awesome-typesafe
Curated list of official resources and community projects for TypeSafe, System One models, and Jev, with a GitHub Pages site.
Find official documentation, practical articles, and community-maintained lists for building with Jev.
84 entries in the current community snapshotCurated list of official resources and community projects for TypeSafe, System One models, and Jev, with a GitHub Pages site.
A curated list of awesome Jev / TypeSafe System One applications, libraries, and resources.
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.
Company homepage, waitlist, and product overview.
Introduction, primitives, patterns, cookbooks, HTTP API, and SDK references.
Shortest path from an API key to a typed decision.
Paste a state, add questions, and see typed answers in the browser.
Request and response contract for POST /v1/systemone.
Choice, Score, and Noul: the three question types and what they return.
Speculative fan-out, confidence-gated routing, composite scoring, and intent routing.
Reproducible recipes: parallel questions, reranking, guardrails, citation checks, extraction, hierarchical classification.
Official interactive demo of speculative fan-out: many questions in one call, code keeps the relevant answers.
Published eval methodology and per-model results for System One workflows.
Known failure modes of the current public model, documented by TypeSafe.
Launch post: architecture, RLCD training, pricing, Doom and Wikiracing demos, FAQ.
The case for machine-native intelligence built for software, not conversation.
Official TypeSafe server. Builder demos live in the Show and Tell channel.
Product and research updates.
1,800-point thread debating whether typed decisions replace LLM calls for classification, routing, and scoring.
Latent Space's launch-day roundup: over 100x faster and 200x cheaper than small frontier LLMs.
The Register on the launch, the Doom demo, and the $40M seed round.
The Neuron's explainer on AI decisions without a chatbot.
Every's Mike Taylor runs his whole archive through Jev.
Anthony Maio's essay on what a model that cannot generate text is for.
Release-week technical roundup: API, evals, adapter, and skill.
dev.to walkthrough of the Vercel AI SDK evaluate integration.
Independent walkthrough separating TypeSafe's published claims from public evidence.
Short practical intro with a Python ticket-triage example.
Practical guide: playground, Python and JS SDKs, raw HTTP, and the agent skill.
Head-to-head test at validating local event listings, with cost and latency.
Japanese walkthrough of what Jev is and is not.
Jev vs Jev gomoku with source and timing logs.
TypeSafe's founder on why RLCD-trained decision models are a shorter path to value than chat models.
Aaron Levin: 155x cheaper than Opus 5, about 20x faster, and it generalizes across operating systems.
Gregor Zunic's flight-search demo with a dynamic DOM action space.
Steve Krouse's playable 16-judgment demo and video.
Ephraim Duncan's demo where Jev decides which model should serve a request.
Video comparison against a structured-output LLM baseline.
Matched-precision comparison against a private fine-tuned classifier.
Test report using Jev to check each agent action first: most attacks caught, almost no false blocks.
Marcel Pociot's browser extension that collapses posts based on a Jev judgment.
Work-in-progress demo of Jev driving Minecraft, including fleeing zombies at night.
Guillermo Rauch: Jev reviews every fx command, faster and more accurate than a chat model.
Observe the accessibility tree, Jev chooses the next action, Stagehand executes.
Preview of fast browser use with Jev and OpenCode's browser CLI.
Browser extension that classifies an article's framing, type, topic, and loaded language with Jev.
Desktop writing app using Jev for fast structured writing judgments.
Jev trades 15-minute and 1-hour BTC, ETH, and SOL markets on Kalshi.
Task plus subscription list in, Jev picks which model or agent should handle it.
Jev labels category, urgency, and human-versus-auto handling for support tickets.
Racing UI wired to Jev driving decisions.
MCP skill router where Jev picks the relevant skills instead of a long agent search.
Work-in-progress PR reviewer with plain-English Jev rules.
Voice-dialog turn-end detection using Jev scores after speech.
Thread cataloguing the first wave of Jev tools: MCP servers, routers, reviewers, and browser agents.
Third-party write-up of the System One primitives, pricing, and vendor workflow evals.
DuckDB extension that classifies rows in CSV, Parquet, or DuckDB tables with Jev, about 10 seconds per 1,000 rows.
Near-real-time scoring of TikTok and Instagram hooks against about 100 personas.
Local tactics shrink 225 moves to about 40 candidates, then Jev picks among tiered options.
Two decision channels on ViZDoom, navigation at 5 Hz and combat at 12 Hz, with an 18-kill test run.
Brood War in WASM exposed as an MCP server, with Jev playing and still losing to a Zerg rush.
Jev versus a hand-built regex on 544 public data-protection resolutions: 98.2% agreement for about five cents.
Eval of Jev turning free-text player intent into typed server actions: 96% agreement, 317 ms median.
Short video explainer of how Jev's typed-decision loop works.
Page-level demo where Jev picks which candidate link to click toward a goal.
A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.
A source-backed Jev project directory with a reusable Jev-only GitHub review workflow.
Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync
Papers, open reproductions and independent evaluations behind System One models and Jev.
One direct Jev question per row against 12–14 Jev-scored dimensions with locally fitted weights on three classification tasks: 5,477 test rows, 25,174 Jev calls, $1.43. Decomposition wins on Japanese NLI (0.9076 vs 0.8373) but flags about 25× more hard benign rows as attacks (37.2% vs 1.5%).
Typed decisions with TypeSafe's Jev, the first System One model
A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.
Jev / TypeSafe System One 中文精选列表:官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测,附中文上手指南,每日自动收录 GitHub 热门项目。
A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.
Curated Jev resources and runnable examples for typed AI decisions.
An awesome collection of Jev use cases, workflows, and agent skills.
JEV HUB · X 上关于 TypeSafe AI「系统一模型」Jev 的长文与演示视频聚合(保留原链与作者)| 谁是专家 出品
A verified, community-maintained catalog of 485 open-source projects built with Jev.
Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results
⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.
📡 全网最全 · The world's most comprehensive tracker of the Jev (TypeSafe AI System One) ecosystem — 220+ documented cases · 108 confidence-graded entries · verified & rescanned every 3 hours · API access guide included
Evidence-backed use cases, patterns, and guidance for building with Jev, TypeSafe AI's System One model. Every claim is labeled and sourced.
Public examples of Jev used for robot control, 3D modeling and adjacent control tasks, with sources and archived media
A curated list of tools, integrations, and experiments built on Jev, TypeSafe AI's System One model for fast, typed decisions.