GitHub trends for September 19, 2026
What was taking off on GitHub on September 19, 2026: peak magnitude of the day, summary and where it was spotted.
-
9.6
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.
-
9.5
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.
-
8.5
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…
-
8.4
robbietilton/Compositor
A free, open-source raster image editor for macOS written in Swift — a Photoshop alternative focused on compositing and post-processing.
-
8.3
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.
-
8.1
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.
-
8.1
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.
-
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.
-
7.6
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.
-
7.4
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).
-
7.3
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.
-
7.2
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…
-
7.2
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…
-
7.2
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.
-
7.1
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…
-
7.0
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.
-
6.8
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.
-
6.7
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…
-
6.7
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.
-
6.6
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.
-
6.6
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,…
-
6.5
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…
-
6.5
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…
-
6.4
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.
-
6.4
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.
-
6.3
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.
-
6.3
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.
-
6.3
wide-trace/open-higgsfield
Open-source self-hosted studio for image and video generation across 32 models (8 image, 24 video) in one interface with a single prompt bar, gallery and per-model settings.
-
6.3
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).
-
6.2
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.
-
6.2
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,…
-
6.2
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…
-
6.2
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.
-
6.1
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.
-
6.1
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…
-
6.0
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).
-
6.0
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.
-
5.9
AbdelStark/awesome-typesafe-jev
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.
-
5.9
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.
-
5.9
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
dabit3/jev-experiments
A collection of TypeScript demo apps focused on low latency and type safety; each app lives in its own top-level directory with its own README and tests.
-
5.8
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.
-
5.7
ankitects/anki
Anki is a spaced repetition flashcard program for memorizing information. This repo holds the source code of the desktop version, written in Rust.
-
5.7
Fission-AI/OpenSpec
OpenSpec is a spec-driven development framework for AI coding assistants: it turns ideas into Markdown specs with requirements and scenarios before any code is written. It supports 30+ tools (Cursor, Copilot, Codex,…
-
5.7
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…
-
5.6
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.
-
5.6
chaseleantj/deskworlds
A living aquarium on your macOS desktop: fish react to your cursor and compete for food while plants sway in a slow current. The scene renders locally with Three.js and WebGL2, fully offline.
-
5.6
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.
-
5.6
jemalloc/jemalloc
A general purpose malloc(3) implementation focused on avoiding fragmentation and supporting scalable concurrency. Used as the FreeBSD libc allocator and in many applications, it includes heap profiling and…
-
5.6
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.
-
5.6
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…
-
5.6
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.
-
5.6
yynxxxxx/gpt_sub_analysis
A guide to analyzing the ChatGPT iOS subscription flow: it describes intercepting the buyProduct request via Reqable and SSL Kill Switch 3 and rewriting the offerName and salableAdamId fields to obtain the Pro 20x…
-
5.5
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.
-
5.5
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,…
-
5.5
sabbircode-dev/learning-python
A personal repository of learning programs and exercises covering Python basics: variables, conditions, loops, functions and simple projects.
-
5.5
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.
-
5.5
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…
-
5.4
fatwang2/awesome-jev
A directory of open-source projects built on TypeSafe Jev: SDKs, integrations and developer tools, plus a reusable GitHub Action for reviewing submissions to the list.
-
5.4
rit3zh/expo-dynamic-notifications
A React Native library that shows in-app notifications in a Dynamic Island style with goo morph animation, gestures and Skia rendering.
-
5.4
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.
-
5.3
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.
-
5.3
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.
-
5.3
indada/repopilot
Self-hosted agent built on the OpenAI Codex SDK that turns GitHub Issues and PRs into a bounded cycle of test generation, failure reproduction, code repair and independent Docker verification. The merge decision stays…
-
5.3
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…
-
5.3
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.
-
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.…
-
5.3
realZachi/pg-jev
A PostgreSQL extension that lets you filter, rank and classify table rows using plain-language conditions via TypeSafe's Jev model.
-
5.3
Tencent/WeKnora
Open-source LLM knowledge platform: turns raw documents into queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
-
5.3
XGEN-Labs/XGEN-JING
XGEN-JING is an egocentric interactive experience model built on MiniMax-H3 that generates first-person video and audio for navigation, object interaction, and dialogue from actions, reference images, and observation…
-
5.2
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.
-
5.2
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…
-
5.2
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.
-
5.1
anthropics/uplifting-biomolecular-modeling
A reference collection of 36 drop-in optimization kits for the inference paths of open protein- and genomics-ML tools, from structure prediction to protein language models. Each kit speeds up a pinned upstream release…
-
5.1
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…
-
5.1
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…
-
5.1
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…
-
5.1
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.
-
5.1
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.
-
5.0
jkudish/jev-browser
Browser automation tool: given a task and URL, it drives a headless browser via MCP, CLI, or library, picking one action per step using TypeSafe's Jev model.
-
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
repoboost-hq/github-launch-checklist
A Python CLI that audits a GitHub repository before launch, scoring ten readiness signals 0-10: name, description, topics, README, license, demo, installation, contributing guide and issue templates.
-
5.0
thruwire/foreman
Foreman is an experimental Python runtime that runs Codex workers on software tasks while independently assessing their progress via the Jev model to decide whether to continue, stop, or finish the work.
-
5.0
VDERR/dsh-echocat-skill-panel
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.
-
4.9
aardappel/goose
Goose is a systems programming language with memory managed via data stacks: no heap, no GC, no lifetime annotations, and it compiles to C. It claims to be faster and more memory-efficient than C++ and Rust while…
-
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
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.
-
4.9
ekzhang/openjev-sglang
HTTP server implementing the TypeSafe/Jev API for structured text classification on Qwen3.6-35B-A3B via SGLang; returns answer probabilities without generating a chain of thought.
-
4.9
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.
-
4.9
tradesdontlie/tradingview-mcp
Bridges Claude Code with your local TradingView Desktop via Chrome DevTools Protocol: the AI assistant reads and controls charts and develops Pine Script. Runs fully locally and requires a TradingView subscription.
-
4.9
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…
-
4.8
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
bojieli/ai-infra-book
Open book "Understanding AI Infra" by Bojie Li: quantitative derivation of LLM inference and training system design from hardware constraints and model architecture. Includes full text, PDF, calculation tools and…
-
4.8
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.
-
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
hr98w/jev-visual
An educational project for running vision-language model inference on Apple Silicon via MLX: answers multiple questions about one image by choosing options or scoring levels, without autoregressive generation.
-
4.8
kitze/skillbox
Self-hosted versioned skills library for AI agents: stores markdown skills with immutable revisions, access profiles and client keys, exposed via HTTP MCP or a stdio bridge. Lets a team centrally manage prompts and…
-
4.8
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.
-
4.8
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.
-
4.8
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.