Drives native macOS apps through the Accessibility API. Jev chooses the next action and target token from a live snapshot, and stops if confidence drops too low.

github.comGoMITpushed sep 17added sep 20

Headless browser agent. Jev picks click / type / select / done from the page's elements; code owns budgets and stop gates. MCP server, CLI, or library.

github.comJavaScriptMITpushed nov 1435 forksadded sep 20

Split-brain browser agent: Jev clicks, Codex thinks and verifies.

github.comJavaScriptMITpushed oct 1934 forksadded sep 23

Browser agent with a dynamic, indexed action space. Jev picks an operation and an element in one request; a small LLM writes text only when the operation is TYPE_TEXT. Zürich to London on Google Flights in 7.1 seconds.

github.comPythonMITpushed nov 111.9k forksadded sep 20

Android agent on a real phone via Mobilerun. Jev picks OPEN_APP / TAP / TYPE_TEXT from an indexed snapshot. Text is copied from the goal, not generated.

github.comJavaScriptMITpushed sep 1759 forksadded sep 20

Local computer-use app for macOS where Jev is the default engine: it picks from locally detected controls and the app executes and validates each action.

github.comSwiftpushed oct 15108 forksadded sep 24

Computer use for about $0.0002 a step: OCR the screen, Jev classifies the next action, code clicks. macOS.

github.comPythonMITpushed sep 29124 forksadded sep 23

MuJoCo robot decision workbench: MiniCPM-2B or Jev-class APIs pick the next action, with physics previews.

github.comPythonMITpushed sep 2214 forksadded sep 23

Chat decision copilot across Android, Windows, macOS, and iOS: Jev reads the conversation, judges intent and risk, and drafts replies you fill in with one tap. Read-only, no app hooks. MIT, ~7.9K stars, the largest end-user Jev app by traction.

github.comKotlinMITpushed nov 51.3k forksadded sep 23

Camera-only autonomous drone in MuJoCo with Jev in the loop at 2.5 Hz.

github.comPythonMITpushed sep 2441 forksadded sep 23

Local-first social-media research agent for Instagram, TikTok, and LinkedIn: Jev picks each next operation (search, open a post or profile, read comments, finish), a local CLI executes it in your signed-in Chrome, and every observed result goes back to Jev. Source-cited reports, no account credentials leave the machine.

github.comJavaScriptMITpushed nov 843 forksadded oct 13

Experimental: one Jev buy/sell decision every Monad block (about 300 ms) on the Kuru MON-USDC book. Dry-run by default.

github.comTypeScriptMITpushed oct 13598 forksadded sep 20

Jev navigates a Neo4j graph by classifying over each node's neighboring relationships: graph traversal as a chain of typed choices.

github.comJupyter NotebookMITpushed sep 1827 forksadded sep 23

Open-source AI trading OS with a Jev decision gate in front of live entry orders: typed Choice plus an auditable decision timeline, fail-open, and exits that always bypass AI.

github.comPythonApache-2.0pushed nov 142.8k forksadded sep 24

Prebuilt agents that run a System 1 model (Jev, Laya, or Cua-S1) as the brain across browser use, computer use, robotics, and games, with Claude Code or Codex scaffolding new ones. Publishes per-scenario timings: up to 6× faster and 25× cheaper than a chat model at the same score.

github.comPythonApache-2.0pushed nov 1326 forksadded oct 13

Home Assistant conversation agent. Jev maps a spoken command plus exposed entities onto built-in intents. Free-text intents fall back to another agent.

github.comPythonpushed sep 211 forksadded sep 20

Jev plays Super Mario Bros. from structured emulator state: the classic RL demo with a decision model in the loop.

github.comPythonpushed sep 1664 forksadded sep 23

Token-saver for agent sessions with a documented Jev routing layer.

github.comRustApache-2.0pushed nov 1355 forksadded sep 24

Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one request and the stale ones dropped.

github.comTypeScriptMITpushed sep 18587 forksadded sep 21

Invalidation layer for AI memory: every fact gets a lease, and new evidence ends it.

github.comPythonApache-2.0pushed sep 212 forksadded sep 23

Zilliz's agent memory layer, with optional Jev reranking and a published Chinese/English reranking evaluation.

github.comPythonMITpushed nov 13288 forksadded sep 24

Local proxy that learns your app's typed LLM decisions and answers them itself with a Laya head. Jev- and OpenAI-compatible.

github.comPythonApache-2.0pushed oct 116 forksadded sep 23

Claude Code hook that splits large tool results into blocks, asks Jev a yes/no relevance question per block, and stubs the ones that fail.

github.comPythonMITpushed oct 612 forksadded sep 23

Multi-agent collaboration across Slack, Telegram, and GitHub, using Jev for agent routing, model selection, and support triage.

github.comTypeScriptApache-2.0pushed nov 1482 forksadded sep 24

Adaptive reasoning effort: Jev judges each Codex step and turns GPT-6's thinking effort up or down mid-task, so easy steps stop burning tokens.

github.comJavaScriptMITpushed nov 1228 forksadded sep 26

Jev as a fast supervisor above slower coding agents, judging whether the work is complete, the requirements met, the tests sufficient, or a human is needed.

github.comPythonMITpushed oct 1570 forksadded sep 21

Jev-powered skill suite for Hermes agents (also Claude Code and Codex): model routing, memory, compaction, skill selection, computer and browser use.

github.comPythonMITpushed nov 13128 forksadded sep 23

Intent compiler that converges vague requests into typed IntentSpec contracts — probe, ask, or halt — before routing. The input layer in front of routers and decision models like Jev or Laya.

github.comPythonMITpushed nov 819 forksadded oct 8

Per-turn model and reasoning-effort routing for Codex. Jev classifies each turn and picks the tier; a 7-day replay of 237 real turns measured about 60% savings against all-frontier.

github.comJavaScriptMITpushed sep 2248 forksadded sep 23

Jev-powered router across models, tools, and subagents.

github.comTypeScriptMITpushed oct 431 forksadded sep 23

Calibrated judge in front of a frontier model: a small local model answers routine decisions under a distribution-free bound on disagreement; everything else escalates, and each escalation teaches the judge further. Includes an MCP server.

github.comPythonApache-2.0pushed oct 111 forksadded oct 12

Pi coding-agent extension: semantic tool and skill routing, typed choice / noul / score evaluations, optional auto-approval, and a post-run jev-gate CLI.

github.comTypeScriptMITpushed oct 2914 forksadded sep 20

Open, programmable decision layer for models and compute: routes requests across models, enforces safety checks, and picks reasoning effort — with the Vela decision models as its routing brain. Apache 2.0.

github.comGoApache-2.0pushed nov 141.1k forksadded oct 8

Stops coding agents from claiming done without evidence: deterministic hooks decide what needs checking, Jev judges the result.

github.comTypeScriptMITpushed nov 1318 forksadded sep 23

Staged code-review workflow with a local dashboard, using Jev to score and sort findings before a human opens the queue.

github.comTypeScriptMITpushed sep 1746 forksadded sep 23

Semantic code linting: rules written in plain English, judged by Jev.

github.comJavaScriptMITpushed nov 1018 forksadded sep 26

Verification harness for agent-built code; the jev driver explores a page by choosing among DOM-enumerated candidates — the model chooses, never composes.

github.comTypeScriptpushed nov 14250 forksadded sep 24

Plain-English browser tests on Playwright where Jev only picks targets and next actions (Choice) and judges claims (holds/contradicted Nouls), and code owns every action and verdict. TypeScript, MIT.

github.comTypeScriptMITpushed nov 113 forksadded oct 1

Prose linter that sniffs out AI writing tells: zero-dependency countable rules plus one judgment model.

github.comTypeScriptMITpushed oct 262 forksadded sep 23

Codebase search powered by Jev decisions: typed questions find where a task lives in a repo.

github.comTypeScriptpushed sep 1610 forksadded sep 23

Very fast document classifier and PDF splitter from the creator of LlamaIndex: plain-English rules, Jev assigns each page a category and finds document boundaries.

github.comPythonApache-2.0pushed sep 2638 forksadded sep 26

Dataset sifter for synthetic and pretraining corpora: a Rust streaming core sends Jev keep/drop decisions over Parquet rows.

github.comRustMITpushed nov 1114 forksadded sep 23

Web search pipeline where Jev handles source selection, query understanding, and relevance ranking.

github.comTypeScriptMITpushed nov 769 forksadded sep 23

Recursive Jev choice over a taxonomy: selects from more than 255 options without hitting the choice cap.

github.comTypeScriptMITpushed sep 182 forksadded sep 23

Semantic AI for Pandas and Polars: classify and score DataFrame rows with natural-language questions and full probabilities.

github.comPythonMITpushed sep 243 forksadded sep 23

Codebase search for coding agents: Jev judges folders, files, and declarations, then returns reading leads and verbatim source excerpts. npm CLI plus an agent-skill installer; matched the baseline 8/10 on a ten-task SWE-bench at ~30% lower cost.

github.comTypeScriptMITpushed nov 12248 forksadded sep 29

Grep where the pattern is a description: filters lines by meaning for about a thousandth of a cent each.

github.comPythonMITpushed oct 175 forksadded sep 23

PostgreSQL extension (on PGXN): jev(rows, 'plain-language condition') filters, ranks, and classifies table rows. The clever part — it batches 20 rows into one shared-state request with a noul each, amortizing Jev's request overhead ~2.5×, with read-ahead and per-row answer caching.

github.comShellpushed oct 6109 forksadded sep 23

Trace mining for post-training: reads agent traces (OTel, Langfuse, Claude Code), judges each step by the tool's reaction rather than the agent's claim, distills the LLM judge into deterministic Python checks a human signs off on, and exports labeled SFT rows with full lineage. Its bundled Jev recipe trains a decision model on those labels with an honest scorecard — their Qwen3.5-4B reports 79.1% vs Jev's 66.8% on 1,920 held-out AgentProcessBench steps.

github.comPythonpushed nov 137 forksadded oct 8

Build calibrated AI functions from human feedback: Jev judgments optimized with GEPA. From Sutro.

github.comPythonApache-2.0pushed nov 425 forksadded sep 23

Proxy that distills a repeated Jev call on the fly: trains a small local model on Jev's own answer distributions, verifies agreement within a budget you set, then answers locally in ~15 ms while a permanent random audit slice keeps checking against Jev. PyPI, Apache 2.0.

github.comPythonApache-2.0pushed nov 1113 forksadded oct 16

Turns Jev usage into small local classifiers: --teacher typesafe-ai/jev labels the data, then a MiniLM model runs it in Node or the browser.

github.comTypeScriptMITpushed sep 213 forksadded sep 26

Open-source local fine-tuning app from the systemonemodels.ai platform: MLX on Mac, PyTorch on NVIDIA / AMD / CPU, LoRA / DoRA / rsLoRA / LoRA+, scoring the fine-tune against the base before it publishes.

layastudio.biplovgautam.com.npadded oct 15

Decision-model fine-tuning at ecosystem scale (~79K stars): FastDecisionModel + DecisionTrainer attach a Clef-style decision head to any Qwen, Gemma, Llama, or DeepSeek base via 4-bit LoRA on consumer GPUs, with a documented recipe that lifts Qwen3.5-0.8B from chance to 78% on Banking77, CLINC150, and typed-decisions. The honest note is in their own docs: for existing decision models like d1-3B, fine-tune the model's own readout rather than grafting a new head. The default on-ramp for training your own.

unsloth.aiadded nov 10

Vercel Labs terminal client. The evaluate command sends a state plus typed questions to typesafe-ai/jev on AI Gateway (-m jev for short).

github.comTypeScriptpushed nov 1179 forksadded sep 21

The LM Studio of decision models, from Bud Ecosystem: a cross-platform desktop app that checks your hardware, pulls Jev-like models, and serves them locally. Give a model a situation and typed questions, get calibrated probabilities in milliseconds.

github.comHTMLpushed oct 97 forksadded oct 13

Zero-shot text classification as a URL: classifier.dev/spam,not+spam/your+text returns a label with calibrated confidence — no key, no account, up to 1,000 texts per call. One Cloudflare Worker on Jev with an LLM fallback chain, plus a CLI and MCP server. MIT.

github.comTypeScriptMITpushed nov 635 forksadded oct 1

Local visualizer for Jev: a live view of every call your code makes.

github.comJavaScriptMITpushed sep 2111 forksadded sep 23

Open-source Gmail triage: sorts an inbox into needs-reply / updates / promos / spam. Read-only, runs locally, about 3 cents per 1,000 emails.

github.comTypeScriptMITpushed sep 199 forksadded sep 23

Vercel Labs generative-UI framework with an experimental Jev mode: Jev picks components from your catalog instead of a model writing markup.

github.comTypeScriptApache-2.0pushed nov 141k forksadded sep 23

Jev calls as Unix-pipeline predicates: routing, scoring, and JSONL filtering with stable exit codes, plus an agent-safety guard recipe.

github.comPythonMITpushed nov 710 forksadded sep 23

Browser extension that removes page clutter: Jev scores elements against reusable rules, the extension hides the junk.

github.comTypeScriptMITpushed oct 2847 forksadded sep 26