--- title: "Repos: data, documents, judging, real-time, markets, business apps, replicas" type: community source_tier: community tags: [community, repos, data, documents, replicas] created: 2026-09-21 updated: 2026-09-21 confidence: medium sources: - raw/x-repos/kyotofin__tax-doc-classifier.md - raw/x-repos/INDEX.json - raw/x-repos/superagents-lab__jev-search.md - raw/x-repos/realZachi__pg-jev.md - raw/x-repos/jexp__neo4jev.md - raw/x-repos/AkashPriyadarshii__jev-curate.md - raw/x-repos/jerryjliu__docjev.md - raw/x-repos/trungdq88__youtube-sponsor-detection.md - raw/x-repos/ChetasLua__jevmeter.md - raw/x-repos/brainstormity__Jev-Moderation-Bot.md - raw/x-repos/danielgshea__jev-as-a-judge.md - raw/x-repos/fhshaik__typesafe-mario.md - raw/x-repos/standardagents__jevpilot.md - raw/x-repos/RomanSlack__jev-drone.md - raw/x-repos/AboveColin__HA-Jev.md - raw/x-repos/emrickgarrett__OneVOneJev.md - raw/x-repos/jarrodwatts__jev-trader.md - raw/x-repos/monteduro__killmyidea.md - raw/x-repos/usenotra__notra.md - raw/x-repos/TheoLeeCJ__SemIf.md - raw/x-repos/TianyuCodings__NanoJev.md - raw/x-repos/vinnylarouge__jevlike.md - raw/x-repos/ekzhang__openjev-sglang.md - raw/x-repos/r-ms__mini-jev.md jev_version: "jev-1.13.0" summary: "23 community repos that point Jev at rows, documents, media, live simulations, markets, business questions — plus the open replicas of the interface." --- # Repos: data, documents, judging, real-time, markets, business apps, replicas > **TL;DR** The application half of the community repo catalogue. Index and the vetting checklist: [[ideas/community-repos]]. Coding agents, browser/computer use and integrations: [[ideas/repos-agents]]. Stars and languages are the 2026-09-20 capture (DocJev, jev-curate, killmyidea and OneVOneJev were captured 2026-09-21). **Unaudited code**, and several of these ship your rows, documents or transcripts to TypeSafe. ## Search, data and databases | repo | stars/lang | what it does, and how it uses Jev | maps to | |---|---|---|---| | [jev-search](https://github.com/superagents-lab/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 | [[cookbooks/rerank]], [[ideas/patterns-data]] P17 | | [pg-jev](https://github.com/realZachi/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 | [[cookbooks/parallel-questions]], [[ideas/patterns-data]] P17 | | [neo4jev](https://github.com/jexp/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 | [[cookbooks/hierarchical-classification]], [[ideas/patterns-data]] P17 | | [jev-curate](https://github.com/AkashPriyadarshii/jev-curate) | 9/Rust | Streams Parquet/JSONL training data through Jev row by row, three presets: `reasoning-math` (`has_circular_logic` `Noul`, `is_step_valid` `Noul`, `reasoning_depth` `Score` 1–5), `anti-sycophancy` (`is_sycophantic`, `has_robotic_filler`), `code-correctness` (`has_unclosed_fence`, `has_stub_placeholders`). Clean and rejected records are written **verbatim** — it never rewrites a row. Adaptive token bucket backs off on `429`; `--dry-run` prunes host-side with zero API calls. Author claims "1,500+ rows/sec" and "over 100× cheaper than GPT-4o-mini and 700× cheaper than Claude 3.5 Sonnet" — `unverified`, no harness published, and cross-vendor prices are not in any TypeSafe source. Its $0.042/Mtok input with free output is `verified` ([[reference/models-and-pricing]]), and "~$4.20 per 100M tokens" follows from it. | [[cookbooks/parallel-questions]], [[ideas/patterns-data]] P18 | ## Documents | repo | stars/lang | what it does, and how it uses Jev | maps to | |---|---|---|---| | [docjev](https://github.com/jerryjliu/docjev) | 163/Py | Two jobs: **classify** one PDF/DOCX/PPTX into one category with probabilities and review flags, and **split** a packet into ordered categories and page ranges with optional per-document PDF export. LiteParse extracts page text locally; only normalised page text reaches Jev (PDF bytes leave only if you pick the optional LlamaParse OCR tiers). Rules are stable category ids plus purpose descriptions, with separate `instructions` and `splitting_instructions` ("Keep continuation pages together. Different invoice references identify separate documents, even when adjacent documents share a category"). Splitting is page-level and contiguous, every split covers each canonical page exactly once, and an oversized page/context pair **fails explicitly** rather than truncating. The README is unusually careful about what the numbers are: the selected-category probability and provider confidence are different values, neither is claimed calibrated, and a segment's mean category probability is an average of page scores, not a joint probability. | [[cookbooks/hierarchical-classification]], [[ideas/patterns-data]] P26 | | [tax-doc-classifier](https://github.com/kyotofin/tax-doc-classifier) | 333/TS | Tax-form page classifier, no training: a JSON file of form descriptions generated from the IRS's own PDFs. One request per page: `Choice` over 7 page kinds plus `Choice` over 230 forms with `not_in_this_list`; a second small `Choice` only when one of five parent forms wins. Gate at 0.95 on the minimum confidence, below it fall back to the old path. Author-measured: 0 wrong on 1,067 pages (38 under the gate), $0.00115/page vs $0.039 and ~0.5 s vs ~3.3 s for its Claude Sonnet predecessor. 230 options is `verified` under the 255 limit. Swappable `Backend` interface | [[ideas/patterns-data]] P26, [[cookbooks/hierarchical-classification]] | **The 40-document pilot, as the README states it** (independent, author-run, attributed): "Both engines classified 40/40 originals correctly; Jev split 7/8 packets exactly and Luna split 8/8." Medians on the same LiteParse text, decision time only, concurrency 1, retries off: classification 138.6 ms for Jev 1.13.0 vs 794.3 ms for GPT-5.6 Luna (5.73×); splitting 209.6 ms vs 1,352.3 ms (6.45×). Measured decisions cost an estimated $0.011663 for Jev and $0.046894 for Luna. Both engines found all 32 true packet boundaries, including all four adjacent same-category boundaries; Jev's one extra boundary fell before a Federal Reserve statement's implementation attachment, which the frozen rules treat as part of the publication. The author's own caveats stand: a small convenience sample, shared source and template families, uncontrolled provider caching, no confidence interval and no repeat-stability claim. Cross-checked in [[ideas/field-reports]]. ## Moderation, judging and media | repo | stars/lang | what it does, and how it uses Jev | maps to | |---|---|---|---| | [youtube-sponsor-detection](https://github.com/trungdq88/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% | [[cookbooks/semantic-find]], [[ideas/patterns-data]] P27 | | [jevmeter](https://github.com/ChetasLua/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 | [[cookbooks/consistency-noul]], [[ideas/patterns-data]] P27 | | [Jev-Moderation-Bot](https://github.com/brainstormity/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 | [[patterns/composite-scoring]], [[ideas/patterns-data]] P16 | | [jev-as-a-judge](https://github.com/danielgshea/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 | [[guides/testing-and-evaluation]], [[ideas/patterns-data]] P15 | ## Real-time, games, robotics and IoT | repo | stars/lang | what it does, and how it uses Jev | maps to | |---|---|---|---| | [typesafe-mario](https://github.com/fhshaik/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 | [[guides/choosing-a-primitive]], [[ideas/patterns-data]] P24 | | [jevpilot](https://github.com/standardagents/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 | [[concepts/state]], [[ideas/patterns-data]] P24 | | [jev-drone](https://github.com/RomanSlack/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 | [[guides/writing-instructions-and-criteria]], [[ideas/patterns-data]] P24 | | [HA-Jev](https://github.com/AboveColin/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 | [[guides/smart-home-demo]], [[ideas/patterns-data]] P24 | | [OneVOneJev](https://github.com/emrickgarrett/OneVOneJev) | 10/TS | Browser FPS where Jev is the opponent. A server-authoritative sim (60 Hz, 20 Hz snapshots) builds structured JSON state per **decision tick at ~9 Hz** and fans out `Choice`/`Noul` questions — move, yaw, pitch, ADS, fire, jump — through `@typesafe-ai/sdk` on `jev-latest`. The key never reaches the browser, and calls run only while a match is `playing` and both fighters are alive. A deterministic heuristic behind the same action interface takes over when TypeSafe is unreachable, so matches never stall — which is what makes 9 Hz viable at all: independent testers measured hosted round trips at 260–280 ms and advise against control loops faster than ~4 Hz ([[ideas/field-reports]]). | [[guides/choosing-a-primitive]], [[ideas/patterns-data]] P24 | ## Markets Nothing here is investment advice and nothing here is a recommendation to trade. `jev-1.13` is documented to be unreliable at arithmetic, numeric representations and date/time comparison — most of what a market decision rests on ([[concepts/jaggedness-jev-1-13]]). Read these as engineering demos of a tight decision loop, not as strategies. | repo | stars/lang | what it does, and how it uses Jev | maps to | |---|---|---|---| | [jev-trader](https://github.com/jarrodwatts/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**, and the author states profitability is unverified — a latency demo, not a trading system | [[concepts/jaggedness-jev-1-13]], [[ideas/patterns-data]] P25 | `irfndi/prism-liquidity-agent` (59★/TS, MIT) appears in the same roundup and is an autonomous Solana LP rebalancer with its own confidence gate (`CONFIDENCE_THRESHOLD` 0.65) — but its README mentions neither Jev nor TypeSafe, so it is not a Jev repo. See the index. ## Business and idea tools | repo | stars/lang | what it does, and how it uses Jev | maps to | |---|---|---|---| | [killmyidea](https://github.com/monteduro/killmyidea) | 51/TS | Describe a startup idea, get KILL / FIX / SHIP. One request, 10 questions in parallel: eight indie-hacker `Score`s (real problem, clear customer, demand, money, reach, different, buildable, shareable) whose five levels are each written as a concrete situation, plus a category `Choice` and an understandability question. Code does the rest — each 0–4 score × 25, weighted average with the two goal-defining questions counted twice, thresholds KILL < 50 / FIX 50–64 / SHIP 65+, and a clarity gate that asks for more detail below 0.3 understandability instead of showing a verdict. `SCORING_VERSION` pins the exact questions, weights and thresholds so old rows are never reinterpreted. Note it archives each evaluation, idea text included, to SQLite unless the user opts out. | [[patterns/composite-scoring]], [[concepts/score]] | | [notra](https://github.com/usenotra/notra) | 193/TS | GEO platform tracking brand mentions. Not documented — no Jev or TypeSafe mention in the README | [[ideas/patterns-business]] P21 | ## Open replicas and Jev-compatible servers None affiliated with TypeSafe. Numbers compared in [[ideas/field-reports]]. | repo | stars/lang | what it is, and its relation to Jev | maps to | |---|---|---|---| | [SemIf](https://github.com/TheoLeeCJ/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 | [[syntheses/jev-vs-llm-structured-outputs]] | | [NanoJev](https://github.com/TianyuCodings/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. | [[concepts/primitives]] | | [jevlike](https://github.com/vinnylarouge/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 | [[syntheses/jev-vs-llm-structured-outputs]] | | [openjev-sglang](https://github.com/ekzhang/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 | [[concepts/confidence]] | | [mini-jev](https://github.com/r-ms/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 | [[concepts/confidence]] | | [openjev](https://github.com/TheoLeeCJ/openjev) | 2310/Py | Same URL, stars and README as SemIf: one project after a rename ("SemIf (formerly OpenJev)"). Count it once | see SemIf | ## Related - [[ideas/community-repos]] — the index, top picks and the vetting checklist - [[ideas/repos-agents]] — coding agents, orchestration, memory, browser and computer use, integrations - [[ideas/patterns]] — the decision patterns these repos share, with fit verdicts - [[ideas/consult]] — answering "could Jev help this project?" - [[ideas/field-reports]] — independent evaluations and replica numbers - [[entities/github-repos]] — the official `typesafe-ai` repos ## Sources - raw/x-repos/INDEX.json and the per-repo captures listed in this page's frontmatter (metadata + README; 2026-09-20, the @charliejhills roundup 2026-09-21) - raw/x-repos/jerryjliu__docjev.md — the 40-document pilot numbers quoted above