Fast browser and macOS computer use for MCP agents. Local execution, TypeSafe Jev decisions, verified outcomes.
Local & offline models — page 3
Local alternatives and on-device decision models that follow the System One interface, plus shims for existing Jev clients.
368 active projects match this task, ordered by traction.
23
A local code index for AI coding agents: search, symbols, callers, task scope and Git history from one CLI, so your agent reads the lines it needs instead of whole files.
Open-source, local decision models inspired by TypeSafe’s Jev and System One - built on Qwen3 for NVIDIA DGX Spark.
17
Open-source System One decision engine. Typed choice / score / noul with calibrated probabilities. Self-host with Ollama or any OpenAI-compatible model. Apache-2.0.
14
Using Apple's Neural Engine as a fast and free local "System One" Decision Engine (macOS 27) - "Honey, we have Jev at home"
14
One local endpoint. The right model for every turn — enforced in code, not prompts.
AI summaries of Signal group content - text, images, links, voices. Runnable locally through ollama.
13
离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev
A Swift package for typed decisions from language models (probabilities, choices, and scores), with support for local MLX models and the TypeSafe Jev API.
11
Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.
11
Open-source, local Jev alternative: a System One decision layer with provably calibrated confidence (ECE 0.170→0.071). Typed decisions, runs offline, no API key, no waitlist.
10
A local, offline System One server compatible with TypeSafe's Jev API. It answers typed yes/no, category and score questions with small open models.
10
Independent measurements of typed-decision models: Jev (TypeSafe API) vs Laya (open weights), and a local-first cascade that matches Jev's accuracy at 1.8x the speed
9
Local Context Compiler (lcc): clean, dedupe and compact prompt context before it reaches the model, then report every block dropped, the cache tokens a pass invalidates and when pruning pays off. Runs offline with a local 1K decision model. MIT, no API key, zero telemetry.
Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.
Use local and hosted classifiers aka decision models aka Jev-like models, all through a single TypeSafe API
MiniMax Code CLI enhancement pack: continuous 25% context renewal, context progress meter, browser tooling, Syntra and djev-spark local decision integrations.
Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist
Jev Auto Router (Jev Router): experimental per-call GPT model routing for Codex via TypeSafe Jev and a local Responses proxy, with independent task verification.
NanoJev Snake Arena: 1v4 human-vs-AI battleship + 100-agent swarm simulator. Local demo of Jev System-One model (open-source mini replica).
JevNoiseGate filters unwanted notifications and SMS on Android. Rather than matching keywords, an LLM decides what's noise — and only what it explicitly flags is blocked. Verification codes are matched on-device and never uploaded; anything uncertain passes through.
Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.
6
Run Laya locally with Bun: native ONNX inference, a TypeSafe-compatible API, and a bilingual decision playground.
6
Local System-One decision models: typed questions in, calibrated probabilities out. General decisions and browser-agent steps.