All decision model projects

Local-first Windows writing studio with knowledge graphs and author voice, where optional Jev evaluates candidates and editorial decisions.

Unix filters (grev, tagv, rank, sortv, cutv, uniqv and more) that select, label and rank lines by meaning with Jev.

Elixir DSL (Gut.feel) that picks an Elixir value for a subject and question, with a Jev evaluation adapter among LLM options.

Home Assistant integration that runs weekly checks with Jev judgments and turns confident findings into Repairs cards for you to confirm.

Go gateway exposing the Jev /v1/systemone contract over ordinary LLM backends by reading single-token label logprobs.

Orchestrator that probes which coding agents are installed and logged in, then has Jev pick the best one for a task.

Static, source-attributed archive of Hermes Agent workflows and skills whose harvest job uses Jev to shelve and rank new entries.

Nerve: asynchronous System-1 supervisory plugin for Hermes Agent judging relevance, completion and recovery with Jev, Laya or OpenJev.

Two stdlib-only Hermes Agent plugins: a Jev pre-tool gate with a jev_ask tool, and a skill router that names one skill per turn.

Hermes Agent plugin that classifies each turn's route (skill, research, history, others) with Jev before the model call.

Hermes skill that turns an intention into a judgeable finish line and a run prompt, with Jev deciding fuzzy requirements at the gate.

Hermes Agent plugin exposing Jev as four coding-workflow tools: jev_check, jev_route, jev_score and jev_evaluate.

Hermes Agent plugin that picks the model each turn with a direct TypeSafe Jev Choice and enforces trim-then-compress context handling.

Skill pack handing an agent's small decisions to Jev: model routing, skill choice, search, memory, compaction and computer use.

Hermes Desktop plugin where Jev maps misspelled, shortened or meaning-based slash commands to real ones at ≥0.85 confidence.

Scores HeyReach LinkedIn leads and first-message variants with Jev, picks a message per lead and writes draft campaigns back.

Python and Node library that classifies Hugging Face dataset rows on typed Choice, Score and Noul dimensions using Jev.

Chrome extension that sorts Hacker News comments into user-defined buckets with one Jev Choice call per comment.

Local agent workbench whose decision crate borrows the System One state/questions request shape, starting with Cloudflare's Clef.

Semantic code search and plain-English review rules that send repository chunks to Jev and return scored source locations.

GitHub Action that triages issues with Jev, applying label, spam, needs-info and duplicate tags only above set thresholds.

llama.cpp-based C++ server that turns any LLM into a System One decision model, reading answers from next-token logits.

Open-source dual-brain runtime that answers typed decisions with a fast local engine or the Jev API before falling back to LLMs.

Intent compiler skill that turns vague coding requests into a typed IntentSpec, with Jev or LAYA as optional decision backends.

Local guard layer for coding agents that blocks dangerous tool calls by deterministic rules, with optional Jev judgments.

Runs Intern-Decision-0.8B on Apple Silicon behind a local /v1/systemone endpoint that accepts screenshots for agent decisions.

Invalidation layer for agent memory: each fact gets a lease and Jev yes/no votes decide whether new evidence ends it.

Goal-driven browser agent where each step is one Jev choice over the page's controls, then reviews the run for root causes.

CLI that scans source, build and CI files with Jev for hidden, deceptive or data-stealing behavior before you run unfamiliar code.

Desktop workspace for coding agents that runs tasks in parallel worktrees, listed as using Jev to pick the best agent per task.