# GitHub trends for September 22, 2026

Peak magnitude of each repository on September 22, 2026 (UTC). Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.

1. **NandhaKishorM/laya** — 9.4 · Breakout · AI agents · Python · ≈ +3,381 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.md
2. **zai-org/ZCode** — 9.1 · Breakout · AI agents · TypeScript · ≈ +979 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/zai-org/ZCode.md
3. **mizorewww/laya-mlx** — 9.0 · Breakout · Language models · Python · ≈ +1,178 stars by the end of the day
   Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-mlx.md
4. **jaredpalmer/kev** — 8.8 · Breakout · Language models · Python · ≈ +761 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/jaredpalmer/kev.md
5. **browser-use/jev-ultrafast** — 8.7 · Peaking · AI agents · Python · ≈ +1,814 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/browser-use/jev-ultrafast.md
6. **jev-chat/jev-chat-jarvis** — 8.6 · Breakout · AI agents · Kotlin · ≈ +1,003 stars by the end of the day
   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 sent manually.
   Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-jarvis.md
7. **eternity4719/HowToLiveBetter** — 8.5 · Breakout · Productivity & self-hosted · HTML · ≈ +1,081 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/eternity4719/HowToLiveBetter.md
8. **Mak5er/AirCard** — 8.1 · Breakout · Apps · Swift · ≈ +720 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/Mak5er/AirCard.md
9. **hydra-db/open-glean** — 7.5 · Early signal · AI agents · TypeScript · ≈ +327 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/hydra-db/open-glean.md
10. **Open-Dev-Society/OpenStock** — 7.5 · Breakout · Finance & crypto · TypeScript · ≈ +509 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/Open-Dev-Society/OpenStock.md
11. **BuilderIO/agent-native** — 7.4 · Breakout · AI agents · TypeScript · ≈ +368 stars by the end of the day
   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 with a real UI for…
   Full card: https://gitnova.dev/en/r/BuilderIO/agent-native.md
12. **TheoLeeCJ/SemIf** — 7.4 · Peaking · Language models · Python · ≈ +405 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/TheoLeeCJ/SemIf.md
13. **volotat/mini-AGI** — 7.3 · Early signal · Language models · Python · ≈ +172 stars by the end of the day
   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 without catastrophic…
   Full card: https://gitnova.dev/en/r/volotat/mini-AGI.md
14. **mizorewww/laya-coreml** — 7.0 · Early signal · Language models · Python · ≈ +266 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-coreml.md
15. **QwenLM/Qwen-Image-2.1** — 7.0 · Early signal · Generative media · Python · ≈ +204 stars by the end of the day
   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, SGLang.
   Full card: https://gitnova.dev/en/r/QwenLM/Qwen-Image-2.1.md
16. **trycua/cua** — 6.9 · Breakout · AI agents · HTML · ≈ +260 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/trycua/cua.md
17. **caxete/crypto-tax-calculator** — 6.8 · Early signal · Finance & crypto · Python · ≈ +114 stars by the end of the day
   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, historical price…
   Full card: https://gitnova.dev/en/r/caxete/crypto-tax-calculator.md
18. **anthropics/financial-services** — 6.6 · Breakout · AI agents · Python · ≈ +222 stars by the end of the day
   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 Managed Agents API.
   Full card: https://gitnova.dev/en/r/anthropics/financial-services.md
19. **mvt-project/mvt** — 6.5 · Breakout · Security · Python · ≈ +195 stars by the end of the day
   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 Lab for…
   Full card: https://gitnova.dev/en/r/mvt-project/mvt.md
20. **robbietilton/Compositor** — 6.5 · Peaking · Apps · Swift · ≈ +343 stars by the end of the day
   A free, open-source raster image editor for macOS written in Swift — a Photoshop alternative focused on compositing and post-processing.
   Full card: https://gitnova.dev/en/r/robbietilton/Compositor.md
21. **typesafe-ai/skills** — 6.4 · Breakout · AI agents · ≈ +162 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/typesafe-ai/skills.md
22. **vercel-labs/json-render** — 6.4 · Breakout · AI agents · TypeScript · ≈ +206 stars by the end of the day
   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, PDF, email, video…
   Full card: https://gitnova.dev/en/r/vercel-labs/json-render.md
23. **FareedKhan-dev/train-llm-from-scratch** — 6.3 · Breakout · Language models · Python · ≈ +133 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/FareedKhan-dev/train-llm-from-scratch.md
24. **ruanyf/weekly** — 6.3 · Breakout · Learning & lists · ≈ +290 stars by the end of the day
   A weekly tech digest by Ruan Yifeng: articles, tools and resources, published every Friday. Also includes a section with programmer job postings.
   Full card: https://gitnova.dev/en/r/ruanyf/weekly.md
25. **Rizzo-AI-Academy/rizzo-flow** — 6.1 · Early signal · Language models · Python · ≈ +124 stars by the end of the day
   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 API.
   Full card: https://gitnova.dev/en/r/Rizzo-AI-Academy/rizzo-flow.md
26. **yibie/awesome-jev** — 6.1 · Early signal · Learning & lists · Python · ≈ +188 stars by the end of the day
   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).
   Full card: https://gitnova.dev/en/r/yibie/awesome-jev.md
27. **cloudflare/quiche** — 6.0 · Breakout · DevOps & infrastructure · Rust · ≈ +144 stars by the end of the day
   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 integration.
   Full card: https://gitnova.dev/en/r/cloudflare/quiche.md
28. **f/jev-leftpad** — 6.0 · Early signal · Other · JavaScript · ≈ +38 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/f/jev-leftpad.md
29. **mcncarl/jianying-headless** — 6.0 · Peaking · Generative media · Python · ≈ +134 stars by the end of the day
   Local automation tool for Jianying Professional on macOS: builds native drafts from a JSON plan, edits copies of existing multi-track projects, and exports MP4 via the native engine on demand. Requires installed Jianying 11.4.0/11.4.2 and…
   Full card: https://gitnova.dev/en/r/mcncarl/jianying-headless.md
30. **rmalde/minecraft-agent** — 6.0 · Early signal · AI agents · JavaScript · ≈ +76 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/rmalde/minecraft-agent.md
31. **bendlang/bend** — 5.9 · Peaking · Developer tools · TypeScript · ≈ +102 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/bendlang/bend.md
32. **coder/coder** — 5.9 · Breakout · DevOps & infrastructure · Go · ≈ +183 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/coder/coder.md
33. **kloxeld/xscrape** — 5.9 · Early signal · Data & analytics · Python · ≈ +52 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/kloxeld/xscrape.md
34. **latent-spaces/brag** — 5.9 · Peaking · AI agents · Python · ≈ +210 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/latent-spaces/brag.md
35. **newliver666/apk-reverse** — 5.9 · Early signal · Security · Python · ≈ +162 stars by the end of the day
   An Agent Skill for Android APK reverse engineering: unpacking, ad removal, dex patching, repacking, and runtime/server analysis. Loaded by an agent (Claude Code, Codex) while it works.
   Full card: https://gitnova.dev/en/r/newliver666/apk-reverse.md
36. **qwdwqfwq/topconf-paper-figure-gallery** — 5.9 · Early signal · Learning & lists · Python · ≈ +94 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/qwdwqfwq/topconf-paper-figure-gallery.md
37. **zhouxiaoka/autoclip** — 5.9 · Breakout · Generative media · Python · ≈ +281 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/zhouxiaoka/autoclip.md
38. **Albert-Weasker/niubigeo** — 5.8 · Breakout · Language models · TypeScript · ≈ +580 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/Albert-Weasker/niubigeo.md
39. **aru-labs/lossless-memory** — 5.8 · Early signal · AI agents · Python · ≈ +42 stars by the end of the day
   Local long-term memory for a personal AI: keeps every conversation line without summarization, with timestamps and time-first, words-second search.
   Full card: https://gitnova.dev/en/r/aru-labs/lossless-memory.md
40. **ethanplusai/astra-flash-orchestrator** — 5.8 · Early signal · AI agents · Python · ≈ +106 stars by the end of the day
   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 usage on large…
   Full card: https://gitnova.dev/en/r/ethanplusai/astra-flash-orchestrator.md
41. **tamaratran/fast-jev-compaction** — 5.8 · Cooling · AI agents · TypeScript · ≈ +288 stars by the end of the day
   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 usable as an npm library.
   Full card: https://gitnova.dev/en/r/tamaratran/fast-jev-compaction.md
42. **paperless-ngx/paperless-ngx** — 5.7 · Breakout · Productivity & self-hosted · Python · ≈ +85 stars by the end of the day
   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 and keep sensitive…
   Full card: https://gitnova.dev/en/r/paperless-ngx/paperless-ngx.md
43. **heyjunpenn/awesome-jev** — 5.6 · Early signal · Learning & lists · Astro · ≈ +122 stars by the end of the day
   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 ecosystem.
   Full card: https://gitnova.dev/en/r/heyjunpenn/awesome-jev.md
44. **jarrodwatts/jev-trader** — 5.6 · Peaking · Finance & crypto · TypeScript · ≈ +144 stars by the end of the day
   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 dry-run mode without a…
   Full card: https://gitnova.dev/en/r/jarrodwatts/jev-trader.md
45. **maanHimself/OpenDLSS-NR** — 5.6 · Early signal · Generative media · JavaScript · ≈ +84 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/maanHimself/OpenDLSS-NR.md
46. **wuyoscar/jev-skill** — 5.6 · Early signal · AI agents · Python · ≈ +85 stars by the end of the day
   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 prompts and skills.
   Full card: https://gitnova.dev/en/r/wuyoscar/jev-skill.md
47. **yifanzhang-pro/KLPO** — 5.6 · Early signal · Language models · Python · ≈ +42 stars by the end of the day
   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 loss…
   Full card: https://gitnova.dev/en/r/yifanzhang-pro/KLPO.md
48. **mabdulre9/electrical-engineering** — 5.5 · Early signal · Learning & lists · ≈ +68 stars by the end of the day
   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 enrollment or fees.
   Full card: https://gitnova.dev/en/r/mabdulre9/electrical-engineering.md
49. **receptron/laya** — 5.5 · Early signal · Language models · TypeScript · ≈ +78 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/receptron/laya.md
50. **yynxxxxx/Codex-X** — 5.5 · Breakout · AI agents · Rust · ≈ +114 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/yynxxxxx/Codex-X.md
51. **agent-substrate/substrate** — 5.4 · Breakout · AI agents · Go · ≈ +136 stars by the end of the day
   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 meant for running…
   Full card: https://gitnova.dev/en/r/agent-substrate/substrate.md
52. **Futureppo/typesafe_register** — 5.3 · Early signal · Other · Python · ≈ +49 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/Futureppo/typesafe_register.md
53. **pacifio/atlas** — 5.3 · Breakout · AI agents · TypeScript · ≈ +593 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/pacifio/atlas.md
54. **Tencent/BrowserSkill** — 5.3 · Peaking · AI agents · TypeScript · ≈ +136 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/Tencent/BrowserSkill.md
55. **TianyuCodings/NanoJev** — 5.3 · Peaking · Language models · Python · ≈ +147 stars by the end of the day
   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).
   Full card: https://gitnova.dev/en/r/TianyuCodings/NanoJev.md
56. **bespokelabsai/nimble** — 5.2 · Peaking · Language models · Python · ≈ +135 stars by the end of the day
   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 checks, and policy…
   Full card: https://gitnova.dev/en/r/bespokelabsai/nimble.md
57. **minorun365/minorun-marp-skill** — 5.2 · Early signal · Productivity & self-hosted · Python · ≈ +56 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/minorun365/minorun-marp-skill.md
58. **Zefan-Cai/Open-Jev** — 5.2 · Early signal · Language models · Python · ≈ +46 stars by the end of the day
   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 head and a local…
   Full card: https://gitnova.dev/en/r/Zefan-Cai/Open-Jev.md
59. **AnotiaWang/awesome-jev** — 5.1 · Early signal · Learning & lists · ≈ +62 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/AnotiaWang/awesome-jev.md
60. **jerryjliu/docjev** — 5.1 · Early signal · Language models · Python · ≈ +47 stars by the end of the day
   Python library, CLI, and local app for classifying documents into categories and splitting PDF/DOCX/PPTX packets into separate documents using natural-language rules.
   Full card: https://gitnova.dev/en/r/jerryjliu/docjev.md
61. **Lumid-Off/AirCard-Windows** — 5.1 · Early signal · Apps · Rust · ≈ +92 stars by the end of the day
   Native Windows app in Rust for customizing Apple Wallet cards and lockscreen passcode themes on iOS 18+ without jailbreak via the AirTraffic sync exploit.
   Full card: https://gitnova.dev/en/r/Lumid-Off/AirCard-Windows.md
62. **wfzyx/von** — 5.1 · Early signal · Language models · Python · ≈ +59 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/wfzyx/von.md
63. **adonis-singh/re4** — 5.0 · Early signal · Games & graphics · C++ · ≈ +26 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/adonis-singh/re4.md
64. **hypit-ai/hypit** — 5.0 · Peaking · AI agents · TypeScript · ≈ +508 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/hypit-ai/hypit.md
65. **Mapika/decider** — 5.0 · Early signal · Language models · Python · ≈ +57 stars by the end of the day
   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 class built on…
   Full card: https://gitnova.dev/en/r/Mapika/decider.md
66. **TianyuCodings/JevHarness** — 5.0 · Early signal · AI agents · Python · ≈ +59 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/TianyuCodings/JevHarness.md
67. **cloudflare/security-audit-skill** — 4.9 · Peaking · Security · JavaScript · ≈ +506 stars by the end of the day
   A coding-agent skill that turns the agent into a security auditor, running a multi-phase code audit with independently verified, machine-readable findings.
   Full card: https://gitnova.dev/en/r/cloudflare/security-audit-skill.md
68. **Crosstalk-Solutions/project-nomad** — 4.9 · Breakout · Productivity & self-hosted · TypeScript · ≈ +253 stars by the end of the day
   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 no internet required.
   Full card: https://gitnova.dev/en/r/Crosstalk-Solutions/project-nomad.md
69. **deepopen-com/deepopen** — 4.9 · Early signal · Language models · Python · ≈ +105 stars by the end of the day
   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 classification, routing and…
   Full card: https://gitnova.dev/en/r/deepopen-com/deepopen.md
70. **haplollc/ThinkingOrbs** — 4.9 · Early signal · Web & frontend · Swift · ≈ +40 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/haplollc/ThinkingOrbs.md
71. **affaan-m/ECC** — 4.8 · Steady · AI agents · JavaScript · ≈ +464 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/affaan-m/ECC.md
72. **awlevin/typesafe-computer-use** — 4.8 · Early signal · AI agents · Python · ≈ +48 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/awlevin/typesafe-computer-use.md
73. **benjiyaya/ComfyUI-Qwen-Image-2.1-Prompt-Enhancer** — 4.8 · Early signal · Generative media · Python · ≈ +39 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/benjiyaya/ComfyUI-Qwen-Image-2.1-Prompt-Enhancer.md
74. **happy666End/MenuBarHider** — 4.8 · Early signal · Productivity & self-hosted · Swift · ≈ +79 stars by the end of the day
   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 macOS 27 rewrote…
   Full card: https://gitnova.dev/en/r/happy666End/MenuBarHider.md
75. **higgsfield-ai/higgsfield** — 4.8 · Peaking · Language models · Jupyter Notebook · ≈ +54 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/higgsfield-ai/higgsfield.md
76. **kerpopule/hermes-jev-skills** — 4.8 · Early signal · AI agents · Python · ≈ +51 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/kerpopule/hermes-jev-skills.md
77. **Mak5er/AirCard-iOS** — 4.8 · Early signal · Apps · Swift · ≈ +77 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/Mak5er/AirCard-iOS.md
78. **amitshekhariitbhu/ai-engineer-roadmap** — 4.7 · Early signal · Learning & lists · Markdown · ≈ +30 stars by the end of the day
   A step-by-step AI Engineering roadmap covering ML foundations, transformers, RAG, agents, and deployment, with a blog for every topic. For anyone aiming to become an AI/LLM/Agent engineer from scratch.
   Full card: https://gitnova.dev/en/r/amitshekhariitbhu/ai-engineer-roadmap.md
79. **anmolkapil/plexo** — 4.7 · Early signal · Developer tools · TypeScript · ≈ +78 stars by the end of the day
   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).
   Full card: https://gitnova.dev/en/r/anmolkapil/plexo.md
80. **cdyforever/how-to-live-better** — 4.7 · Early signal · Learning & lists · HTML · ≈ +71 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/cdyforever/how-to-live-better.md
81. **deepseek-ai/deepseek-harness** — 4.7 · Steady · AI agents · TypeScript · ≈ +587 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/deepseek-ai/deepseek-harness.md
82. **juspay/hyperswitch** — 4.7 · Breakout · Finance & crypto · Rust · ≈ +35 stars by the end of the day
   Open-source composable payments infrastructure in Rust: routing transactions across 120+ providers, retries, a PCI-compliant vault, reconciliation and cost observability. For teams that want to own their payments stack without vendor…
   Full card: https://gitnova.dev/en/r/juspay/hyperswitch.md
83. **Promethe-us/awesome-jev** — 4.7 · Early signal · Learning & lists · ≈ +49 stars by the end of the day
   A community-curated list of resources about Jev, TypeSafe AI's non-autoregressive "System One" decision model, covering its launch week: official docs, SDKs, demos, papers, media coverage and criticism.
   Full card: https://gitnova.dev/en/r/Promethe-us/awesome-jev.md
84. **ysh1112/codex-model-watch** — 4.7 · Early signal · Developer tools · HTML · ≈ +42 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/ysh1112/codex-model-watch.md
85. **akitaonrails/ai-memory** — 4.6 · Breakout · AI agents · Rust · ≈ +269 stars by the end of the day
   Long-term memory server for AI coding agents: stores notes as a markdown wiki and hands off context between different agents and machines. Lets you resume a task in another CLI without re-explaining architecture or open questions.
   Full card: https://gitnova.dev/en/r/akitaonrails/ai-memory.md
86. **FerryCorleone/crush-monitor** — 4.6 · Early signal · AI agents · TypeScript · ≈ +35 stars by the end of the day
   A local web tool that analyzes WeChat chat logs copied from the app using the Jev model: it shows emotions, intents, a liking-signal score and grades your own replies. Runs on your machine with your own TypeSafe API key.
   Full card: https://gitnova.dev/en/r/FerryCorleone/crush-monitor.md
87. **kyle-pena-nlp/jevchat** — 4.6 · Early signal · Language models · Python · ≈ +17 stars by the end of the day
   An experimental chatbot that generates replies by asking the Jev model which symbol, word or hypothesis comes next; built for fun, not practical use.
   Full card: https://gitnova.dev/en/r/kyle-pena-nlp/jevchat.md
88. **NxcoreAI/NxMem** — 4.6 · Early signal · AI agents · TypeScript · ≈ +185 stars by the end of the day
   A context and long-term memory engine for LLM agents: turns conversations and documents into structured facts, manages short- and long-term memory, and assembles cited context packs.
   Full card: https://gitnova.dev/en/r/NxcoreAI/NxMem.md
89. **ryana/jevify** — 4.6 · Early signal · AI agents · ≈ +57 stars by the end of the day
   A set of prompts for coding agents that helps investigate what TypeSafe's structured decision model Jev could enable in an existing project.
   Full card: https://gitnova.dev/en/r/ryana/jevify.md
90. **stablyai/orca** — 4.6 · Steady · AI agents · TypeScript · ≈ +530 stars by the end of the day
   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.
   Full card: https://gitnova.dev/en/r/stablyai/orca.md
91. **Haleclipse/CometixCode** — 4.5 · Early signal · AI agents · Rust · ≈ +26 stars by the end of the day
   An unofficial Rust reimplementation of Anthropic's Claude Code terminal UI on top of iocraft, porting the original file by file. Work in progress: large parts of the interactive loop, tools, permissions, MCP and slash commands are…
   Full card: https://gitnova.dev/en/r/Haleclipse/CometixCode.md
92. **lightorigins/Light-O1** — 4.5 · Early signal · Hardware, IoT & robotics · Python · ≈ +34 stars by the end of the day
   Light-O1-Preview is a text-to-action model that turns natural-language instructions into whole-body humanoid motion, outputting a (frames, 138) action array at 20 FPS. It is pretrained on human action recovered from internet video and…
   Full card: https://gitnova.dev/en/r/lightorigins/Light-O1.md
93. **xianxie6/qingming-riverside** — 4.5 · Early signal · Games & graphics · JavaScript · ≈ +22 stars by the end of the day
   An interactive scroll inspired by 'Along the River During the Qingming Festival': walking the streets, ferry rides, rain, and a boat-passing event under the Rainbow Bridge. Runs in the browser with no install.
   Full card: https://gitnova.dev/en/r/xianxie6/qingming-riverside.md
94. **lfarroco/ogre-battle-64-recomp** — 4.4 · Early signal · Games & graphics · Assembly · ≈ +12 stars by the end of the day
   Static recompilation of the N64 game Ogre Battle 64: Person of Lordly Caliber into a native PC executable using the N64Recomp toolchain. No game data is bundled — you must supply your own ROM dump.
   Full card: https://gitnova.dev/en/r/lfarroco/ogre-battle-64-recomp.md
95. **maxperry2/facebook-reporting-bot** — 4.4 · Early signal · Security · ≈ +44 stars by the end of the day
   A tool for automating the submission of Facebook reports against profiles, pages, and content that may violate platform policies. The README only describes the general process and contains no code.
   Full card: https://gitnova.dev/en/r/maxperry2/facebook-reporting-bot.md
96. **vinnylarouge/jevlike** — 4.4 · Cooling · Language models · Python · ≈ +41 stars by the end of the day
   A small trainable model that picks one option from a changing list of text options in a single forward pass, an open alternative to TypeSafe's Jev. Aimed at developers who need fast classification or menu selection over variable option…
   Full card: https://gitnova.dev/en/r/vinnylarouge/jevlike.md
97. **0xNatoshi/jev-codex-router** — 4.3 · Early signal · AI agents · JavaScript · ≈ +42 stars by the end of the day
   A local router for Codex that classifies each turn via Jev and picks the model, reasoning depth and speed mode. It plugs into an existing Codex Router install as a generic provider and saves about 60% versus a full-frontier baseline.
   Full card: https://gitnova.dev/en/r/0xNatoshi/jev-codex-router.md
98. **ahmedkhaleel2004/gitdiagram** — 4.3 · Peaking · Developer tools · TypeScript · ≈ +44 stars by the end of the day
   A web service that turns any public or private GitHub repository into an interactive architecture diagram: it analyzes the file tree, README and code excerpts with an LLM to build a system graph with links to sources.
   Full card: https://gitnova.dev/en/r/ahmedkhaleel2004/gitdiagram.md
99. **alibaba/open-code-review** — 4.3 · Cooling · Developer tools · Go · ≈ +378 stars by the end of the day
   AI code review tool from Alibaba: reads git diffs and, via an LLM agent with file access and repo search, produces line-level review comments. Ships with built-in rules (NPE, thread-safety, XSS, SQL injection) and a whole-file scan mode.
   Full card: https://gitnova.dev/en/r/alibaba/open-code-review.md
100. **bilawalsidhu/gods-eye-view** — 4.3 · Cooling · Data & analytics · JavaScript · ≈ +456 stars by the end of the day
   A browser-based spy-satellite simulator on a photorealistic 3D globe that unifies public feeds: aircraft, ships, satellites, earthquakes, cameras, and traffic. Runs locally, with each layer as a separate module.
   Full card: https://gitnova.dev/en/r/bilawalsidhu/gods-eye-view.md

For agents: https://gitnova.dev/llms.txt · search: https://gitnova.dev/api/v1/search?q=… · MCP: https://gitnova.dev/mcp · any page as Markdown — append .md to its URL