GitHub trends for September 20, 2026
What was taking off on GitHub on September 20, 2026: peak magnitude of the day, summary and where it was spotted.
-
8.7
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.
-
8.6
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.
-
8.5
robbietilton/Compositor
A free, open-source raster image editor for macOS written in Swift — a Photoshop alternative focused on compositing and post-processing.
-
8.1
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.
-
8.0
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.
-
7.2
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.
-
7.1
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…
-
7.0
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…
-
7.0
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.
-
7.0
jackwener/wx-cli-again
A Rust CLI for querying local WeChat data: sessions, chat history, search, contacts, group members, favorites, stats and export. It decrypts local SQLCipher databases and returns JSON output designed for AI agents.
-
7.0
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.
-
6.9
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).
-
6.7
newliver666/apk-reverse
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.
-
6.6
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…
-
6.6
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…
-
6.5
arvindear/wp2shell-PoC
Proof-of-concept for the wp2shell vulnerability chain in WordPress Core (CVE-2026-63030 and CVE-2026-60137) that gives an unauthenticated attacker RCE. A tool for testing and exploitation in controlled environments and…
-
6.5
mcncarl/jianying-headless
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…
-
6.4
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.
-
6.4
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…
-
6.4
TheoLeeCJ/SemIf
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.
-
6.3
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.
-
6.3
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.
-
6.3
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.
-
6.2
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…
-
6.2
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,…
-
6.1
gylive/ccodex-sleep-state
A local Go tool that tries to improve Codex behavior: it collects and injects X-Codex-Turn-State and manages proxies, subscriptions and Astra/Sol/Terra models via a web panel. It does not guarantee better model quality…
-
6.1
incoai/splash
A local LLM inference engine for Apple silicon, specialized per model: serves OpenAI- and Anthropic-compatible APIs to coding agents on a single Mac.
-
6.0
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.
-
5.9
HyNetworks/OpenGFW
An open-source DIY Great Firewall for Linux: it reassembles IP/TCP flows, analyzes protocols (HTTP, TLS, QUIC, DNS, SSH, VPNs) and filters connections via an expr-based rule engine. Aimed at home routers and servers…
-
5.9
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'.
-
5.8
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.
-
5.7
anthropics/knowledge-work-plugins
A collection of open-source plugins for Claude Cowork and Claude Code that turn the assistant into a specialist for a specific role: sales, support, finance, legal, marketing, data and more. Each plugin bundles skills,…
-
5.7
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…
-
5.7
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…
-
5.7
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.
-
5.6
ejfkdev/ddc
A Rust DEX-to-Java decompiler for Android with progressive analysis: query metadata first and decompile classes on demand instead of a full run. Its output is javac-verified across seven real-world APKs.
-
5.5
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).
-
5.4
ERRRC/kaogongzhentizhengliu
An Obsidian vault of 22,375 notes reorganizing 2016–2026 Chinese civil service exam questions by topic, with deep annotations, links and local images.
-
5.4
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.
-
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
mindbox77/zxdesk
A graphical windowed OS for the 48K ZX Spectrum written in Z80 assembly: overlapping windows, menus, a heap, an event queue, a file manager and settings — all fitting in 48K and running on real hardware.
-
5.3
cobanov/awesome-jev
A curated list of projects built with Jev, TypeSafe AI's System One model for fast typed probabilistic decisions (classification, routing, scoring, guardrails).
-
5.3
kyotofin/tax-doc-classifier
A TypeScript tax document page classifier that identifies one of 261 IRS forms and the page kind from page text using the Jev decision model instead of an LLM. No training or hosting required — just a JSON file of form…
-
5.3
lakeday-org/perch
CLI linter that finds semantic defects in code (wrong call order, inverted conditions, off-by-one) and ranks them by probability. Supports custom rules in perch.yaml and integration with agents (Claude Code, Codex,…
-
5.3
razorback16/openjev
An open-source "System One" decision server on DiffusionGemma: send a state and typed questions (yes/no, choice, score) and get probabilities plus confidence in tens of milliseconds, with no text generated.…
-
5.2
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.
-
5.2
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.
-
5.2
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.
-
5.2
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…
-
5.1
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.
-
5.1
liushunqi8-hash/editaplot2026
EditaPlot is a Codex skill for Windows that turns experimental data tables into editable Origin (OPJU) figures with PNG, PDF, and TIF exports, confirming each column's role with the user.
-
5.1
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.
-
5.1
op7418/guizang-product-video-skill
A skill for AI coding agents (Claude Code, Codex) that turns a product's codebase into a release promo video: reuses real components, writes the script, generates music and SFX, and renders an MP4.
-
5.0
asciimoo/hister
A private Go search engine that indexes the full contents of visited pages and local files. Search is available via web UI, terminal, or an AI assistant through MCP.
-
5.0
cactus-compute/needle
A 2-bit, 8-29 MB foundation model for phones, wearables, robots and microcontrollers that handles tool calls, structured extraction and text embeddings on-device.
-
5.0
logan-markewich/jeff
A self-hosted drop-in replacement for TypeSafe's jev System One API, powered by the GLiFormer model (400M) and compatible with the official typesafe-sdk. It classifies text locally into choices, ordered scores, and…
-
5.0
Oldcircle/geo-sleuth
An agent skill that geolocates photos using OpenStreetMap geometry, elevation data, satellite imagery and street view, and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.
-
5.0
superagents-lab/jev-search
A web search app where TypeSafe's Jev interprets plain-language questions to pick sources, time ranges and queries, then ranks results from Search1API with visible relevance scores. Returns links and snippets instead…
-
5.0
tamaratran/jev-pruner
A Claude Code plugin that uses TypeSafe's Jev to trim noisy Bash output after the command runs but before the result reaches the main LLM. It reduces data carried into later turns without generating a summary.
-
5.0
unclebob/uml-viewer
Live Quil UML class-diagram viewer that lays out topology from an EDN IR and overlays metrics (CC, coverage, CRAP) from .metrics/ snapshots.
-
4.9
rustfs/rustfs
RustFS is a distributed object storage system written in Rust with an S3-compatible API, positioned as a faster Apache 2.0 alternative to MinIO. It is optimized for data lake, AI, and big data workloads.
-
4.8
AbdelStark/awesome-typesafe
A curated list of official resources and community projects around TypeSafe, System One models, and Jev — an API that returns typed probabilistic decisions instead of generated text.
-
4.8
coldteadotai/abide
A tool that checks every edit made by coding agents (Claude Code, Codex, OpenCode) against rules in AGENTS.md and CLAUDE.md that no linter can catch, and makes the agent fix violations in the same turn.
-
4.8
Continuum-AI-Corp/OrcaBonsai-27B-Uncensored
A tool for runtime refusal ablation in the compressed Ternary Bonsai 2 27B LLM: it projects the residual stream to remove the refusal direction without modifying or re-quantizing weights. Runs on Apple Silicon via MLX.
-
4.8
sabbircode-dev/learning-python
A personal repository of learning programs and exercises covering Python basics: variables, conditions, loops, functions and simple projects.
-
4.8
supabase/supabase
Postgres development platform: hosted database with auth, auto-generated REST/GraphQL APIs, realtime subscriptions, file storage and edge functions. An open-source Firebase alternative.
-
4.8
VDERR/echocat-skill-panel-3.0
A cordis plugin for DSH Desktop Beta that reports which skills were invoked in each conversation turn and lets you install or remove skills directly inside the app.
-
4.7
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.
-
4.7
fastino-ai/GLiNER2
A family of schema-conditioned encoder models for information extraction: NER, text classification, structured record extraction, relations, and span attributes. Runs locally on CPU without a GPU.
-
4.7
logicrw/awesome-jev-projects
A directory of open-source projects built around TypeSafe Jev, a fast typed-decision (System 1) architecture for autonomous agents. It catalogs 260+ projects across 17 categories with commit-pinned source evidence.
-
4.6
kvmem/kvmem-llama.cpp
A llama.cpp port with tiered KV memory: a bounded GPU KV working set, host-RAM storage and query-based retrieval of relevant blocks. Runs Qwen3.8-27B with a 256K logical workspace on 16 GiB VRAM for long-running agent…
-
4.6
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…
-
4.6
wangyunjeff/sub2api-state-kit
An experimental Sub2API extension adding account-level STATE management: Pro/Team selection, fixed-proxy verification, and dynamic guards against anomalies (312 signal). Aims to mitigate OpenAI-side model rerouting and…
-
4.6
webprodigies-org/flute
Flute turns real React components into cinematic 3D scenes: your coding agent composes camera, depth and motion, while Flute renders, plays back and exports MP4.
-
4.5
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.
-
4.5
alibaba/open-code-review
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…
-
4.5
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.
-
4.5
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.
-
4.5
leoliu0/ratex
A self-contained pure-Rust TeX engine and typesetting toolchain: compiles LaTeX documents without a TeX Live install, with millisecond incremental builds and embedded BibTeX.
-
4.5
mmastrac/djev-spark
Container recipe for running DiffusionGemma 26B-A4B (NVFP4) on a DGX Spark with vLLM and a structured-decision server exposing Jev's /v1/systemone API.
-
4.5
uehaj/jev-semgrep
A grep CLI that finds lines by meaning rather than regular expressions: each line is scored by the Jev model for how likely it matches a given meaning, and meanings combine with AND/OR/NOT. It is language-agnostic — a…
-
4.4
BillionsBobby/JevRouter
A lightweight Jev-powered router that decides which model, subagent, Skill, MCP tool or CLI should handle the next step of an agent task. It keeps reasoning tokens free from tool selection and makes every decision…
-
4.4
danfromtico/autorun
Homebrew app for Nintendo Switch that runs 32-bit Windows games via Wine and translates x86 code to ARM with Box64. Games are copied to the SD card and launched from a built-in library.
-
4.4
droidrun/mobile-jev
A standalone mobile agent for Android: given a text goal, it drives a real phone via the Mobilerun API and the Jev model, with a React studio, CLI, and action traces. No ADB required.
-
4.4
kunchenguid/compact-adviser
A plugin for agent CLIs (Pi, Claude Code, Codex CLI, Grok Build) that advises when to run /compact by using the Jev model to judge whether the current work unit is finished.
-
4.4
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.
-
4.4
moritzkremb/jev-voice-browser
A Node app that controls a real Chromium window via Playwright by voice: speech is streamed word by word and the Jev model decides intent and target element in ~300 ms. It enables hands-free browser control.
-
4.4
niedachu/MateriaSim
MateriaSim is a Python framework for reproducible molecular simulation of multi-component materials: it organizes configurations, studies and runs on top of GROMACS with input validation and result traceability.
-
4.4
TencentCloud/Octop
Self-hosted AI assistant in Python with multi-user and multi-agent support: a single process serves a web dashboard, CLI, IM integrations and cron, with all data kept locally.
-
4.3
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…
-
4.3
Vodiwalker/vodiwalker_panel
A Python panel for managing VPN services and configurations with support for TCP and WS protocols. It is free to use, with setup and usage covered in a video tutorial.
-
4.3
wy-coliney/jev-browser-use
A browser Skill for Codex: Jev handles routine actions (navigation, clicks, toggles, scrolling) while Codex handles text input, visual judgment, and final verification.
-
4.3
zhengkid/Dream-RSI
Research project on recursive self-improvement: past discovery histories become a replay simulator used to evaluate and refine exploration policies. Code is still being prepared; paper and demo are available.
-
4.2
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…
-
4.2
coolbbcamp/OfficialSite
CoolBB agency's official site — an interactive Three.js 3D scene with an igloo HQ, a six-cube services portfolio, and entry holograms. A static site with patch scripts for content and asset builds.
-
4.2
eliasstravik/herdr-projects
A Herdr plugin that runs multiple coding agents in parallel: one coordinator splits tasks into separate git worktrees and branches, shares memory and instructions, and shows which threads need you.
-
4.2
guohuiyuan/go-music-dl
A Go-based music search and download tool for 10+ platforms (NetEase, QQ, Kugou, Bilibili, etc.) with Web, TUI and desktop modes, supporting playlists, albums and lossless FLAC.
-
4.2
hexiaofeier/hehe-industry-research-skill-pack
A pack of 14 agent Skills for Chinese-language industry and company research: a lead skill orchestrates 13 specialized modules covering market sizing, industry chain, financials, valuation and investment logic.
-
4.2
ruanyf/weekly
A weekly tech digest by Ruan Yifeng: articles, tools and resources, published every Friday. Also includes a section with programmer job postings.
-
4.2
supermemoryai/supermemory
Memory and context engine for AI: extracts facts from conversations, builds user profiles, combines RAG and memory in one API, runs locally or in the cloud.