GitNova

GitHub seismograph — discoveries and growing interest

GitHub trends for September 22, 2026

What was taking off on GitHub on September 22, 2026: peak magnitude of the day, summary and where it was spotted.

  1. 9.7
    NandhaKishorM/laya

    Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.

    BreakoutAI agentsPython+4,184 stars that day

  2. 9.4
    google/ax

    A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and…

    BreakoutAI agentsGo+1,130 stars that day

  3. 9.2
    jaredpalmer/kev

    kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.

    BreakoutLanguage modelsPython+1,454 stars that day

  4. 9.1
    zai-org/ZCode

    Z.ai's coding agent workbench: an Electron desktop app, browser UI and terminal Agent CLI. The repo contains the client, backend, shared UI and the agent CLI/runtime sources.

    BreakoutAI agentsTypeScript+326 stars that day

  5. 9.0
    mizorewww/laya-mlx

    Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.

    BreakoutLanguage modelsPython+1,036 stars that day

  6. 8.8
    browser-use/jev-ultrafast

    A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.

    PeakingAI agentsPython+1,343 stars that day

  7. 8.6
    jev-chat/jev-chat-jarvis

    Android app that reads the on-screen chat via AccessibilityService, judges the other side's intent with the Jev model, and shows 3 ranked reply drafts in a translucent overlay. Replies are filled into the input box but…

    BreakoutAI agentsKotlin+1,829 stars that day

  8. 8.5
    eternity4719/HowToLiveBetter

    An evidence-based life guide: 498 recommendations on longevity, first aid, personal finance, law, employment, family and emigration. Each lists costs, benefits, evidence level and primary sources.

    BreakoutProductivity & self-hostedHTML+581 stars that day

  9. 8.2
    Mak5er/AirCard

    A macOS tool that customizes Apple Wallet cards and lockscreen passcode keypad themes on iOS 18+ without jailbreak via the airlift exploit. It lets you assign custom artwork to Apple Pay cards and apply .passthm themes.

    BreakoutAppsSwift+708 stars that day

  10. 8.1
    unreallabsai/unreal-agent

    Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components.

    Early signalAI agentsGo+892 stars that day

  11. 7.5
    hydra-db/open-glean

    An open-source AI workspace over Hydra DB: it answers questions across your files, notes and connected apps, writes the answer and cites its sources.

    Early signalAI agentsTypeScript+169 stars that day

  12. 7.5
    Open-Dev-Society/OpenStock

    An open-source alternative to paid market platforms: real-time price tracking, personalized alerts, and company insights. Built with Next.js, MongoDB, and Finnhub, free for everyone.

    BreakoutFinance & cryptoTypeScript+327 stars that day

  13. 7.5
    volotat/mini-AGI

    A byte-level continual-learning language model that assembles its own architecture, trains from scratch on a single 8 GB VRAM GPU, and keeps learning from everything it reads. An experiment showing continual learning…

    Early signalLanguage modelsPython+241 stars that day

  14. 7.4
    BuilderIO/agent-native

    An open-source TypeScript framework for building agentic apps where each capability is defined once as an action, used by the agent as a tool and called by the UI from code. Aimed at developers who need agents paired…

    BreakoutAI agentsTypeScript+194 stars that day

  15. 7.4
    TheoLeeCJ/SemIf-OpenJev

    An open reproduction of the Jev-style semantic decision interface: reads typed option probabilities directly from a 4B model's logits without generating text. Runs on a single RTX 3090.

    PeakingLanguage modelsPython+433 stars that day

  16. 7.1
    anthropics/financial-services

    Reference agents, skills, and MCP connectors for financial-services workflows: investment banking, equity research, private equity, and wealth management. Installs as a Claude Cowork plugin or deploys via the Claude…

    BreakoutAI agentsPython+373 stars that day

  17. 7.0
    browserbase/stagehand

    SDK in TypeScript, Python and Go for LLM-driven browser control: observe/act/extract find selectors, perform actions and return schema-validated data. Built for agents that operate websites like humans.

    BreakoutAI agentsTypeScript+448 stars that day

  18. 7.0
    mizorewww/laya-coreml

    Local port of the Laya model to Apple Core ML and Neural Engine: returns typed decisions (choice, score, yes/no) without token generation, with speed and energy benchmarks.

    Early signalLanguage modelsPython+280 stars that day

  19. 7.0
    QwenLM/Qwen-Image-2.1

    Qwen's open-source text-to-image generation and image editing model, including transparent RGBA output and up to 10 reference images. 7B generation component, 2K support, integrations with Diffusers, ComfyUI, vLLM,…

    Early signalGenerative mediaPython+157 stars that day

  20. 6.9
    ruanyf/weekly

    A weekly tech digest by Ruan Yifeng: articles, tools and resources, published every Friday. Also includes a section with programmer job postings.

    BreakoutLearning & lists+226 stars that day

  21. 6.9
    trycua/cua

    Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.

    BreakoutAI agentsRust+161 stars that day

  22. 6.8
    caxete/crypto-tax-calculator

    An open-source Python tool for crypto and personal income tax calculation that consolidates data from exchanges, wallets, and blockchain explorers into tax-compliant reports. It supports multiple jurisdictions,…

    Early signalFinance & cryptoPython+1 star that day

  23. 6.8
    dream-num/univer

    Open-source TypeScript SDK for embedding spreadsheet, document, and presentation editors into your own product, with a plugin architecture, Canvas rendering, a formula engine, and one Facade API for browser and…

    BreakoutDeveloper toolsTypeScript+589 stars that day

  24. 6.8
    mvt-project/mvt

    A collection of mobile forensics utilities that gather and analyze traces of compromise on Android and iOS devices, matching them against public indicators of compromise (IOCs). Built by Amnesty International Security…

    BreakoutSecurityPython+374 stars that day

  25. 6.6
    heyjunpenn/awesome-jev

    A catalog of 530 open-source projects built with Jev, TypeSafe AI's System One model for typed decisions inside software. It serves as a curated list of implementations, SDKs, and tooling for evaluating the Jev…

    Early signalLearning & listsAstro+302 stars that day

  26. 6.6
    yibie/awesome-jev

    A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions (choice, score, boolean with confidence).

    Early signalLearning & listsPython+214 stars that day

  27. 6.5
    robbietilton/Compositor

    A free, open-source raster image editor for macOS written in Swift — a Photoshop alternative focused on compositing and post-processing.

    PeakingAppsSwift+337 stars that day

  28. 6.5
    typesafe-ai/skills

    Agent skills for building with TypeSafe's System One API: typed decisions and probabilities for LLM agents. Installs as a Claude Code plugin or via skills.sh.

    BreakoutAI agents+177 stars that day

  29. 6.4
    vercel-labs/json-render

    Generative UI framework: an LLM turns prompts into JSON interfaces constrained to a catalog of components you define, keeping output predictable and safe. Supports React, Vue, Svelte, Solid, React Native, Next.js, 3D,…

    BreakoutAI agentsTypeScript+103 stars that day

  30. 6.3
    FareedKhan-dev/train-llm-from-scratch

    Educational project: a from-scratch PyTorch Transformer plus a full LLM training pipeline — from raw text through SFT, reward modeling, PPO/DPO/GRPO to chat, without transformers, trl or peft.

    BreakoutLanguage modelsPython+66 stars that day

  31. 6.2
    anmolkapil/plexo

    Download manager for Windows and macOS that speeds up downloads by splitting files into 8 MB chunks fetched in parallel across multiple network interfaces (Wi-Fi, Ethernet, USB tethering).

    Early signalDeveloper toolsTypeScript+339 stars that day

  32. 6.2
    freestylefly/WeChatBridge

    A native macOS tool that uses a Share Extension to take a WeChat chat export and forward it to AI agents (Codex, Claude, Doubao, etc.) or archive it into Obsidian. Runs fully locally without reading the WeChat database.

    Early signalProductivity & self-hostedSwift+212 stars that day

  33. 6.2
    zhouxiaoka/autoclip

    AI-powered video clipping tool that downloads videos from YouTube and Bilibili, analyzes content with Qwen LLM, and automatically extracts highlight clips and generates compilations.

    BreakoutGenerative mediaPython+233 stars that day

  34. 6.1
    cloudflare/quiche

    A Rust implementation of the QUIC transport protocol and HTTP/3 with a low-level API: the application handles sockets, event loop and timers itself. Used in Cloudflare's edge network, Android's DNS resolver and curl…

    BreakoutDevOps & infrastructureRust+62 stars that day

  35. 6.1
    jev-chat/jev-chat-windows

    A reply helper for WeChat on Windows: it captures the window, reads incoming messages with offline OCR, infers the other person's intent, and offers 3 candidate replies to insert into the input box. Sending is always…

    Early signalAI agentsPython+174 stars that day

  36. 6.1
    maanHimself/OpenDLSS-NR

    A Vulkan reimplementation of NVIDIA's DLSS 5 Neural Rendering network, bit-exact against the original. Requires your own weights and an NVIDIA Ada or newer GPU.

    Early signalGenerative mediaJavaScript+113 stars that day

  37. 6.1
    Rizzo-AI-Academy/rizzo-flow

    A local-first implementation of the Jev idea: an LLM returns typed decisions (boolean, choice, score, numeric) with probabilities in a single forward pass, without generating tokens. Compatible with the TypeSafe HTTP…

    Early signalLanguage modelsPython+100 stars that day

  38. 6.0
    f/jev-leftpad

    A joke npm library that left-pads strings by calling TypeSafe's Jev AI model instead of the built-in padStart(). Made for laughs and explicitly not for production.

    Early signalOtherJavaScript+7 stars that day

  39. 6.0
    miuuyy/Astra-Ares

    Experimental reference tool that dynamically selects reasoning effort for GPT-6 Astra via Jev during Codex tasks to reduce token usage. Requires building a patched Codex CLI from source.

    Early signalAI agentsJavaScript+145 stars that day

  40. 6.0
    rmalde/minecraft-agent

    An AI agent that plays Minecraft Java 1.16.5: the Astra GPT planner sets objectives, JEV picks actions, and Mineflayer executes them via the normal player protocol. Includes run recording and verification.

    Early signalAI agentsJavaScript+29 stars that day

  41. 5.9
    Amal-David/awesome-jev

    A curated catalog of projects, demos and SDKs for TypeSafe Jev, a model that answers typed questions about text or JSON. It helps move from a demo clip to understandable code and separates reviewed sources from the…

    Early signalLearning & listsPython+141 stars that day

  42. 5.9
    bendlang/bend

    Bend 2 is a dependently-typed programming language with proofs that compiles to CPU and GPU. It lets you declare laws in LAWS.bend that the compiler mechanically verifies, blocking AI-agent mistakes.

    PeakingDeveloper toolsTypeScript+132 stars that day

  43. 5.9
    coder/coder

    Self-hosted platform for cloud development environments and AI coding agents: workspaces are defined in Terraform, connected via a Wireguard tunnel, and shut down automatically when idle.

    BreakoutDevOps & infrastructureGo+92 stars that day

  44. 5.9
    kloxeld/xscrape

    Async Python client for collecting public data from X (Twitter): posts, profiles, threads, replies and media. Supports account pool, adaptive rate limiting and export to JSON/CSV/SQLite.

    Early signalData & analyticsPython+0 stars that day

  45. 5.9
    latent-spaces/brag

    An agent skill (Claude Code, Codex, opencode, etc.) that turns a project you just built into a short launch video with music, motion, and share copy — in one command. Rendering is powered by Hyperframes.

    PeakingAI agentsPython+206 stars that day

  46. 5.9
    qwdwqfwq/topconf-paper-figure-gallery

    A searchable static gallery of 2,298 hand-curated Figure 1 and teaser figures from ICLR, ICML, NeurIPS, CVPR, ACL and AAAI (2023-2025), meant as inspiration for designing paper overview figures.

    Early signalLearning & listsHTML+39 stars that day

  47. 5.9
    tamaratran/fast-jev-compaction

    Claude Code plugin that replaces context compaction summaries with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. Also…

    CoolingAI agentsTypeScript+225 stars that day

  48. 5.8
    Albert-Weasker/niubigeo

    Open-source tool for tracking brand visibility and competitors in AI answers: given a domain, it shows how models describe your product, whom they recommend, and which sources they cite.

    BreakoutLanguage modelsTypeScript+32 stars that day

  49. 5.8
    aru-labs/lossless-memory

    Local long-term memory for a personal AI: keeps every conversation line without summarization, with timestamps and time-first, words-second search.

    Early signalAI agentsPython+12 stars that day

  50. 5.8
    ethanplusai/codex-on-crack

    A Codex skill that splits coding work between two models: Astra plans, reviews and makes decisions, while DeepSeek V4.1 Flash handles bulk implementation, testing and debugging. Aims to cut the cost of expensive model…

    Early signalAI agentsJavaScript+88 stars that day

  51. 5.7
    jev-chat/jev-chat-jarvis-mac

    A macOS app that OCR-reads WeChat messages on screen and uses a local model to classify intent and risk, suggesting reply candidates. Read-only, with no injection into WeChat.

    Early signalAI agentsPython+114 stars that day

  52. 5.7
    paperless-ngx/paperless-ngx

    Paperless-ngx is a self-hosted document management system that scans, OCRs, indexes and archives physical documents into a searchable online archive. It is aimed at individuals and small teams who want to go paperless…

    BreakoutProductivity & self-hostedPython+43 stars that day

  53. 5.7
    yynxxxxx/Codex-X

    Cross-platform GUI tool for OpenAI Codex (desktop/CLI): manage providers and APIs, prompt templates, sessions, Skills/MCP and TOML config without hand-editing files.

    BreakoutAI agentsRust+75 stars that day

  54. 5.6
    agent-substrate/substrate

    Agent Substrate is a secure-by-default agent execution runtime built on Kubernetes that multiplexes many "actors" onto a small pool of workers with sub-second suspend/resume and isolation via microVMs and gVisor. It is…

    BreakoutAI agentsGo+315 stars that day

  55. 5.6
    hydra-db/hydradb

    HydraDB is a distributed graph database written in Rust that stores the graph durably on S3-compatible object storage, with separate data nodes and indexers. It supports OpenCypher queries, GraphBLAS traversal, Neo4j…

    BreakoutBackend & databasesRust+227 stars that day

  56. 5.6
    jarrodwatts/jev-trader

    Trading bot for the Kuru DEX on Monad: every block (~300 ms) an AI model decides buy or sell from the MON-USDC order book and posts a post-only limit order one tick inside the touch, earning the spread. Includes a…

    PeakingFinance & cryptoTypeScript+159 stars that day

  57. 5.6
    Nasiko-Labs/nasiko

    A single control-plane for AI agents: deploy, route, proxy A2A traffic, plus MCP gateway, LLM router and tracing in one Rust process.

    BreakoutAI agentsRust+230 stars that day

  58. 5.6
    Tencent/BrowserSkill

    BrowserSkill connects AI agents (Cursor, Claude Code, Codex, etc.) to your already logged-in browser via the bsk CLI and an extension, letting the agent work in a separate window without interrupting you.

    PeakingAI agentsTypeScript+213 stars that day

  59. 5.6
    wuyoscar/jev-skill

    A collection of skills and scenarios for Jev, a service that classifies and scores candidate decisions while your agent supplies context and does the work. Installs into Codex, Claude Code or OpenCode as a set of…

    Early signalAI agentsPython+34 stars that day

  60. 5.6
    yifanzhang-pro/KLPO

    KLPO is a critic-free, single-rollout reinforcement learning method for training agentic language models, using token regression and Monte Carlo KL estimation instead of value models or response groups. It provides the…

    Early signalLanguage modelsPython+5 stars that day

  61. 5.5
    mabdulre9/electrical-engineering

    A curated list of free university-level electrical engineering courses (MIT, Stanford, Yale, NPTEL, etc.) covering math, physics, circuits, machines, communications and control. For self-taught EE study without…

    Early signalLearning & lists+20 stars that day

  62. 5.5
    malevrigns/agent-jev

    AgentJev-0.6B is a specialist decision model for AI agent loops: it takes unstructured state (diffs, traces, logs) plus typed questions and returns a probability distribution over options in a single forward pass with…

    Early signalAI agentsPython+199 stars that day

  63. 5.5
    receptron/laya

    TypeScript wrapper for running the open-source Laya System-1 decision model via ONNX Runtime: takes a state and typed questions, returns answers with calibrated probabilities in one forward pass.

    Early signalLanguage modelsTypeScript+82 stars that day

  64. 5.4
    cloudflare/security-audit-skill

    A coding-agent skill that turns the agent into a security auditor, running a multi-phase code audit with independently verified, machine-readable findings.

    PeakingSecurityJavaScript+876 stars that day

  65. 5.4
    wfzyx/von

    An open-source non-autoregressive System One decision model for classification, intent routing, and guardrail validation without text generation, with calibrated probabilities and sub-25ms latency.

    Early signalLanguage modelsPython+100 stars that day

  66. 5.3
    Futureppo/typesafe_register

    A Python script for bulk-registering accounts on typesafe.ai with automatic API Key creation; supports multithreading. Stated as a tool for learning and research.

    Early signalOtherPython+15 stars that day

  67. 5.3
    Lumid-Off/AirCard-Windows

    Native Windows app in Rust for customizing Apple Wallet cards and lockscreen passcode themes on iOS 18+ without jailbreak via the AirTraffic sync exploit.

    Early signalAppsRust+113 stars that day

  68. 5.3
    pacifio/atlas

    Atlas is source control for coding agents: it links every commit back to the agent session with its prompts, tool calls and reasoning, and lets you run multiple agents side by side with shared memory.

    BreakoutAI agentsRust+86 stars that day

  69. 5.3
    TianyuCodings/NanoJev

    A nano replica of Jev built on Qwen3-0.6B that outputs probability distributions over candidates in a single forward pass with no token decoding, plus a training pipeline and game demos (maze, Snake).

    PeakingLanguage modelsPython+113 stars that day

  70. 5.3
    Zefan-Cai/Open-Jev

    Open-Jev serves a context, questions and candidate answers to Qwen-based models and returns typed probabilities directly, without autoregressive generation or JSON parsing. It provides LoRA adapters, a scalar decision…

    Early signalLanguage modelsPython+81 stars that day

  71. 5.2
    bespokelabsai/nimble

    Nimble is a model and training recipe for fast typed decisions over text: given a flat schema of enum and boolean fields, it picks an answer and returns probabilities for each option. It targets routing, condition…

    PeakingLanguage modelsPython+98 stars that day

  72. 5.2
    hypit-ai/hypit

    Hypit gives AI agents a language and system to create video: the agent clones a viral clip as an editable workflow — footage, captions, B-roll and effects anchored to words instead of seconds.

    PeakingAI agentsTypeScript+793 stars that day

  73. 5.2
    jerryjliu/docjev

    Python library, CLI, and local app for classifying documents into categories and splitting PDF/DOCX/PPTX packets into separate documents using natural-language rules.

    Early signalLanguage modelsPython+70 stars that day

  74. 5.2
    lordx64/phantom-kv

    Removes refusal behavior from language models by grafting a small trained KV-cache bank into the context, without editing weights or projecting activations, and is fully reversible.

    Early signalLanguage modelsPython+72 stars that day

  75. 5.2
    Mak5er/AirCard-iOS

    iOS app that writes custom artwork into iOS 27 system caches over a local loopback tunnel, letting you restyle Apple Wallet cards and the lock screen passcode keypad directly on the iPhone.

    Early signalAppsSwift+132 stars that day

  76. 5.2
    minorun365/minorun-marp-skill

    A skill set for AI agents (Claude Code) and humans for building conference slides with Marp: rules for storytelling, figures, and a dark theme, plus scripts to inspect PDF and SVG output.

    Early signalProductivity & self-hostedPython+14 stars that day

  77. 5.1
    AnotiaWang/awesome-decision-models

    A curated list of applications, libraries, and resources for Jev, TypeSafe's System One model that evaluates typed questions against a state and returns structured answers with probabilities.

    Early signalLearning & listsPython+28 stars that day

  78. 5.1
    CTNicholas/jev-workflow-builder

    A TypeScript demo app for building multiplayer workflows that wire together Jev and LLMs using Liveblocks. It lets you assemble call chains, invoke them via REST API, and see other participants' state and cursors.

    Early signalAI agentsTypeScript+51 stars that day

  79. 5.1
    dorkitude/webctl

    A web search CLI for AI agents that filters and deduplicates search results and page chunks via Jev, saving context tokens.

    Early signalAI agentsGo+80 stars that day

  80. 5.1
    kerpopule/hermes-jev-skills

    A set of eight SKILL.md files and a CLI that wires the Jev decision model into Hermes, Claude Code and Codex agents for model routing, memory filtering, skill selection and GUI actions.

    Early signalAI agentsPython+137 stars that day

  81. 5.1
    TianyuCodings/JevHarness

    A tool where an LLM authors a task-specific harness for fast Jev decisions: code computes features, Jev makes fuzzy decisions, and the harness can be improved via rewards and full execution traces.

    Early signalAI agentsPython+29 stars that day

  82. 5.1
    upscayl/upscayl

    Cross-platform open-source desktop app that enlarges and enhances low-resolution images using AI models (Real-ESRGAN, NCNN Vulkan).

    BreakoutGenerative mediaTypeScript+79 stars that day

  83. 5.0
    adonis-singh/re4

    A complete byte-identical decompilation of Resident Evil 4 for the GameCube (G4BE08 debug build) into C/C++, reproducing main.dol and all 110 REL overlays.

    Early signalGames & graphicsC+++11 stars that day

  84. 5.0
    Crosstalk-Solutions/project-nomad

    Offline-first knowledge and education server: a Docker-orchestrating management UI and API that hosts offline Wikipedia, books, Khan Academy courses, maps, and a local AI chat with RAG. Runs on your own hardware with…

    BreakoutProductivity & self-hostedTypeScript+136 stars that day

  85. 5.0
    FluidInference/FluidUse

    Local computer use on Apple silicon: reads forms in macOS apps via the Accessibility API, asks a small on-device model what belongs in each field, and types the answer into the real app.

    Early signalAI agentsSwift+64 stars that day

  86. 5.0
    Mapika/decider

    A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model…

    Early signalLanguage modelsPython+27 stars that day

  87. 5.0
    stablyai/orca

    Orca is an ADE for running a fleet of parallel coding agents (Claude Code, Codex, OpenCode, etc.) in isolated git worktrees with a unified interface, mobile companion, and remote runtime.

    SteadyAI agentsTypeScript+674 stars that day

  88. 4.9
    cdyforever/how-to-live-better

    A single-file HTML reading page for the open book "High Cost-Performance Life Guide" — 528 tips across 32 sections, searchable, offline-capable, zero dependencies.

    Early signalLearning & listsHTML+72 stars that day

  89. 4.9
    deepopen-com/deepopen

    Open-source non-autoregressive System 1 decision engine for typed decisions: returns typed answers (choice, score, noul) in a single forward pass across 100+ languages without generating text. Suited for…

    Early signalLanguage modelsPython+67 stars that day

  90. 4.9
    deepseek-ai/deepseek-harness

    Open-source agent harness by DeepSeek AI written in TypeScript, built on an everything-is-a-plugin architecture powered by Cordis. It runs as a web UI via npx and serves as a base for composing AI agents from plugins.

    SteadyAI agentsTypeScript+759 stars that day

  91. 4.9
    haplollc/ThinkingOrbs

    A SwiftUI package with nine dotted, genuinely 3D loading indicators for AI and agent interfaces, each mapped to a specific agent state like searching, solving or composing.

    Early signalWeb & frontendSwift+20 stars that day

  92. 4.9
    wdobry/laya-playground

    A playground for Laya, the open-source decision model: a website, three games, a benchmark and an agent skill. A local server takes typed questions and returns probabilities in one forward pass.

    Early signalLanguage modelsJavaScript+54 stars that day

  93. 4.8
    affaan-m/ECC

    A performance optimization system for coding agents: a set of agents, skills, memory, and rules that adds a plan-test-review-remember workflow to Claude Code, Codex, Cursor, and other harnesses.

    SteadyAI agentsJavaScript+564 stars that day

  94. 4.8
    awlevin/typesafe-computer-use

    Drives macOS toward a goal typed in plain English: OCR the screen, pick the next action via a TypeSafe classifier, click. Costs about $0.0002 per step and never sends screenshots to large models.

    Early signalAI agentsPython+51 stars that day

  95. 4.8
    benjiyaya/ComfyUI-Qwen-Image-2.1-Prompt-Enhancer

    ComfyUI custom nodes wrapping Qwen-Image-2.1 prompt-enhancer models: expand short text into detailed prompts for text-to-image and rewrite vague edit instructions using source images.

    Early signalGenerative mediaPython+15 stars that day

  96. 4.8
    happy666End/MenuBarHider

    A macOS 27 utility that hides menu bar icons using two separators and the private MenuBarAgent API, without Screen Recording permission. It targets users whose Hidden Bar, Ice and similar managers stopped working after…

    Early signalProductivity & self-hostedSwift+17 stars that day

  97. 4.8
    higgsfield-ai/higgsfield

    Fault-tolerant GPU orchestration and ML framework for distributed training of models with billions to trillions of parameters, including LLMs. Manages node access, experiment queueing, and GitHub Actions integration.

    PeakingLanguage modelsJupyter Notebook+25 stars that day

  98. 4.8
    ipenywis/laya-ultrafast

    A local port of the jev-ultrafast browser agent that makes action decisions with the open-weight Laya model via MLX instead of a hosted API. Apple Silicon only, and it runs browser tasks without per-step cost.

    Early signalAI agentsPython+57 stars that day

  99. 4.8
    laoma528/awesome-zhuiju-free

    A curated list of free movie and TV streaming resources: online sites, apps, cloud and torrent search, subtitles, TVBox configs, IPTV and related open-source projects. Resources are hand-picked and checked daily for…

    BreakoutProductivity & self-hostedJavaScript+418 stars that day

  100. 4.8
    ysh1112/codex-model-watch

    A local Python tool that monitors Codex model usage: token consumption, 5h/7d quota levels, capacity rejections, and actively probes for silent model substitution via a minimal request.

    Early signalDeveloper toolsHTML+29 stars that day