Jev & Laya Projects on GitHub: Runtimes, Lists and Tools

Every project below was found on GitHub, and the star counts were read directly from the repository pages on September 21, 2026 — they change fast, so treat them as a snapshot. Nothing here is sponsored or affiliated with this site; links go straight to the source.

Open Laya runtimes

• mizorewww/laya-mlx★ 2,047

  Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

• mizorewww/laya-coreml★ 483

  Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

• wdobry/laya-playground★ 13

  A website, two games, a benchmark and an agent skill for Laya, the open-source decision model. Runs on your machine.

• cv/laya-plays-smb3★ 3

  World 1-1 cleared with unmodified Laya on DGX Spark. Model-driven jumping, replay-verified frames, and every decision recorded.

• ahmadjehad2000/laya-codex★ n/a

  Independent Codex MCP integration for Laya-MLX, with verified local inference, PoCs and evidence. Built on mizorewww/laya-mlx and Convai Innovations/Laya.

Awesome lists and indexes

• Anil-matcha/awesome-jev-by-typesafe★ 725

  Evidence-backed use cases, patterns, prompts, and starter code for TypeSafe Jev — a System One model for fast, typed, confidence-aware decisions in software.

• yibie/awesome-jev★ 707

  A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.

• v-modal/awesome-jev-tools★ 580

  A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

• logicrw/awesome-jev-projects★ 249

  Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync

• cobanov/awesome-jev★ 280

  A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.

• AbdelStark/awesome-typesafe★ 407

  A curated list of official resources and community projects for TypeSafe, System One models, and Jev.

• OmniJev/awesome-jev-gallery★ 123

  🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

• valentynkit/awesome-jev-typesafe★ 112

  Typed decisions with TypeSafe's Jev, the first System One model

• walidboulanouar/awesome-jev-use-cases★ 23

  Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API examples. CC0, sponsored by AY Automate.

Benchmarks, distills and open checkpoints

• jaredpalmer/kev★ 1,222

  tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own

• samuelfaj/distill★ 682

  Get FAR MORE done with FAR FEWER tokens 🔥

• wfzyx/von★ 268

  The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

• sutro-sh/jev-align★ 248

  Build calibrated AI Functions from human feedback using Jev and GEPA.

• ekzhang/openjev-sglang★ 239

  Jev-compatible API endpoint based on open models (prefill-only)

• Heman10x-NGU/openJev-verdict-2.0★ 211

  Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

• ikermoel/open-alternative-jev★ 39

  Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks

• intikhab49/open-jev-typed-decision-engine★ 27

  Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free

Apps, agents and integrations

• OpenByteInc/QuantDinger★ 11,861

  Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch

• reticlehq/reticle★ 779

  AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

• milind-soni/tiptour-macos★ 623

  Open-Source fast local computer use

• Asymptote-Labs/agent-beacon★ 461

  The cross-harness self-improving memory layer for AI agents.

• devagrawal09/jev-review★ 427

  A staged code-review workflow and local dashboard built with TypeSafe Jev.

• juspay/neurolink★ 134

  One TypeScript interface for 40 AI providers across three inference types — generate, stream, and decide. Decide returns typed, calibrated judgments (boolean/choice/score) via TypeSafe Jev, not text.

How to read this list

• Run something before you trust the numbers. Ports ship benchmark scripts precisely so you can reproduce them.
• Star counts measure attention, not quality. The 30-star eval harness that fixes your thresholds is worth more than the 700-star link list.
• Licences differ. Several of these are tooling around a hosted model with its own terms; check before you ship anything commercial.

Last updated: 2026-09-21 · sources & corrections