1
Turn any local LLM into a Jev-style System One decision engine: type-safe answers with raw softmax probabilities. 100% offline, zero API cost.
Local & offline models — page 7
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.
An open-source System One decision model — Kahneman's term for the fast, automatic judgment faculty. Calibrated choice/score/noul probabilities in one forward pass on small fine-tuned open models. Local on Apple Silicon (MLX), Jev-compatible API, audited experiment log.
Local alternative to Jev: typed decisions (choice/score/yes-no) with real probability distributions, from any llama.cpp-supported GGUF model. Easy CLI for humans and AI agents. No generation, no fine-tuning, no compiler.
Local-first task router for microservices, polyrepos, monorepos, and coding agents.
Experimental selective context compaction for Hermes Agent using TypeSafe Jev. Native plugin, local archives, bounded scoring and honest evaluation.
A zero-dependency MCP server for TypeSafe's Jev — calibrated, typed judgments for Claude Code, with a local answer cache and cost tracking.
Offline-first experiments for abstention and open-world routing with Jev.
1
A local-first RSS reader with Jev-powered semantic screening. Follow what matters, inspect every judgment, and keep control of your reading. English / 简体中文.
1
Jev decision visualisation and debugging panel for coding agents. MCP server + local web timeline, confidence alerts and trace export.
1
Page truth for browser agents — and decisions that replay, test and audit. Jev picks the element, risky actions are gated, every run replays offline in CI.
A proof of concept implementation of TypeSafe's Jev API, backed by local Laya checkpoints.
1
PT-BR-first, local decision engine for typed decisions at volume.
Find the LLM calls you should move to JEV — scan logs & code for decision-shaped calls, price the migration, calibrate decision models, generate the migration PR. Zero deps, fully local.
Vendor-neutral SDK for typed decision-making (yes/no, choice, score) — hosted and local
One CLI and Jev-compatible API for local and hosted typed-decision backends (planning)
1
Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.
Codex plugin and MCP server for TypeSafe Jev decisions and recoverable context reduction, with optional local Laya-MLX and token/time measurement tools.
Local console + CLI for TypeSafe's Jev (System One) model: send a state and typed questions, get calibrated probabilities back.
1
Jev Router demo: TypeSafe Jev signals route prompts to a local or frontier model (Cloudflare Worker proxy + single-file web app)
1
Give Jev eyes — honest, local image perception for TypeSafe's text-only System One model. OCR + spatial layout → Jev state. CLI, MCP server, agent skill.
GitHub issue triage with side-by-side evidence. Try the public sample without setup, or run the local app with TypeSafe Jev via OpenRouter.
JEV-Local: System-1 decision engine for local LLMs. Mimics TypefAI JEV: structured choices only, no chatter, calibrated confidence. Works with Ollama, vLLM, llama.cpp, LM Studio.
1
MCP local que expone Jev (TypeSafe) como herramienta para Claude Code, Codex, Hermes y cualquier agente: ask_jev y list_jev_models, sin dependencias
Table tennis vs. TypeSafe's Jev (System One). Every paddle move on the right is a live model decision — no local prediction, just a lookup table and a servo.