# GitHub trends for September 23, 2026 Peak magnitude of each repository on September 23, 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. **jaredpalmer/kev** — 8.9 · Breakout · Language models · Python · ≈ +1,354 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 2. **unreallabsai/unreal-agent** — 8.8 · Early signal · AI agents · Go · ≈ +841 stars by the end of the day Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components. Full card: https://gitnova.dev/en/r/unreallabsai/unreal-agent.md 3. **NandhaKishorM/laya** — 8.7 · Breakout · AI agents · Python · ≈ +3,806 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 4. **google/ax** — 8.6 · Breakout · AI agents · Go · ≈ +1,047 stars by the end of the day 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 restricts network… Full card: https://gitnova.dev/en/r/google/ax.md 5. **CopilotKit/openmuse** — 8.4 · Early signal · AI agents · TypeScript · ≈ +767 stars by the end of the day A personal AI agent with a browser, terminal, and files that carries out tasks on request and shows its work. Built with CopilotKit and AG-UI for iOS, Android, and web. Full card: https://gitnova.dev/en/r/CopilotKit/openmuse.md 6. **jev-chat/jev-chat-jarvis** — 8.2 · Breakout · AI agents · Kotlin · ≈ +1,709 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. **dream-num/univer** — 7.5 · Breakout · Developer tools · TypeScript · ≈ +586 stars by the end of the day 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 Node.js. Suited for SaaS,… Full card: https://gitnova.dev/en/r/dream-num/univer.md 8. **browser-use/jev-ultrafast** — 7.3 · Peaking · AI agents · Python · ≈ +1,209 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 9. **browserbase/stagehand** — 7.3 · Breakout · AI agents · TypeScript · ≈ +390 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/browserbase/stagehand.md 10. **Mak5er/AirCard** — 7.2 · Breakout · Apps · Swift · ≈ +641 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 11. **volotat/mini-AGI** — 7.2 · Early signal · Language models · Python · ≈ +214 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 12. **mizorewww/laya-mlx** — 7.1 · Peaking · Language models · Python · ≈ +923 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 13. **mvt-project/mvt** — 6.9 · Breakout · Security · Python · ≈ +353 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 14. **anthropics/financial-services** — 6.8 · Breakout · AI agents · Python · ≈ +364 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 15. **heyjunpenn/awesome-jev** — 6.8 · Early signal · Learning & lists · TypeScript · ≈ +282 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 16. **freestylefly/WeChatBridge** — 6.7 · Early signal · Productivity & self-hosted · Swift · ≈ +206 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/freestylefly/WeChatBridge.md 17. **TheoLeeCJ/SemIf** — 6.6 · Peaking · Language models · Python · ≈ +378 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 18. **Amal-David/awesome-jev** — 6.4 · Early signal · Learning & lists · Python · ≈ +122 stars by the end of the day 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 broader discovery queue. Full card: https://gitnova.dev/en/r/Amal-David/awesome-jev.md 19. **hydra-db/open-glean** — 6.2 · Early signal · AI agents · TypeScript · ≈ +141 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 20. **Open-Dev-Society/OpenStock** — 6.1 · Peaking · Finance & crypto · TypeScript · ≈ +303 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 21. **jev-chat/jev-chat-jarvis-mac** — 6.0 · Early signal · AI agents · Python · ≈ +115 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-jarvis-mac.md 22. **jev-chat/jev-chat-windows** — 6.0 · Early signal · AI agents · Python · ≈ +166 stars by the end of the day 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 manual. Full card: https://gitnova.dev/en/r/jev-chat/jev-chat-windows.md 23. **malevrigns/agent-jev** — 6.0 · Early signal · AI agents · Python · ≈ +177 stars by the end of the day 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 zero token decoding. Full card: https://gitnova.dev/en/r/malevrigns/agent-jev.md 24. **miuuyy/Astra-Ares** — 6.0 · Early signal · AI agents · JavaScript · ≈ +133 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/miuuyy/Astra-Ares.md 25. **mizorewww/laya-coreml** — 5.9 · Early signal · Language models · Python · ≈ +245 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 26. **zai-org/ZCode** — 5.9 · Cooling · AI agents · TypeScript · ≈ +301 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 27. **robbietilton/Compositor** — 5.8 · Cooling · Apps · Swift · ≈ +307 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 28. **typesafe-ai/skills** — 5.8 · Breakout · AI agents · ≈ +168 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 29. **maanHimself/OpenDLSS-NR** — 5.7 · Early signal · Generative media · JavaScript · ≈ +97 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 30. **trycua/cua** — 5.7 · Peaking · AI agents · HTML · ≈ +146 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 31. **yibie/awesome-jev** — 5.7 · Early signal · Learning & lists · Python · ≈ +196 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 32. **agent-substrate/substrate** — 5.6 · Breakout · AI agents · Go · ≈ +297 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 33. **BuilderIO/agent-native** — 5.6 · Breakout · AI agents · TypeScript · ≈ +167 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 34. **newliver666/apk-reverse** — 5.6 · Early signal · Security · Python · ≈ +202 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 35. **MelisaPeteRs2006/Silent-Crypto-Miner** — 5.4 · Early signal · Finance & crypto · Python · ≈ +117 stars by the end of the day A cryptocurrency mining builder and runtime with CPU/GPU support, multiple algorithms and pools, plus a stealth mode (process disguise, auto-start, pause on activity). Full card: https://gitnova.dev/en/r/MelisaPeteRs2006/Silent-Crypto-Miner.md 36. **Tencent/BrowserSkill** — 5.4 · Peaking · AI agents · TypeScript · ≈ +205 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 37. **bendlang/bend** — 5.3 · Peaking · Developer tools · TypeScript · ≈ +114 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 38. **dorkitude/webctl** — 5.3 · Early signal · AI agents · Go · ≈ +69 stars by the end of the day A web search CLI for AI agents that filters and deduplicates search results and page chunks via Jev, saving context tokens. Full card: https://gitnova.dev/en/r/dorkitude/webctl.md 39. **geastack/examples** — 5.3 · Early signal · Developer tools · TypeScript · ≈ +49 stars by the end of the day A collection of example applications and tools for GeaStack: small TSX apps with a gea manifest, used by the simulator, embedded boards, GeaOS and the IDE extension. Full card: https://gitnova.dev/en/r/geastack/examples.md 40. **kerpopule/hermes-jev-skills** — 5.3 · Early signal · AI agents · Python · ≈ +150 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 41. **latent-spaces/brag** — 5.3 · Cooling · AI agents · Python · ≈ +183 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 42. **anmolkapil/plexo** — 5.2 · Breakout · Developer tools · TypeScript · ≈ +304 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 43. **davila7/claude-code-templates** — 5.2 · Breakout · AI agents · Python · ≈ +208 stars by the end of the day CLI tool for installing and configuring ready-made Claude Code setups: agents, slash commands, MCP integrations, hooks and settings, plus session monitoring. Aimed at developers using Claude Code. Full card: https://gitnova.dev/en/r/davila7/claude-code-templates.md 44. **jarrodwatts/jev-trader** — 5.2 · Cooling · Finance & crypto · TypeScript · ≈ +145 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. **lhlGitHub/threejs-architecture-effects** — 5.2 · Early signal · Web & frontend · TypeScript · ≈ +71 stars by the end of the day An Agent Skill for Codex, Claude Code and Cursor that generates an interactive Vite + React + Three.js site with a procedural 3D building assembled along a 0–1 timeline. Full card: https://gitnova.dev/en/r/lhlGitHub/threejs-architecture-effects.md 46. **lordx64/phantom-kv** — 5.2 · Early signal · Language models · Python · ≈ +60 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/lordx64/phantom-kv.md 47. **Mak5er/AirCard-iOS** — 5.2 · Early signal · Apps · Swift · ≈ +115 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 48. **QwenLM/Qwen-Image-2.1** — 5.2 · Early signal · Generative media · Python · ≈ +140 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 49. **Rizzo-AI-Academy/rizzo-flow** — 5.2 · Early signal · Language models · Python · ≈ +85 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 50. **ruanyf/weekly** — 5.2 · Breakout · Learning & lists · ≈ +200 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 51. **hypit-ai/hypit** — 5.1 · Peaking · AI agents · TypeScript · ≈ +905 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 52. **strands-agents/harness-sdk** — 5.1 · Breakout · AI agents · Python · ≈ +82 stars by the end of the day Open-source Python and TypeScript SDK for building and running AI agents: agent loop, tools, MCP, memory, multi-agent patterns and tracing in one package. Runs in your process with no hosted control plane and supports multiple model… Full card: https://gitnova.dev/en/r/strands-agents/harness-sdk.md 53. **FluidInference/FluidUse** — 5.0 · Early signal · AI agents · Swift · ≈ +57 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/FluidInference/FluidUse.md 54. **Nasiko-Labs/nasiko** — 5.0 · Breakout · AI agents · Rust · ≈ +194 stars by the end of the day A single control-plane for AI agents: deploy, route, proxy A2A traffic, plus MCP gateway, LLM router and tracing in one Rust process. Full card: https://gitnova.dev/en/r/Nasiko-Labs/nasiko.md 55. **receptron/laya** — 5.0 · Early signal · Language models · TypeScript · ≈ +73 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 56. **tamaratran/fast-jev-compaction** — 5.0 · Cooling · AI agents · TypeScript · ≈ +205 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 57. **wfzyx/von** — 5.0 · Early signal · Language models · Python · ≈ +91 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 58. **cloudflare/security-audit-skill** — 4.9 · Peaking · Security · JavaScript · ≈ +781 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 59. **laoma2053/awesome-zhuiju-free** — 4.9 · Breakout · Productivity & self-hosted · JavaScript · ≈ +395 stars by the end of the day 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 availability via… Full card: https://gitnova.dev/en/r/laoma2053/awesome-zhuiju-free.md 60. **zhouxiaoka/autoclip** — 4.9 · Breakout · Generative media · Python · ≈ +209 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 61. **browser-use/video-use** — 4.8 · Breakout · AI agents · Python · ≈ +357 stars by the end of the day A skill that lets coding agents (Claude Code, Codex) edit raw video footage via chat: it transcribes takes with ElevenLabs, builds an edit decision list, and renders final.mp4 with cuts, color grades, subtitles and animations. Full card: https://gitnova.dev/en/r/browser-use/video-use.md 62. **hydra-db/hydradb** — 4.8 · Breakout · Backend & databases · Rust · ≈ +192 stars by the end of the day 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 Bolt 5.x drivers, and… Full card: https://gitnova.dev/en/r/hydra-db/hydradb.md 63. **Lumid-Off/AirCard-Windows** — 4.8 · Early signal · Apps · Rust · ≈ +110 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 64. **rgem227/knoweldge-base** — 4.8 · Early signal · Productivity & self-hosted · Python · ≈ +98 stars by the end of the day A self-hosted personal or team file knowledge base built with FastAPI and SQLite, with folders, tags, in-app previews, and a read-only MCP service for agents. Full card: https://gitnova.dev/en/r/rgem227/knoweldge-base.md 65. **superdesigndev/treg** — 4.8 · Breakout · AI agents · Python · ≈ +272 stars by the end of the day Treg is a proxy registry of tools for AI agents: one base URL and token give access to 3,000+ endpoints across 60+ providers (SEO, social, data enrichment, media generation) with per-call pricing and no provider signup. Full card: https://gitnova.dev/en/r/superdesigndev/treg.md 66. **deepseek-ai/deepseek-harness** — 4.7 · Steady · AI agents · TypeScript · ≈ +722 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 67. **ipenywis/laya-ultrafast** — 4.7 · Early signal · AI agents · Python · ≈ +50 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/ipenywis/laya-ultrafast.md 68. **kydlikebtc/awesome-jev** — 4.7 · Early signal · AI agents · Python · ≈ +94 stars by the end of the day A catalog of public examples of Jev, TypeSafe AI's typed decision model, indexed by the decision each example makes, with weekly CI link verification. Full card: https://gitnova.dev/en/r/kydlikebtc/awesome-jev.md 69. **stablyai/orca** — 4.7 · Steady · AI agents · TypeScript · ≈ +640 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 70. **Zefan-Cai/Open-Jev** — 4.7 · Early signal · Language models · Python · ≈ +71 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 71. **CTNicholas/jev-workflow-builder** — 4.6 · Early signal · AI agents · TypeScript · ≈ +44 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/CTNicholas/jev-workflow-builder.md 72. **Driftmireminisce/MarkText-Pro-Desktop** — 4.6 · Early signal · Apps · ≈ +82 stars by the end of the day A lightweight desktop companion for MarkText: a Markdown editor for notes and writing with dark and light modes and easy customization. Builds are available in the Releases tab. Full card: https://gitnova.dev/en/r/Driftmireminisce/MarkText-Pro-Desktop.md 73. **ethanplusai/astra-flash-orchestrator** — 4.6 · Early signal · AI agents · Python · ≈ +76 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 74. **haibarazz/awesome-codex-research** — 4.6 · Early signal · AI agents · Python · ≈ +75 stars by the end of the day A collection of reusable Skills and Codex Plugins for research workflows: literature review, paper polishing, review-comment decomposition, ML experiment planning, and remote GPU control via MCP. Aimed at researchers who use Codex to make… Full card: https://gitnova.dev/en/r/haibarazz/awesome-codex-research.md 75. **jerryjliu/docjev** — 4.6 · Early signal · Language models · Python · ≈ +64 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 76. **kryvora-network/kryvora-node** — 4.6 · Early signal · DevOps & infrastructure · Go · ≈ +88 stars by the end of the day Official client daemon for Kryvora Network nodes, a decentralized physical infrastructure network. Connects worker hardware to the coordination hub, runs telemetry probes, and reports proof of availability. Full card: https://gitnova.dev/en/r/kryvora-network/kryvora-node.md 77. **vercel-labs/json-render** — 4.6 · Peaking · AI agents · TypeScript · ≈ +94 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 78. **wdobry/laya-playground** — 4.6 · Early signal · Language models · JavaScript · ≈ +48 stars by the end of the day 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. Full card: https://gitnova.dev/en/r/wdobry/laya-playground.md 79. **yynxxxxx/Codex-X** — 4.6 · Breakout · AI agents · Rust · ≈ +74 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 80. **affaan-m/ECC** — 4.5 · Steady · AI agents · JavaScript · ≈ +524 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 81. **BansheeLight/MongoDB-Suite** — 4.5 · Early signal · Backend & databases · ≈ +81 stars by the end of the day A lightweight local-first companion tool for everyday MongoDB workflows, based on the repository topics (backend, database, nosql). The README gives few details beyond customization, small footprint, and local-first design. Full card: https://gitnova.dev/en/r/BansheeLight/MongoDB-Suite.md 82. **blixvip/NullMotion** — 4.5 · Early signal · Generative media · HTML · ≈ +82 stars by the end of the day A web tool that plays a finished motion-graphics ad over its black-and-white HyperFrames drafts, keeping them in sync with the film and letting you export everything to MP4 frame by frame. Full card: https://gitnova.dev/en/r/blixvip/NullMotion.md 83. **Michael-Jiahao-Zhang/game-the-llm-reviewer** — 4.5 · Early signal · AI agents · ≈ +68 stars by the end of the day An agent skill that performs a final editing pass on research papers, rewording passages to match documented LLM reviewer preferences while preserving scientific meaning. Full card: https://gitnova.dev/en/r/Michael-Jiahao-Zhang/game-the-llm-reviewer.md 84. **Re1nhard-1/deconv-preflight** — 4.5 · Early signal · Science & research · Python · ≈ +56 stars by the end of the day A Python CLI that validates bulk expression tables and single-cell reference metadata before deconvolution, catching missing or duplicate IDs, cell mismatches, and zero-only samples. Full card: https://gitnova.dev/en/r/Re1nhard-1/deconv-preflight.md 85. **TianyuCodings/NanoJev** — 4.5 · Cooling · Language models · Python · ≈ +106 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 86. **cloudflare/quiche** — 4.4 · Breakout · DevOps & infrastructure · Rust · ≈ +57 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 87. **eternity4719/HowToLiveBetter** — 4.4 · Peaking · Productivity & self-hosted · HTML · ≈ +535 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 88. **TencentARC/GameHorizon** — 4.4 · Early signal · Language models · ≈ +71 stars by the end of the day Official repo of GameHorizon, a data and evaluation suite for measuring model gameplay capabilities in AAA games across different temporal horizons, with 5,000 hours of gameplay and offline/online benchmarks. Full card: https://gitnova.dev/en/r/TencentARC/GameHorizon.md 89. **vinnylarouge/jevlike** — 4.4 · Cooling · Language models · Python · ≈ +49 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 90. **awlevin/typesafe-computer-use** — 4.3 · Cooling · AI agents · Python · ≈ +54 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 91. **bespokelabsai/nimble** — 4.3 · Cooling · Language models · Python · ≈ +87 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 92. **cdyforever/how-to-live-better** — 4.3 · 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 93. **deepopen-com/deepopen** — 4.3 · Early signal · Language models · Python · ≈ +56 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 94. **vinilana/jev-gateway** — 4.3 · Early signal · AI agents · TypeScript · ≈ +48 stars by the end of the day A local LLM gateway for coding agents: before choosing a tool, the agent asks the fast Jev model which tool to call instead of the expensive reasoning model. Works with Codex, Claude Code, OpenCode and Gemini CLI. Full card: https://gitnova.dev/en/r/vinilana/jev-gateway.md 95. **akitaonrails/ai-memory** — 4.2 · Breakout · AI agents · Rust · ≈ +218 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 96. **debpalash/VoiceStudio** — 4.2 · Cooling · Generative media · Python · ≈ +386 stars by the end of the day A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11 ASR engines, a… Full card: https://gitnova.dev/en/r/debpalash/VoiceStudio.md 97. **FareedKhan-dev/kimi-k3-in-c** — 4.2 · Breakout · Language models · C · ≈ +157 stars by the end of the day A portable C99 inference engine that runs the 2.78-trillion-parameter Kimi K3 model on a single CPU within 8.24 GB of RAM, with no BLAS, framework, or GPU. The model streams from disk, and memory only affects speed. Full card: https://gitnova.dev/en/r/FareedKhan-dev/kimi-k3-in-c.md 98. **General-Instinct/InstinctFlash** — 4.2 · Early signal · Hardware, IoT & robotics · C++ · ≈ +26 stars by the end of the day A high-performance serving runtime for robotics models (VLA, WAM, policies) with FP8 acceleration and optimized kernels on Jetson Thor and RTX 4090/5090. Full card: https://gitnova.dev/en/r/General-Instinct/InstinctFlash.md 99. **ryana/jevify** — 4.2 · Early signal · AI agents · ≈ +50 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 100. **HeyPuter/builder** — 4.1 · Early signal · AI agents · JavaScript · ≈ +29 stars by the end of the day Open-source AI builder for websites and apps: describe your idea in plain language and the model generates and publishes the project. An alternative to Lovable, Replit and v0 built on Puter.js. Full card: https://gitnova.dev/en/r/HeyPuter/builder.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