Three decision models, a coding workbench in three shells, and a reply copilot that never hits send

Fastest-growing this period

Counts come from GitHub's official stargazers/history endpoint: the stars gained on each day of the window. Project briefs and the reading notes below are editorial additions.

1. 1

   NandhaKishorM/laya : Answer typed questions about any text in one 33-millisecond forward pass

   Python

   A non-autoregressive decision engine that reads text, an email or a JSON document and returns a typed answer, a choice, a score or a yes/no flag, in one 33-millisecond forward pass. Three checkpoints cover English, over one hundred languages and typed workflows, and a built-in router picks one per request. Nothing is generated, so there is nothing to parse or hallucinate.

   +6,524
2. 2

   browser-use/jev-ultrafast : A browser agent that picks each click and typed word in one model call

   Python

   Give it one natural-language goal and it renders the page as a numbered table of controls. TypeSafe's Jev picks the operation and target element in one request, and a small LLM writes text only when a field needs filling, so no site scripts or screenshots drive the loop. The README's measured demo finds flights from Zürich to London in about seven seconds.

   +3,606
3. 3

   google/ax : Declare agent tasks in YAML, sandbox them, then SSH into a running one

   Go

   A declarative orchestrator from Google for agent workloads on a cluster, in the spirit of Kubernetes. One YAML file declares the task, pre-wired Git repos and MCP servers, a network allowlist and the model; ax apply launches it into a sandbox with CPU and memory limits, and ax ssh opens a shell inside a running agent to watch what it does.

   +2,530
4. 4

   mizorewww/laya-mlx : Typed decisions from the laya family, rebuilt to run natively on Apple Silicon

   Python

   A native Apple Silicon build of the laya typed-decision engine on Apple's MLX runtime, with no PyTorch, no Transformers dependency and no cloud API. A short English typed question is answered in about 13 milliseconds with zero output tokens, and the multilingual checkpoint is faster still. Weights download once, then every call runs fully local.

   +2,317
5. 5

   eternity4719/HowToLiveBetter : Life advice that logs what you spend, what you gain and how solid the evidence is

   HTML

   A Chinese guide of practical suggestions on health, money, scams and legal traps, from chronic disease and first aid to rent disputes and workplace compensation. Each entry records what you spend, what you get back and how strong the evidence is, citing only journal papers and official documents, with an online search page for quick lookups.

   +2,090
6. 6

   zai-org/ZCode : An AI coding workbench shipping as desktop app, browser UI and terminal agent

   TypeScript

   An AI coding workbench from Z.ai that runs as an Electron desktop app, a browser UI or a terminal agent, all built from one monorepo. The zcode command opens a TUI by default, its web mode serves the workbench on localhost, and the agent CLI and runtime source live in the same tree, so every surface can be built from source.

   +1,969
7. 7

   jev-chat/jev-chat-jarvis : A phone copilot that reads on-screen chats and drafts replies, sending stays yours

   Kotlin

   An Android assistant that follows conversations in any chat app via the accessibility service, never hooking or modifying the app. It first judges the other side's intent and a danger level, then drafts ranked candidate replies and pastes the one you pick into the input box; it never presses send and keys stay on the device. WeChat, QQ and X run the full pipeline.

   +1,903
8. 8

   jaredpalmer/kev : Small open decision models answering choice, yes/no and scoring questions in one request

   Python

   A family of small decision models built on Qwen3.5, with 0.8B, 4B and 9B variants you can run or train yourself. One request shares a single input across choice, yes/no and rating questions, each answered with probabilities instead of a single label. It serves locally on CUDA, ROCm and Apple Silicon, and a web playground shows how option order changes the answers.

   +1,497
9. 9

   Mak5er/AirCard : Reskin Apple Wallet cards and lockscreen passcode buttons on iOS, no jailbreak required

   Swift

   A macOS app that flashes custom artwork onto Apple Pay and Wallet cards and applies keypad themes to the iOS lock screen over USB, no jailbreak needed. Scan cards straight from the iPhone's Wallet tap, drag images onto card mockups, or open an existing passcode theme package in the built-in creator, tweak each key and flash the result.

   +1,366
10. 10

    Albert-Weasker/niubigeo : Check whether AI assistants recommend your product

    TypeScript

    Self-hosted tool that tests how different AI models describe your product. Enter a domain, pick models, and it runs keyword tests showing who appears in answers, how your brand is described and which sources are cited, with original responses open for inspection. Useful for teams wondering where they stand in AI answers. Needs Node.js 22+ and your own OpenRouter API key.

    +1,207

Ranking window: 2026-09-21 UTC, full day.