I wanted to try too. Wrote the wrapper for 'dev-browser' and called it 'jev-browser'. And then tried to put it to a test: "Find the best pricing model for WP Multitool for someone who runs 3 sites, spends 3h/yr on each, and has $50/hr rate and will run them for 2 years." I saw that it did the right steps until the last one. Was adding the Lite version to the cart. That's how I discovered that while my Pricing page LOOKS good it's structurally awful and definitely nor readable for BOTS or SCREEN READERS. Learned something = PR

judge jev is the law. score two browser agents w/ different models on task completion, using jev to judge which was more efficient at the job. scored on correctness, time, actions, and cost. https://t.co/8M7JBou6O1

Implemented this exact thing today in the @knocklabs agent harness using Jev based on the common types of requests we see from live traces.

I built a Chrome extension for agentic browsing using Jev by @typesafeai, https://t.co/Xa9toMieqT including AI Gateway by @vercel. Now agents can browse, click, and interact with websites directly in your browser. Cost effective and fassst. Decision-making by Jev. https://t.co/bIqkUbCkvc

Vibe coded a parallel search using jev for agents, planning to hook up a local LLM to this to get human output. Discovers new pages and adds them to a BFS queue, jev consumes pages in parallel, reranks and adds to the queue. https://t.co/EkpZhuYmRB