02Ideas (community)

Community repos: what people built and how they use Jev

type: communityupdated: 2026-09-20confidence: medium jev: jev-1.13.0 tags: community repos examples integrations replicas

TL;DR Third-party projects captured 2026-09-20 from the owner's X bookmarks; stars are that day's snapshot. Each row gives the state, the primitives and what the code does with the answers. Unaudited code — read it before running it, and never paste a TYPESAFE_API_KEY into a tool you have not read. Official repos: typesafe-ai GitHub organisation and repos.

Start here

jev-ultrafast — cleanest Speculative fan-out: operation plus a target per operation, one request.
typesafe-computer-use — OCR → candidates in code → three Choices + a Noul.
fast-jev-compaction — two Nouls per tool call; code prunes, survivors verbatim.
foreman — ten Noul dimensions in one call; a deterministic policy acts.
pg-jev — 20 rows per state, one Noul per row; honest about where it degrades.
SemIf — top open replica; the interface, mechanically.

Coding agents and developer workflow

repo	stars/lang	what it does, and how it uses Jev	maps to
fast-jev-compaction	4918/TS	Replaces Claude Code compaction. Conversation as state → 2 `noul` per unpinned call (keep call? keep result?) → drop or truncate below 0.5.	Cookbook: Classifying RAG passages
foreman	425/Py	Supervises coding agents. Factory events → 10 `noul`s (`worker_stuck`, `work_off_track`, `needs_human`...) in one call → a deterministic policy picks STEER/STOP/VERIFY	Confidence-gated routing
jev-review	400/TS	Staged review. `Noul` risk matrix → `Choice`+`Score` file profiles → `Choice` evidence → `Choice` mechanism → `Score` severity → routing	Composite scoring
jev-router	245/JS	Per-turn model routing. Prompt + tier + context tokens → four scored dimensions + confidence → fast or strong tier	Intent routing
compact-adviser	146/TS	"Compact now?" Two one-sentence questions per request → one composed score against a floor sliding 0.90→0.50 as context fills.	Confidence-gated routing
building-with-jev-skill	124/—	Agent skill for writing Jev programs, not a caller: question design, state structure, thresholds; targets `jev-1.13`.	The typesafe-ai agent skill and Claude Code plugin
pi-warden	102/TS	Pi guardrails. Tool call + project Markdown rules → Jev judges irreversible calls, rule breaches, stuck loops and unverified "done", then steers rather than blocks. Questions only in `docs/guards.md`	Cookbook: Guardrails for LLMs
stanley-code	98/TS	Bounded agent workflows. One `choice` over workflow metadata + `cannot_tell`, gated on confidence ≥ 0.6, probability ≥ 0.55, margin ≥ 0.15; then per-hunk `choice`	Intent routing
jev-shell-history	69/TS	zsh suggestions. Typed prefix + 100 ID-tagged history entries → `Choice` over IDs + `Noul` "does any complete this?" → show if top ≥ 0.3 and Noul ≥ 0.5	Cookbook: Line-by-line search
jev-rules	43/JS	Injects only the relevant standing rules. Prompt text → one `noul` per rule and map doc in one call → inject ≥ 0.6; shows all on error	Cookbook: Skill suggestion

Browser, computer and mobile use

repo	stars/lang	what it does, and how it uses Jev	maps to
jev-ultrafast	11208/Py	Browser agent, no screenshots. Indexed DOM element table → one request: `operation` (CLICK/TYPE_TEXT/SELECT/SCROLL/WAIT/DONE/BLOCKED) plus a speculative target question per operation.	Speculative fan-out
trycua/cua	25014/HTML	Computer-use platform with a `jev-use` recipe. Not in the README; per the team's article, code builds candidate actions with IDs, Jev picks one, code validates, executes and re-observes	State: what you send Jev
typesafe-computer-use	582/Py	macOS computer use, ~$0.0002/step (author). OCR + accessibility tree → candidates → three `Choice`s plus an `offscreen` question per request; a `Noul` verifies the typed field. Aborts below 0.4	Speculative fan-out
mobile-jev	264/JS	Android agent, no ADB. Screen + installed apps → operation + compatible-target questions per request; code rejects stale targets. Typed text is a span from the goal; `DONE` is not proof	Speculative fan-out
jev-voice-browser	148/JS	Voice to Playwright, acting on partial speech. 9–11 questions per transcript: intent/target/site/spans (`Choice`), complete/is_command/destructive (`Noul`), scroll_amount (`Score`), each thresholded.	Confidence-gated routing
unclutter	143/TS	Hides page clutter. DOM candidates → typed keep/ad/promotion/newsletter/social/cookie/uncertain choices → hides only when probability and confidence are ≥ 0.9	Cookbook: Guardrails for LLMs
WindTunnel	72/HTML	WebMCP interface benchmark. Jev + Mercury 2.5 is 1 of 21 configs (49/49 with WebMCP, 25/49 with DOM controls); Jev decides, Mercury writes arguments. Runner in `experiments/jev/`	Workflow evals: how TypeSafe measures Jev

vlad-terin/jev-browser was announced 2026-09-17 as an adapter for Codex browser tools ("Codex plans, Jev selects, the browser moves"); it 404'd at capture, so nothing more is verified.

Agents, orchestration and memory

repo	stars/lang	what it does, and how it uses Jev	maps to
skillbox	214/TS	Self-hosted skills library over MCP. Task + skill descriptions → an uncalibrated 0–4 rubric score per skill (not a probability); returns ≥ 3, with a search fallback	Cookbook: Skill suggestion
agentic-stack-desktop	64/Py	Knowledge graph across four coding agents. Not in the README; the linked post is about finding Jev-shaped decisions in a workflow	Consult guide: could Jev help this project?
continual-memory-policy-model	5/Py	Memory policy with delayed feedback. Not in the README; its WRITE/UPDATE/DELETE/LINK/COMPACT/NOOP action set is Jev-shaped, but it trains its own policy	Primitives: Choice, Score, Noul
octavus-dual-brain	0/HTML	Write-up placing Jev as System 1 ahead of an orchestrator. `intent` (`Choice`) + `risk_score` (`Score` 0–3) in parallel; 10 filings fanned out in one call	Intent routing

Search, data and databases

repo	stars/lang	what it does, and how it uses Jev	maps to
jev-search	286/TS	Plain-language web search, no generated answers. Typed questions choose query, sources and time range; Jev scores each result, code orders by relevance and engine agreement	Cookbook: Re-ranking
pg-jev	239/Shell	Postgres extension: `jev(table,'condition')` in `WHERE`. 20 rows per request in one shared state, one `Noul` per row. Warns positional `rows[i]` lookup degrades in long arrays	Cookbook: Parallel questions
neo4jev	46/Jup	Graph navigation one hop at a time. Outgoing relationships as `Choice` options + a `Noul` "goal reached?" in the same call → top-k over probabilities is a beam search	Cookbook: Hierarchical classification

Moderation, judging and media

repo	stars/lang	what it does, and how it uses Jev	maps to
notra	193/TS	GEO platform tracking brand mentions. Not documented — no Jev or TypeSafe mention in the README	—
youtube-sponsor-detection	78/JS	Skips YouTube sponsor reads. Transcript as numbered lines → Jev picks line IDs (`Choice`) plus probability questions, each repeating the sponsor definition. Code owns every timestamp; skips above ~70%	Cookbook: Line-by-line search
jevmeter	75/Py	Live "BS meter" over video. One request per sentence; state = sentence + speaker history + last question → 5 preset `noul`s → averaged into a gauge, flagged at the 98th percentile	Cookbook: Self-consistency — nouls
Jev-Moderation-Bot	39/Py	Discord spam/scam filter. Messages + prior infractions → five dimensions (scam, spam, noobness, toxicity, helpfulness) → archetype plus two admin tiers; pardons fed back	Composite scoring
jev-as-a-judge	25/Py	Jev vs three LLM judges on fixed runs. Trace as state → `does_pass` (`Noul`) + a `quality` score. Reports 100% oracle agreement over 500 repeats, variance 92–913× below the LLM judges	Testing and evaluating a Jev workflow

Real-time, games, robotics and IoT

repo	stars/lang	what it does, and how it uses Jev	maps to
jev-trader	1464/TS	One decision per Monad block. Order-book snapshot → buy/sell `Choice` per ~300 ms; code posts the order. Numeric time-series is a documented Jev weakness — a latency demo, not a trading system	Jev 1.13 jaggedness: known failure modes
typesafe-mario	295/Py	Plays Super Mario Bros from emulator RAM. JSON telemetry → `Choice` picks the controller macro, `Noul` whether a jump helps, `Score` immediate danger. No scripted override	Choosing between Choice, Score, Noul
jevpilot	112/JS	Three.js driving-sim autopilot. Compact tables of eligible paths, boundaries, traffic, signals and stop memory → a choice over paths; geometry stays local	State: what you send Jev
jev-drone	83/Py	Camera-only quadrotor in MuJoCo, ~2.5 Hz. Per call: `maneuver` (`Choice`), `risk` (`Score`), `target_truly_lost` (`Noul`) → search gates on the Noul, not the unconfident Choice. Jev never picked `climb` until the state named altitude	Writing instructions and criteria that Jev reads correctly
HA-Jev	32/Py	Home Assistant: questions become sensors. Pickers build the state → `jev.noul`, `jev.choice` (2–255 options), `jev.score` (2–10 levels), `jev.ask`; one context is one request	Smart home assistant demo walkthrough

Integrations and catalogs

repo	stars/lang	what it does, and how it uses Jev	maps to
awesome-jev-by-typesafe	684/Py	Curated use cases and starter code; a directory, not a caller. Quick start matches SDK 0.6.0; pattern list mirrors the official four	Patterns overview
typesafe-mcp	133/Go	MCP server with one `evaluate` tool. Passes `state` + a `questions` map (`{type, instructions, criteria?}`) to `POST /v1/systemone`, default `jev-latest`; validates criteria locally	HTTP API: POST /v1/systemone and GET /v1/models

Open replicas and Jev-compatible servers

None affiliated with TypeSafe. Numbers compared in Field reports: independent evaluations, critiques, open replicas.

repo	stars/lang	what it is, and its relation to Jev	maps to
SemIf	2310/Py	Semantic ifs from open models on a 3090. Reads option logits from a frozen 4B model in one forward pass; ~1.0 s for 21 probability pairs, conditional on the supplied options	Jev vs LLM JSON mode / structured outputs
NanoJev	1322/Py	0.6B parallel decision model + training pipeline. Same request shape (state, question, 2–255 candidates); Choice via set attention, Boolean via sigmoid, Score as a weighted level.	Primitives: Choice, Score, Noul
jevlike	1059/Py	Starter model with Jev's input/output shape. Option-attention head, softmax across options; ~100× faster than a decoder writing 400 tokens. Reused by trycua CUA-S1-FORMS	Jev vs LLM JSON mode / structured outputs
openjev-sglang	214/Py	Jev-compatible `/v1/systemone` on Qwen3.6-35B. N+1 one-token calls over a shared prefix; Noul = P(yes), Choice = argmax + distribution, Score = `sum(level_index * probability)`. Its `confidence` is reimplemented	Confidence vs probability
mini-jev	29/Py	Letter-logit reads vs grammar-constrained JSON on Qwen3-4B. 4× faster on short texts. Making a model write probabilities scored 0.346 vs 0.896 for letter reads; shares are not calibrated	Confidence vs probability
openjev	2310/Py	Same URL, stars and README as SemIf: one project after a rename ("SemIf (formerly OpenJev)"). Count it once	see SemIf

Reusable designs worth stealing

Speculative target heads — ask the operation and a target question per operation in one request; run only the matching target. jev-ultrafast, mobile-jev → Speculative fan-out.
Score every context block for keep/drop — two nouls per item, prune in code, survivors verbatim. fast-jev-compaction → Cookbook: Classifying RAG passages.
Model assesses, code decides — many noul dimensions per call, then a deterministic state machine acts. foreman → Confidence-gated routing.
Staged escalation — each stage's strongest signal selects the next question. jev-review, stanley-code → Intent routing.
Rule or skill selection per prompt — one yes/no question per candidate, one request, inject above a threshold. jev-rules, skillbox → Cookbook: Skill suggestion.
Split one big action choice into narrow ones — overlapping options read as low confidence. typesafe-computer-use → Writing instructions and criteria that Jev reads correctly.
Select the span, never generate it — regex or numbered lines make candidates, Jev picks one, code copies it. jev-voice-browser, sponsor-detection → Cookbook: Pre-parsed value extraction.
Batch N items into one state with N questions — the shared preamble amortises state tokens; positional lookup into long arrays is the failure mode. pg-jev → Cookbook: Parallel questions.
Gate on the primitive that fits — when a Choice is unconfident, a companion Noul may answer cleanly. jev-drone → Choosing between Choice, Score, Noul.

Caveats

Stars are a launch-week snapshot (2026-09-20); several repos were days old. Hype signal, not quality.
Licences missing on Jev-Moderation-Bot, jev-as-a-judge, building-with-jev-skill, openjev-sglang, typesafe-mario, jev-shell-history, jevpilot and sponsor-detection; pg-jev is NOASSERTION.
One duplicate: TheoLeeCJ/openjev and TheoLeeCJ/SemIf are one repository after a rename — identical URL, stars and README.
Jev usage not in the README for notra (no mention at all), agentic-stack-desktop, continual-memory-policy-model, trycua/cua (only its X article) and WindTunnel. pi-warden and Jev-Moderation-Bot name the judgments, not the types.
Community limit claims: fast-jev-compaction calls 32k "Jev's request ceiling"; compact-adviser caps requests at 32,000 bytes. Documented rule: 64k tokens per request, 32k for state plus the longest single question (Models, aliases, pricing, rate limits, context) — those are approximations.
Uncalibrated numbers: skillbox's 0–4 rubric is not a probability, and openjev-sglang computes its own entropy-based confidence (Confidence vs probability).
Security: unaudited code, much of it agent plugins with shell, browser or database reach. Several ship smoke scripts that bill your key. Never pass a key as a CLI arg.

Consult guide: could Jev help this project? — answering "could Jev help this project?"
Decision patterns from the community (with fit verdicts) — the patterns these repos share, with fit verdicts
Field reports: independent evaluations, critiques, open replicas — independent evaluations and replica numbers
typesafe-ai GitHub organisation and repos — the official typesafe-ai repos

Sources

raw/x-repos/INDEX.json and the 42 per-repo captures there (metadata + README, fetched 2026-09-20)
raw/x/trycua-2101437979180904640.md — only source for trycua/cua's Jev usage
raw/x/VladTerin-2100448995415863323.md — only source for vlad-terin/jev-browser

Jev Wiki — an unofficial, agent-maintained knowledge base about TypeSafe AI’s Jev. Built 2026-09-21 · raw markdown · llms.txt