Agent Decisions

Playwright plus Jev core behind a typed SDK, persistent CLI and MCP server, with native operations needing no key and verifiable assertions.

Library, CLI and MCP server where an LLM states each step's outcome and Jev decides element, action, value and done/blocked/irreversible.

Decision-to-action harness that puts Jev between an agent and your data to find the file, check the claim and permit actions.

Pi-based coding agent where a small judge (Jev by default) answers yes/no, choice and score questions at 38 decision points per turn.

Demo that navigates a Neo4j graph hop by hop, asking Jev which relationship to follow and whether the goal is reached.

LangGraph dental-clinic agent where a local Jev-style router picks which tools to bind each turn, halving LLM token use.

Kotlin Android SDK where Jev or DeepSeek selects actions from on-screen controls and an accessibility service executes them.

Design-phase proposals for verbatim, Jev-guided context compaction in Kimi Code CLI via a forked mutating PreCompact hook.

Pi agent harness where Jev routes the model tier, picks runbook sections, gates tool calls and verifies reports on Neon Postgres.

Zero-build local playground for Jev with browser-agent, intent routing and context-pruning presets, including a Playwright agent.

Browser agent that acts on one look at the page with one open-model call per action; Jev is an optional chooser backend.

Ten runnable JavaScript lessons where Jev judges agent situations like memory conflicts and handoffs while code enforces explicit policy.

macOS bookkeeping clerk booking supplier invoices: Jev picks each click from a closed list; a deep model rewrites the playbook.

Agent context compactor where Jev scores transcript segments to keep verbatim or move behind a recoverable pointer.

Terminal Q&A app where Jev sets response policy and reviews drafts while OpenAI only writes, orchestrated with LangGraph.

Zero-dependency agent harness that sends each loop fork (act?, which tool, risk, done?) to a decision model and keeps the LLM for writing.

Coding-agent skill that drives Chrome over CDP to hunt for jobs on company sites, with Jev scoring every link and job posting.

Standalone Android agent on Mobilerun where Jev picks every operation and target, with a live React studio, CLI and traces.

Tiny demo that asks Jev whether an agent should continue, downgrade its model, or stop, given budget and plan.

Agent skill that sends closed coding-agent judgments to Jev before asking the user, before risky commands and after failures.

Experimental Hermes Agent plugin for bounded Jev worker checkpoints, route advisories and request-goal tools.

Open 2B non-autoregressive decision model on Qwen3.5-2B for agent tool routing and DOM actions, with BF16, FP8 and INT8 weights.

Open Apache-2.0 browser-agent decision model (Qwen3.5-35B-A3B fine-tune) that doubled Jev 1.13's task success in the same agent.

Browser driver where Jev makes every decision and agent-browser performs every action, benchmarked against Claude Code on 10 tasks.

Jev-powered browser MCP server that makes each step in one parallel call and escalates to the driving LLM only when unsure.

Python library and CLI that turns noisy sources like CI logs, diffs and web pages into small, traceable Jev briefings.

Browser and macOS desktop agent for Pi where Jev picks each action from a structured text observation in a bounded loop.

Pi extension that dedupes repeated file reads and, opt-in, has Jev mark passing-test noise in long logs, with verbatim recall.

Single-file, zero-dependency port of jev-ultrafast to Ego Lite: one typed-choice Jev request per browser step, with extra guardrails.

Runs jev-browser entirely on a local Jev-style engine (Qwen2.5 1.5B decisions, 0.5B typing) on an RTX 2060 SUPER, with no cloud API.