GitHub trends for September 21, 2026
What was taking off on GitHub on September 21, 2026: peak magnitude of the day, summary and where it was spotted.
-
9.9
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.
-
9.9
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.
-
9.1
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.
-
9.0
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.
-
9.0
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.
-
8.7
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.
-
8.4
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…
-
7.8
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.
-
7.6
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,…
-
7.6
robbietilton/Compositor
A free, open-source raster image editor for macOS written in Swift — a Photoshop alternative focused on compositing and post-processing.
-
7.5
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.
-
7.4
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.
-
7.3
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.
-
7.3
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.
-
7.3
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.
-
7.2
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…
-
7.2
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…
-
7.2
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.
-
7.2
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,…
-
7.1
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.
-
6.9
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.
-
6.9
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.
-
6.9
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…
-
6.9
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.
-
6.9
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…
-
6.9
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…
-
6.8
Haleclipse/CometixCode
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…
-
6.7
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,…
-
6.6
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…
-
6.5
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.
-
6.5
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…
-
6.4
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.
-
6.4
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).
-
6.3
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.
-
6.3
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.
-
6.3
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).
-
6.2
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…
-
6.2
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…
-
6.2
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…
-
6.1
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.
-
6.1
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…
-
6.1
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.
-
6.1
mihail911/modern-software-dev-assignments
Assignments for Stanford's CS146S course "The Modern Software Developer", covering modern software development practices with Python 3.12, Conda and Poetry.
-
6.1
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.
-
6.1
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.
-
6.0
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.
-
6.0
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…
-
5.9
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.
-
5.9
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…
-
5.9
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.
-
5.9
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.
-
5.8
docling-project/docling
Docling is a document parsing library for many formats (PDF, DOCX, PPTX, XLSX, HTML, EPUB, audio, video) with advanced PDF understanding: page layout, tables, formulas, OCR. It prepares structured data for generative…
-
5.8
githubnext/localjev
A local TypeScript/Bun HTTP service implementing a Jev-compatible POST /v1/systemone API on top of an OpenAI-compatible Chat Completions endpoint (DiffusionGemma via oMLX). It acts as a bridge for typed decisions…
-
5.7
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…
-
5.7
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…
-
5.6
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.
-
5.6
ghuntley/underclass
An OpenAI-compatible local proxy that pools multiple ChatGPT/Codex and GitHub Copilot subscriptions behind one endpoint, with sticky sessions, quota cooldowns and fail-fast behavior.
-
5.6
Heman10x-NGU/openJev-verdict-2.0
An open non-autoregressive decision model built on ModernBERT (149.6M) that emits typed decisions (Choice, Score) with calibrated probabilities in ~20-25 ms. On the typed-decisions benchmark it reaches 77.10% accuracy…
-
5.5
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.
-
5.5
ruanyf/weekly
A weekly tech digest by Ruan Yifeng: articles, tools and resources, published every Friday. Also includes a section with programmer job postings.
-
5.5
shhivv/third-hand
A small macOS menu bar assistant: focus an app, press Control–Space, and tell it what to do. It reads accessible controls, types, clicks, and checks the result using Accessibility, Apple Vision, and the Jev model.
-
5.5
yi1108/printfilm
Open-source AI studio for short videos and episodic comics: from theme and script through storyboard, image, video and voice generation to the final cut. Includes a user frontend, admin panel, billing and an open API.
-
5.4
anthropics/claude-code
An agentic coding tool that lives in the terminal: it understands your codebase, executes routine tasks, explains complex code, and handles git workflows via natural language commands.
-
5.4
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…
-
5.4
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.
-
5.4
shilapi/xcertplay
An Android head-unit app that receives CarPlay via an MFI chip (directly over I2C or through a CH341 bridge). Supports wired and wireless iPhone connections.
-
5.4
SunnyMaria/csapp-zh-markdown
A Chinese Markdown edition of the CSAPP third-edition textbook: all chapters, 238 exercise answers, and translations of eight labs, for online or offline study.
-
5.4
v-modal/awesome-jev-tools
A curated list of public projects and practices built on Jev, TypeSafe AI's System One model for typed decisions that takes unstructured state and returns a typed answer with a confidence rating. It gathers production…
-
5.3
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.
-
5.3
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.
-
5.3
valentynkit/awesome-jev-typesafe
A curated list of projects and resources around TypeSafe's Jev, a model that takes state and returns typed answers (probabilities, choices, scale positions) instead of text.
-
5.3
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.
-
5.2
brainstormity/Jev-X-Sentiment-Analysis
A crypto market intelligence terminal that combines live price data, funding rates, and Twitter sentiment to produce a Buy/Sell/Hold decision card with entry, stop-loss, and target levels. It does not execute trades…
-
5.2
LSPosed/ZygiskNext
Standalone implementation of Zygisk that provides Zygisk API support for KernelSU and replaces Magisk's built-in Zygisk. Aimed at rooted Android users on KernelSU or Magisk who need Zygisk module support.
-
5.1
amitshekhariitbhu/ai-engineer-roadmap
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.
-
5.1
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.
-
5.1
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.
-
5.1
huangbai-AI/post-production-skill
A Codex skill that rewrites ideas or reference material into cinematic video prompts for Seedance 2.5, covering VFX, 3D UI, transitions and camera movement.
-
5.1
kyle-pena-nlp/jevchat
An experimental chatbot that generates replies by asking the Jev model which symbol, word or hypothesis comes next; built for fun, not practical use.
-
5.1
unicodef1wn/grokbot-field-notes
Rules, playbooks, bot roles and a failure log from the xAI Grok Bot team's 72-hour live build: drop AGENTS.md into your repo root and your agent reads it.
-
5.0
joeseesun/qiaomu-download
Agent skill that downloads videos and extracts audio/subtitles from YouTube, Bilibili, X, TikTok, Vimeo, Instagram, WeChat Channels and other yt-dlp-supported links via a single phrase 'download this: URL'.
-
5.0
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.
-
5.0
Sac-Y/Jev-cu
Jev-cu connects Computer Use with the Jev model (TypeSafe System One): Jev picks the element, action, completion level and risk from textual UI candidates, while Codex Computer Use reads the interface and executes…
-
4.9
addyosmani/agent-skills
A collection of 25 engineering skills and 9 slash commands for AI coding agents, covering the development lifecycle from spec to ship. Helps agents follow proven practices: TDD, code review, task planning.
-
4.9
ahmedkhaleel2004/gitdiagram
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.
-
4.9
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.
-
4.9
bilawalsidhu/gods-eye-view
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.
-
4.9
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.
-
4.9
dofastted/vm2api
A proxy service that turns a Setup Token into a Console-compatible Anthropic API: requests run through VMs with a native Claude Code subagent, without prompt injection. For those wanting to use Claude via the standard…
-
4.9
krillinai/OpenCreator
Open-source AI workspace for creators powered by Codex CLI: visual tools and agents for video, images, voice, avatars, translation, and editing in one place.
-
4.9
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…
-
4.9
nimaone/persian_tts
Offline Persian text-to-speech with voice cloning that runs on CPU without GPU or internet. Two paths: a lightweight ONNX engine (~200 MB of dependencies) and a reference PyTorch one.
-
4.9
shhivv/arc-cua
Superfast action layer for computer-use agents: takes a bounded subtask from a planner and runs the UI loop itself on macOS via Accessibility and OCR, without calling a frontier model on every click.
-
4.9
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.
-
4.9
sutro-sh/jev-align
An experimental CLI from Sutro for building AI Functions with TypeSafe's Jev: it finds ambiguous examples in your dataset, asks you to label them, and uses GEPA to improve the function.
-
4.9
vinnylarouge/jevlike
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…
-
4.9
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.
-
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.
-
4.8
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.
-
4.8
featherless-ai/simple-jev
A Python server that turns open Hugging Face LLMs into a classifier: it reads next-token logits and returns JSON with choices, rubric scores, or truth judgments without training a separate classifier head.