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.
-
9.3
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.
-
8.4
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…
-
8.1
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
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.
-
7.7
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…
-
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.
-
7.0
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…
-
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).
-
6.8
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.
-
6.8
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.
-
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
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
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
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.
-
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.
-
6.2
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.
-
6.2
korcarc/text-humanizer
A Python tool that rewrites AI-generated text through an LLM and translation pipeline to bypass detectors like Turnitin and GPTZero. Supports 8 languages and requires a DeepSeek API key.
-
6.1
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,…
-
6.1
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.
-
6.0
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.
-
6.0
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
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…
-
6.0
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.
-
5.9
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.
-
5.9
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…
-
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
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.
-
5.8
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.
-
5.8
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).
-
5.7
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
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
chaseleantj/desktop-habitats
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
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,…
-
5.6
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
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
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.
-
5.5
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…
-
5.5
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
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.
-
5.3
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
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.
-
5.3
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
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
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
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…
-
5.1
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…
-
5.0
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.
-
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
sabbircode-dev/learning-python
A personal repository of learning programs and exercises covering Python basics: variables, conditions, loops, functions and simple projects.
-
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.
-
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
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
Tencent/WeKnora
Open-source LLM knowledge platform: turns raw documents into queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
-
4.8
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…
-
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…
-
4.7
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…
-
4.7
dimentary/llm-robotics-playground
A library of experiments applying frontier LLMs/VLMs to robotics: MuJoCo environments, controller code, and recorded runs for tasks like cable untangling, mobile manipulation, writing, and drawing.
-
4.7
jasonku09/grill-with-ui
A skill for coding agents that moves the "grilling" design interview out of the terminal onto a local browser page: questions appear as cards with options and recommendations, and staged answers ship to the agent in…
-
4.7
kitze/unclutter
Chrome and Firefox extension that uses the Jev model via Vercel AI Gateway or TypeSafe AI to classify nonessential page elements and hide them, storing reusable rules per page template.
-
4.7
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…
-
4.7
mirkovicdev/HFTENGINE
A replay console for hftbacktest market-making backtests: shows the order book, queue position of every resting order, feed and order latencies, fills and the raw feed on real recorded Binance Futures data. A…
-
4.7
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.
-
4.7
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.
-
4.7
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.
-
4.6
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.
-
4.6
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.
-
4.6
isinternets/Dawn
A Destiny 2 mod (build 86657) adding authored Lua missions, native gameplay systems and an in-game loadout editor; installed via a PowerShell installer over an existing game installation.
-
4.6
KevinLiss/ApeAdmin
ApeAdmin is an open-source admin framework built on FastAPI + Vue3 for AI applications, with RBAC, audit logs, plugins, and an MCP-SSE gateway exposing system functions as tools for AI agents.
-
4.6
mmdju/digikala-mcp
Public MCP server that gives AI agents real Digikala data: search, compare and price-check products, discounts, ratings, sellers and reviews. Read-only, no API key, hosted on Cloudflare Workers, 16 tools.
-
4.6
RectangleStory/Superpowers_Multi_AI
Modular prompt-engineering framework that turns AI agents (Cursor, Claude Code, Copilot) into disciplined engineers: it forces them to plan, isolate context, and debug code through a strict SDLC protocol.
-
4.6
standardagents/jevpilot
A playable Three.js driving simulator where an autopilot powered by TypeSafe AI's Jev LLM drives the car: it receives compact tables of road, traffic and signal data and picks steering and speed. A demo of Tesla…
-
4.6
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.
-
4.5
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
devagrawal09/jev-review
A TypeScript code-review tool that analyzes a Git diff or a whole codebase through structured TypeSafe Jev model calls and shows the report in a local dashboard.
-
4.5
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.
-
4.5
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
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.
-
4.4
inikolax/remiqora
Local GPU-powered music generation studio unifying ACE-Step 1.5 and YuE2-3B in one Vue interface with a multitrack DAW, stem separation, MIDI transcription, and LoRA fine-tuning.
-
4.4
ruc-datalab/EvoOntology
A self-evolving ontology layer for data agents: a Claude Code and Codex plugin that builds and evolves a semantic ontology over tables, files, and databases via MCP tools.
-
4.4
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.
-
4.3
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.
-
4.3
agentverse-os/AgentVerse-OS
Personal cloud OS for a developer and their AI agents on a single server: a browser-based windowed desktop, isolated workspaces with VS Code, Claude Code and Codex, a store of 944 self-hosted apps, access only via…
-
4.3
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.
-
4.3
giuliosmall/pg_typesafe
Pre-alpha PostgreSQL extension that calls TypeSafe AI (System One / Jev) directly from SQL for categorical classification: Choice, Noul, and Score.
-
4.3
n8n-io/n8n
Fair-code platform for workflow automation and AI agents: visual canvas plus custom code, self-hosted or cloud, with 1500+ integrations.
-
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.
-
4.2
AnotiaWang/awesome-jev
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.
-
4.2
arnegiacomo/fugleramme
E-ink bird frame for Raspberry Pi that detects birds in real time by audio using BirdNET-Go and displays them as hand-cut 1800s illustrations.
-
4.2
dbreunig/building-with-jev-skill
An agent skill for writing and improving programs that call Jev, TypeSafe's System One model. It covers question design (Choice, Score, Noul), state structure, and confidence thresholds.
-
4.2
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.
-
4.2
kuhnhomeuk-cell/procedural-film
An agent skill that turns a topic into a 30-second vertical film: all visuals are drawn on canvas in vanilla JavaScript and sound is synthesised with Web Audio, with no media assets. Output is a single HTML player plus…
-
4.2
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,…
-
4.2
linguo2625469/workbuddy2api-panel
Self-hosted OpenAI-compatible gateway that turns Tencent CodeBuddy accounts into a unified /v1/chat/completions API with account pooling, rotation, cooldowns and a web admin panel.
-
4.2
LingxiangXu/traceclause
A local-first workbench for reviewing requirements against evidence: it compares a requirements document with a proposal or response, surfaces candidate quotations, and records human decisions with traceable citations.…
-
4.2
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.