Agents & browsers

Claude Code plugin that has Jev compare each pending tool call with the session plan before allowing, escalating, or blocking it.

Holy shit. Using Jev in my JARVIS just made it like actual super intelligence. what the fuck. Will release the update asap. https://t.co/LJZA4z7fSf

Humble beginnings using Jev. Trying to integrate it into Codex and help with speeding up browser use. Been working on it all day and running hundreds of trails. So far I've spent... $0.00725 https://t.co/yX3mPB41pL

I made an AI agent using Jev to reply to my wife We’re getting a divorce now and she wants to know who Jason is

Using Jev to catch Codex workers ignoring AGENTS.md. Combine live Codex output, Git changes, and AGENTS.md into one observation Use Jev to score the probability that the worker is drifting from AGENTS.md Steer the active Codex turn when drift crosses a threshold, stopping it if the drift continues Added to Foreman, which automatically watches and steers workers on the software factory floor. https://t.co/g9prp3tsy8

Episode 285: Bendcoder We build an experimental coding agent from scratch using Jev from @typesafeai and new programming language Bend2 from @VictorTaelin. ...while playing WoW Forever on CoderOS; demoing the CoderOS GPU-accelerated multiplex panes and hand tracking (goodbye Hyprland, hello Jarvis); and introducing CoderQuest, a forthcoming game for commanding and upgrading coding agents with real-world prizes. Meanwhile in Azeroth, Eetum arrives in Thunder Bluff and purchases a guild charter. Bendcoder repo: https://t.co/UjtjgTEAZS

Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.

Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.

Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.

Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev).

Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence.

Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on.

One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.

Jev-powered semantic browser use.

Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.

Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.

Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.

MacOS computer use driven by Jev (TypeSafe System One) as the decision maker.

Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark.

Browser agent where Jev selects actions, an LLM reads and plans, and answers cite page evidence.

TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.

5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.

Browser use using Typesafe's Jev model.

Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.

Browser Use's ultrafast agent: Jev picks the operation and DOM element in one request; a small LLM only writes text when typing is needed.

Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation.

Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry.

Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.

Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.

Agent Skill: send closed coding-agent judgments to TypeSafe Jev.

PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.

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.