GitHub trends for September 23, 2026
What was taking off on GitHub on September 23, 2026: peak magnitude of the day, summary and where it was spotted.
-
9.0
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.
-
9.0
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.
-
8.9
google/ax
A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and…
-
8.8
unreallabsai/unreal-agent
Async-first agent harness in Go: sessions with persisted forkable history, input deduplication, an LLM-turn coordinator, and asynchronous operation execution via swappable components.
-
8.5
CopilotKit/openmuse
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.
-
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…
-
7.9
dream-num/univer
Open-source TypeScript SDK for embedding spreadsheet, document, and presentation editors into your own product, with a plugin architecture, Canvas rendering, a formula engine, and one Facade API for browser and…
-
7.7
LearnPrompt/awesome-seedance
Verified Seedance 2.5/2.0 prompt library: 463 cases, 25 category templates and 60 installable AI-video Skills, synced daily from goodcase.ai.
-
7.6
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.
-
7.6
riba2534/claude-opus-5-5-demo
A demonstration of Claude Opus 5.5 code generation: three playable 3D web games, each built from a single one-sentence prompt in one session with zero human edits and deployed online.
-
7.5
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.
-
7.4
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.
-
7.3
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…
-
7.3
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.
-
7.3
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.
-
7.2
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…
-
7.0
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…
-
6.9
driceroland/Search
A small, fast WebKit browser for macOS by design studio Office Commun: no toolbar, start page or accounts, with built-in ad blocking, reading mode and passwords kept in the keychain.
-
6.9
freestylefly/WeChatBridge
A native macOS tool that uses a Share Extension to take a WeChat chat export and forward it to AI agents (Codex, Claude, Doubao, etc.) or archive it into Obsidian. Runs fully locally without reading the WeChat database.
-
6.9
strands-agents/harness-sdk
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…
-
6.8
heyjunpenn/awesome-jev
A catalog of 530 open-source projects built with Jev, TypeSafe AI's System One model for typed decisions inside software. It serves as a curated list of implementations, SDKs, and tooling for evaluating the Jev…
-
6.8
nokia-applied-research/AnyJev
Turns any LLM into a decision model with typed questions (choice, yes/no, score) that return real probabilities read from the next-token distribution, without training. L0 removes position and label-prior bias; L1 adds…
-
6.6
jev-chat/jev-chat-windows
A reply helper for WeChat on Windows: it captures the window, reads incoming messages with offline OCR, infers the other person's intent, and offers 3 candidate replies to insert into the input box. Sending is always…
-
6.6
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.
-
6.5
anishfn/shapeshift
A web app with a single text box that morphs into the right UI as you type: event card, checklist, timer, color picker and more. Intent is classified by the Jev model, while dates and numbers are parsed…
-
6.5
jev-chat/jev-chat-jarvis-mac
A macOS app that OCR-reads WeChat messages on screen and uses a local model to classify intent and risk, suggesting reply candidates. Read-only, with no injection into WeChat.
-
6.4
Amal-David/awesome-jev
A curated catalog of projects, demos and SDKs for TypeSafe Jev, a model that answers typed questions about text or JSON. It helps move from a demo clip to understandable code and separates reviewed sources from the…
-
6.2
hydra-db/hydradb
HydraDB is a distributed graph database written in Rust that stores the graph durably on S3-compatible object storage, with separate data nodes and indexers. It supports OpenCypher queries, GraphBLAS traversal, Neo4j…
-
6.2
Nasiko-Labs/nasiko
A single control-plane for AI agents: deploy, route, proxy A2A traffic, plus MCP gateway, LLM router and tracing in one Rust process.
-
6.2
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.
-
6.2
Shelpid/SETS
A browser sandbox where a genetic algorithm evolves grid-DCA trading strategies on real BTCUSDT candles, gating survivors through out-of-sample validation and paper trading.
-
6.2
taeold/djev-run
Deploys the DiffusionGemma-Jev (djev) model on Google Cloud Run with an NVIDIA RTX PRO 6000 GPU and a TypeSafe AI compatible API. Includes Snake, Dino, and Tetris demos running directly in the browser.
-
6.1
852wa/JIZURA
A browser app that automatically assembles lyric videos (文字PV) from song lyrics using 707 built-in parts and 24 styles, exporting to MP4. An After Effects panel is also included.
-
6.1
davila7/claude-code-templates
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.
-
6.1
malevrigns/agent-jev
AgentJev-0.6B is a specialist decision model for AI agent loops: it takes unstructured state (diffs, traces, logs) plus typed questions and returns a probability distribution over options in a single forward pass with…
-
6.1
zai-org/ZCode
Z.ai's coding agent workbench: an Electron desktop app, browser UI and terminal Agent CLI. The repo contains the client, backend, shared UI and the agent CLI/runtime sources.
-
6.0
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…
-
6.0
miuuyy/Astra-Ares
Experimental reference tool that dynamically selects reasoning effort for GPT-6 Astra via Jev during Codex tasks to reduce token usage. Requires building a patched Codex CLI from source.
-
5.9
JohnHeibel/PDoomVideo
Source code for a music video generated entirely by Claude Opus, with scenes, lyrics and transitions built in p5.js and rendered to MP4 via headless Chrome and ffmpeg.
-
5.9
maanHimself/OpenDLSS-NR
A Vulkan reimplementation of NVIDIA's DLSS 5 Neural Rendering network, bit-exact against the original. Requires your own weights and an NVIDIA Ada or newer GPU.
-
5.9
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.
-
5.9
robbietilton/Compositor
A free, open-source raster image editor for macOS written in Swift — a Photoshop alternative focused on compositing and post-processing.
-
5.9
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.
-
5.8
flexprice/flexprice
Open-source usage-based pricing and billing platform: meters usage in real time, handles credits and feature limits, and generates invoices. Available as cloud or self-hosted.
-
5.8
juspay/hyperswitch
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…
-
5.7
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…
-
5.7
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.
-
5.7
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).
-
5.6
Asymptote-Labs/agent-beacon
Open-source local-first memory layer for AI agents: captures session history from Claude Code, Cursor, Codex, OpenCode and 20+ other harnesses, extracts useful workflows and corrections, and makes them reusable by…
-
5.5
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.
-
5.5
mater1996/travel-planning
A Codex plugin that plans trips: compares routes, queries maps, transport, lodging, weather and community reviews, then produces itinerary.json and a standalone itinerary.html. It does not book or pay — research and…
-
5.5
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.
-
5.5
xCuri0/ReBarUEFI
UEFI DXE driver that enables Resizable BAR on systems without official support. Provides GPU performance gains and is required for Intel Arc GPUs to work optimally.
-
5.4
0xkuch/Fibo
A Python CLI that matches task estimates from your tracker (Jira, Linear, GitHub, GitLab) against actual time from first commit to merge and computes your personal underestimation multiplier. Runs locally, no database…
-
5.4
blixvip/NullMotion
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.
-
5.4
geastack/examples
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.
-
5.4
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.
-
5.4
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.
-
5.4
rgem227/knoweldge-base
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.
-
5.3
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.
-
5.3
dorkitude/webctl
A web search CLI for AI agents that filters and deduplicates search results and page chunks via Jev, saving context tokens.
-
5.3
edison-land/paragravity
CLI manager for running multiple isolated Google Antigravity (Gemini Pro) profiles in parallel on macOS and Windows via Chromium's official --user-data-dir, without patching or proxies.
-
5.3
Miaotofu01/Study-Mate
StudyMate is a "learning mode" preset for DSH (DeepSeek Harness) plus a set of SKILLs: it builds a study roadmap for math and CS subjects and generates HTML lessons with explanations, exercises and hands-on projects.
-
5.2
anmolkapil/plexo
Download manager for Windows and macOS that speeds up downloads by splitting files into 8 MB chunks fetched in parallel across multiple network interfaces (Wi-Fi, Ethernet, USB tethering).
-
5.2
browser-use/video-use
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…
-
5.2
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…
-
5.2
jasonwong1991/WonderBox
A native macOS system toolkit: memory optimization that also handles compressed memory, deep cleanup of developer caches, disk analysis, fan control, and keep-awake. Everything runs on-device; UI is in Simplified…
-
5.2
lhlGitHub/threejs-architecture-effects
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.
-
5.2
lordx64/phantom-kv
Removes refusal behavior from language models by grafting a small trained KV-cache bank into the context, without editing weights or projecting activations, and is fully reversible.
-
5.2
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.
-
5.2
Mak5er/AirCard-iOS
iOS app that writes custom artwork into iOS 27 system caches over a local loopback tunnel, letting you restyle Apple Wallet cards and the lock screen passcode keypad directly on the iPhone.
-
5.2
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,…
-
5.2
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…
-
5.2
ruanyf/weekly
A weekly tech digest by Ruan Yifeng: articles, tools and resources, published every Friday. Also includes a section with programmer job postings.
-
5.2
superdesigndev/treg
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.
-
5.2
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…
-
5.2
tjsky/pinyin-annotator
A web tool that adds pinyin annotations to Chinese texts, producing reading materials for children from kindergarten to early primary school. Runs entirely in the browser without uploading text to any server.
-
5.1
can1357/oh-my-pi
Terminal coding agent with LSP and debugger wired in: 60+ model providers, 31 built-in tools, subagents and collaborative sessions. A fork of Mario Zechner's Pi.
-
5.1
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.
-
5.1
FluidInference/FluidUse
Local computer use on Apple silicon: reads forms in macOS apps via the Accessibility API, asks a small on-device model what belongs in each field, and types the answer into the real app.
-
5.1
kydlikebtc/awesome-jev
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.
-
5.1
poloclub/transformer-explainer
Interactive visualization of how Transformer models work: runs a live GPT-2 in the browser and shows how internal components predict the next tokens.
-
5.0
Alex314618-create/JevRev
A decision layer beside your LLM: JevSift filters weak proposals, JevLoop audits evidence after each agent round, JevLong watches long-running sessions. It keeps workflows from paying for bad directions.
-
5.0
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.
-
5.0
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.
-
5.0
laoma528/awesome-zhuiju-free
A curated list of free movie and TV streaming resources: online sites, apps, cloud and torrent search, subtitles, TVBox configs, IPTV and related open-source projects. Resources are hand-picked and checked daily for…
-
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
sevenevesai/riso-windowseat
Procedural risograph-style animated films, each a single self-contained HTML file using Canvas 2D and Web Audio, plus Claude Code skills, docs and tools for making your own.
-
5.0
stablyai/orca
Orca is an ADE for running a fleet of parallel coding agents (Claude Code, Codex, OpenCode, etc.) in isolated git worktrees with a unified interface, mobile companion, and remote runtime.
-
5.0
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.
-
4.9
deepopen-com/deepopen
Open-source non-autoregressive System 1 decision engine for typed decisions: returns typed answers (choice, score, noul) in a single forward pass across 100+ languages without generating text. Suited for…
-
4.9
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.
-
4.8
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.
-
4.8
Liyucheng1997/332_lab-jev-chat
A non-invasive chat assistant: it reads on-screen conversations (Android via Accessibility, Windows via UI Automation or OCR), the Jev model judges intent and risk, a generative model drafts 3 replies shown in an…
-
4.8
Re1nhard-1/deconv-preflight
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.
-
4.8
surya-koritala/Glyd
Glyd is a fast lossless compression algorithm written in Rust with a C ABI and CLI, aimed at object storage, logs, telemetry and backups where storage size and read speed matter. It is positioned as a drop-in…
-
4.8
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).
-
4.8
Zefan-Cai/Open-Jev
Open-Jev serves a context, questions and candidate answers to Qwen-based models and returns typed probabilities directly, without autoregressive generation or JSON parsing. It provides LoRA adapters, a scalar decision…
-
4.7
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.
-
4.7
cdyforever/how-to-live-better
A single-file HTML reading page for the open book "High Cost-Performance Life Guide" — 528 tips across 32 sections, searchable, offline-capable, zero dependencies.