GitHub trends for September 28, 2026
What was taking off on GitHub on September 28, 2026: peak magnitude of the day, summary and where it was spotted.
-
9.3
vectorize-io/hindsight
Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server…
-
9.0
paperclipai/paperclip
Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage…
-
8.2
mexicat/pdoom-video
A generative, code-rendered music video built with TypeScript and three.js, where every scene is synced to the song's lyrics and each frame is a deterministic function of track time. It includes a Python audio-analysis…
-
8.0
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.
-
7.8
dzhng/jevgrep
A CLI for coding agents that finds relevant files and source excerpts in a repository from a question about code behavior. It uses Jev for relevance ranking and requires a Vercel AI Gateway, TypeSafe, or OpenRouter key.
-
7.4
Niko1221/Strata
A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
-
7.2
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…
-
7.2
mvschwarz/openrig
OpenRig is a harness orchestrator for AI coding agents: a team of agents (Claude Code and Codex) is defined in YAML and booted with one command, turning scattered terminal sessions into a managed team with a lead agent.
-
7.2
yihui-dev/awesome-opus5-5-videos
A collection of 282 viral videos made with Claude Opus 5.5, each with the creator's exact prompt. The prompts generate animations as code using HTML, Canvas, SVG, Three.js and GLSL.
-
7.1
InfinityLoop1308/PipePipe
A NewPipe fork for Android that lets you browse YouTube and other video services without ads, with SponsorBlock, ReturnYouTubeDislike, background playback and playlist downloads.
-
7.0
firelex/jeff
Small fine-tuned Qwen3.5 and Gemma 4 models for zero-shot classification: given a situation description and a list of options, they return a calibrated probability for each option in a single forward pass.
-
6.9
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…
-
6.9
NVIDIA/OpenShell
A safe, private runtime for autonomous AI agents: isolated sandbox containers governed by declarative YAML policies restricting filesystem, network, and process access. Manages credential injection for agents like…
-
6.8
reladraw/reladraw
A text language for diagrams where element placement is stated in words (above-left of, between) instead of coordinates; a TypeScript parser, resolver and SVG renderer plus a CLI.
-
6.7
debpalash/VoiceStudio
A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11…
-
6.7
ollaya-dev/ollaya
A local runtime for decision models: pulls and serves classification and routing models behind a TypeSafe-compatible API. Like Ollama, but for models that return probabilities instead of text.
-
6.6
ucashier/UCashier-USDT-Payment
Stablecoin payment infrastructure for accepting and paying out USDT (TRC/ERC) and USDC (ERC): buyers pay directly into the merchant's wallet, while payouts, splits and supplier settlements go out from the same merchant…
-
6.4
cs341-illinois/coursebook
An open-source introductory systems programming textbook in C for the CS 341 course at the University of Illinois, covering Linux, POSIX, and memory. Built from LaTeX into PDF, Markdown, and HTML.
-
6.4
deepfates/imp
A port of DSPy to the BEAM: declarative LM programs in Elixir with signatures, optimizers and agents running as OTP processes.
-
6.4
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…
-
6.4
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.
-
6.3
feitangyuan/onetake
A Claude Agent Skill for making product launch films and feature demos as one continuous take, where each beat grows out of the previous one and continuity is verified by an oracle.
-
6.3
shihabal3amri/DiPlay
Independent CarPlay receiver for compatible Android head units: wired and wireless, local authentication, no jailbreak or dongle. Public preview 0.2.0.
-
6.3
xikhar/spiderbench
A browser-based 3D web-swinging game built by Claude under human direction as a non-commercial fan project and benchmark of AI game-development capabilities.
-
6.2
Contrastive-LM/CLM
CLM is a class of System One language models trained contrastively to connect states and actions; the repo serves CLM-8B behind a TypeSafe-compatible API for fast agent decision-making.
-
6.2
lemomo-ai/lemo-opuscar
A collection of 39 film styles, each with a reusable style prompt, a short film made entirely in code (Canvas/WebGL, TTS, ffmpeg), and DIRECTOR.md/TECHNIQUE.md guides for an AI agent director.
-
6.2
rohitg00/ai-engineering-from-scratch
Open-source AI engineering curriculum: 523 lessons across 20 phases (~342 hours) in Python, TypeScript, Rust and Julia, where every lesson ships a reusable artifact such as a prompt, skill, agent or MCP server.
-
6.2
VectifyAI/PageIndex
A vectorless RAG engine that builds a hierarchical tree index of a document and retrieves by LLM reasoning over that tree, the way a human navigates a report. Aimed at long professional PDFs such as financial, legal…
-
5.9
brainbrick-trades/The-Quant-Trading-Vault
A catalog of 5,806 quantitative trading strategy specifications in Pine Script, JavaScript, Python, C++, and MyLanguage covering crypto spot, futures, grid systems, arbitrage, and market making. The README also…
-
5.9
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.
-
5.9
moguzbulbul/blueprint-animation
A Claude Design skill that turns a UI screen into a step-by-step blueprint animation explaining UX decisions or showing a Before-to-After redesign.
-
5.9
shengjidaguai-china/goutoujunshi
A Codex Skill for relationship analysis: it first offers emotional support, then separates facts from guesses and gives concrete next steps. It draws on a knowledge base covering psychology, law, sociology and…
-
5.9
yetone/magpie
A menu-bar utility for macOS/Linux/Windows that lets you pick the model for each AI agent (Codex, Claude Code, Gemini CLI, etc.) and runs a local gateway translating OpenAI and Anthropic APIs between agents and…
-
5.8
AgentSystemLabs/agent-office
A 3D cartoon office where a team hires Claude Code, OpenCode or Codex workers at desks, watches their live terminals, chats by voice, and tracks GitHub issues and PRs per project floor.
-
5.8
kaankiziltug/logo-design-skill
A skill set and tools for Claude that turns it into a disciplined logo designer: principles, process, SVG craft, testing tools and a 1,400+ reference library.
-
5.8
seamusc/papermono-shopping-list
Firmware for the M5Stack PaperMono e-paper device that turns it into a fridge shopping list synced with a phone via a FastAPI server.
-
5.8
tobi/disktree
A treemap utility for Omarchy built with Rust + GPUI: scans a disk, draws directories as tiles sized by real disk usage, and lets you mark clutter for deletion or trashing.
-
5.7
Appllama/liquid-glass-chat-ui
A set of two Expo/React Native UI cookbooks for iOS: liquid-glass chat interfaces with animated portraits, stories, and a floating composer. Acts as a reference and copy-paste prompts for integrating these screens into…
-
5.7
ashhart/TensorFold
LLM inference server for Apple Silicon (MLX) and NVIDIA GPUs with an OpenAI-compatible API and exact speculative decoding. Supports Nemotron, Qwen3.8, GLM-5.3 and Gemma 4 families with per-family kernels and draft…
-
5.6
mobile-next/mobile-mcp
MCP server for mobile automation on iOS and Android: agents and LLMs drive emulators, simulators and real devices via the accessibility tree or coordinate-based taps.
-
5.6
satnaing/shadcn-admin
Admin dashboard UI built with Shadcn UI and Vite, featuring multiple pages and components with dark mode, responsiveness, accessibility and RTL support.
-
5.5
ahmd-sh/hntui
A terminal TUI client for reading Hacker News: six feeds, comments, saved posts, themes, and Vim-style navigation.
-
5.5
devdotfast/whiteboard
An open-source desktop IDE for software design where humans and coding agents share a canvas: the agent draws diagrams you can jump from straight into code.
-
5.5
glanderness/BeefTV
A local-first desktop video workspace with AI agents: on a free canvas it links models, assets and generation tasks for text, images, video and audio into an editable workflow.
-
5.5
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.
-
5.5
mrtinkz/ai-charter
A public site hosting the Universal AI Charter — governance principles based on disclosure — plus a certification registry where companies publish model training sources, hazards, and outcomes.
-
5.4
angusdevgo/Seep-Reverse-Lab
Agent-native reverse engineering workbench for binaries and CWE-602 client-side authorization auditing: unifies Radare2, JADX, Apktool, Frida and IDA via 23 MCP tools with automatic task routing.
-
5.4
vercel/next.js
Next.js is a React framework for building full-stack web applications with server rendering and Rust-based build tooling. Used by large companies for fast, universal sites.
-
5.3
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.
-
5.3
emir/aikon
Unofficial Claude client for Nokia Series 40 phones (Java ME) plus a small Go server that proxies requests to the Claude API over TLS 1.0. Lets you chat with Claude, search the web, and manage calendar and notes on old…
-
5.3
mg-chao/snow-shot
Source code for Snow Shot (screenshots, screen recording, OCR) and Snow Image Viewer — C++/Qt utilities for screen capture and image viewing.
-
5.3
rgodha24/walgithub
walgit is a git server as a single binary that stores repositories in an object store (S3/GCS) with no database and no local state. It supports smart HTTP fetch/push, bundle-uri, Git LFS, a web UI, API, push policies,…
-
5.3
Rieranthony/product-film-skill
A Claude Code skill that produces showreel-grade product films with Remotion: it learns your design system, writes the story, cuts music on the beat and renders the final film.
-
5.3
SelmiAbderrahim/rankme.fast
Self-hosted SEO platform: site audits, rank tracking, keyword research, backlinks, Search Console and AI-answer visibility. Uses your own API keys (DataForSEO, Google, Firecrawl) and keeps data in your MongoDB and…
-
5.3
Themaister/pyrowave
PyroWave is an intra-only video codec (essentially a still-image codec) implemented in Vulkan compute shaders, optimized for extremely fast GPU encode/decode (<0.1 ms at 1080p). It targets local network game streaming…
-
5.3
yasinozmeen/animasyon-stil-katalogu
A catalog of 20 animation styles for videos: each style is demonstrated by its own 9–10 second clip, selectable from the README before producing a new video.
-
5.3
zhuyansen/awesome-claude-video-skills
A curated list of 180 open-source skills and toolkits that let Claude Code, Codex and other coding agents create and edit video — from Remotion and HyperFrames to motion graphics and avatars, each repo security-graded.
-
5.2
JoasASantos/Offensive-Security-AI-Models
A curated list of open-weight uncensored LLMs fine-tuned for cybersecurity tasks such as red teaming, penetration testing and security research. Each entry lists base model, size, context, VRAM and uncensoring method.
-
5.2
ZJU-REAL/Easel
An open-source AI agent for social media: it discovers trends, creates content, publishes it to Xiaohongshu, Douyin, Zhihu, Bilibili and more, and analyzes what performs. Aimed at content creators and social media…
-
5.1
dagowda/notRDP
A Havoc C2 plugin that creates a hidden alternate Windows desktop, streams it to a browser viewer, and forwards mouse and keyboard input while staying invisible to the target user.
-
5.1
derv82/wifit3
Cross-platform USB Wi-Fi auditor in Python: scans networks, captures WPA handshakes and PMKIDs, attacks WPS and WEP via its own userland drivers without aircrack-ng.
-
5.1
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…
-
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
DanFessler/trellis
A layout engine for web apps: panels nest to any depth, the view zooms to the part you need, and every view stays mounted. Ships as a framework-agnostic core, a React adapter and a web component.
-
5.0
Inkloom-art/inkloom
Specialised AI models for logo design: brand analysis turns a business into constraints, typography and symbol models construct the mark, and a composition engine produces lockups and clear-space rules. Generation is…
-
5.0
Leonxlnx/claude-launchvideo
The repo contains a 33-second launch film for a fictional product Tessel, fully generated from code: visuals with Remotion (React), soundtrack synthesized in Python. It demonstrates code-driven video production without…
-
4.9
anthropics/claude-code-action
A GitHub Action that runs Claude Code on PRs and issues: answers questions, reviews code, and implements changes triggered by @claude mentions or explicit prompts. Supports Anthropic API, Bedrock, Vertex AI, and…
-
4.9
byoungd/up
An open book-guide on lifelong learning in the AI era: English, working with AI, real projects, recovering from setbacks. For ordinary people seeking direction.
-
4.9
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.
-
4.9
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.
-
4.9
OnlistTeam/ai-manager
A local-first desktop app for installing, updating, and configuring AI coding CLI tools (Claude Code, Codex and others), and managing their API endpoints, Skills, MCP connections, and prompts without hand-editing…
-
4.9
RamitVishwakarma/Janus
A small macOS menu bar app that switches between Claude Code accounts in one click and clears developer caches by moving them to the Trash.
-
4.9
t8y2/dbx
A 20 MB lightweight cross-platform database client for 90+ databases (MySQL, PostgreSQL, SQLite, Redis, MongoDB, etc.) with built-in AI assistant, MCP server, CLI, and desktop/Docker modes.
-
4.9
TwoSevenOneT/InjectSetConsole
Proof of Concept for Windows process code injection via a named pipe, without using VirtualAllocEx or WriteProcessMemory. Demonstrates an EDR evasion technique for security researchers.
-
4.8
alexgreensh/anidoodle
A tool for generating deterministic hand-drawn art and animation as code: nine styles, export to PNG, GIF, MP4, WebM and HTML. Works as an agent skill for Claude Code.
-
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
farion1231/cc-switch
Cross-platform desktop manager for Claude Code, Codex, Gemini CLI, OpenCode and other agentic tools: configure and switch between providers and models in one place.
-
4.8
santtiago49/system-design-trainer
A trainer for system design interviews: a whiteboard with draggable AWS/Azure components, a deterministic capacity model, and design grading by an AI assistant called Jev.
-
4.8
sciaschi/CBFD-Recompiled
A native PC port of Conker's Bad Fur Day (N64), built by static recompilation with N64Recomp, running on N64ModernRuntime and rendered by RT64. Requires your own legally obtained US ROM.
-
4.8
ScottieFox/caustic-volume
Real-time water caustics in the browser built on three.js: sunlight bends through a moving water surface and gathers into bright shifting lines on the pool floor. Two single-file HTML versions, lite and sandbox, with…
-
4.7
aaddrick/building-with-typesafe-jev
Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed questions (Choice, Score, Noul) with calibrated confidence, plus 150+ community project examples.
-
4.7
athemeroy/awesome-claude-5-5-videos
A curated, source-linked guide to 1,000+ videos made with Claude Opus 5.5, covering topics, visual styles, and how the frames were produced.
-
4.7
bjarneo/flux
Connects an Omarchy desktop and an Android phone over the local network: file and clipboard sharing, notifications, media, camera and microphone. Includes a CLI, daemon, Qt window, shell plugin and Android app.
-
4.7
dashersw/coyopedal
Firmware for a guitar pedalboard on ESP32-S3: runs full-size NAM A2 neural amp models in real time, acts as a USB host for an audio interface, and has a touchscreen UI compiled to native C++.
-
4.7
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.
-
4.7
supermemoryai/company-brain
Open-source version of a company brain for Slack: it remembers team conversations, answers from them, and performs tasks in connected tools (GitHub, Linear, Notion, etc.). Runs on your own Cloudflare account.
-
4.7
tigerless-labs/agent-memory
Local long-term memory runtime for AI agents: Markdown files as the source of truth, ranked retrieval over a SQLite index, and sleep-time consolidation. One shared store for Claude Code and Codex, no API keys.
-
4.6
Barty-Bart/motion-graphics
A set of motion-graphics skills for Claude Code and Codex. The first skill, motion-broll, takes a video and transcript and plans, animates and renders B-roll clips timed to your words.
-
4.6
chuspeeism/awesome-opus-5-5-videos
A curated collection of 300 video examples made with Claude Opus 5.5, categorized by purpose, with author credits, original X posts and prompts. Videos play directly inside the README.
-
4.6
Human-Agent-Society/reef
Continual learning infrastructure for self-improving agents: connects agent inference, feedback collection, learning, and versioned delivery of updates. Lets you train model weights or improve an agent's harness…
-
4.6
InternLM/Intern-Decision
A multimodal decision model built on Qwen3.5 that turns a state, optional images, and typed questions (choice, score, yes/no) into decisions with probabilities. Ships with training, two inference backends, temperature…
-
4.6
moeru-ai/airi
Self-hosted AI companion (waifu/VTuber) with realtime voice chat, Live2D/VRM avatar and the ability to play Minecraft and Factorio; runs in browser, on macOS and Windows.
-
4.6
NaiveAI-Labs/Naive-N0.5-Flash
An open-weight 309B MoE model (15.5B active) for coding and AI R&D with a native 1M-token context via hybrid SWA–DSA attention. Weights and inference code under MIT, plus API access.
-
4.6
NVIDIA/Model-Optimizer
NVIDIA library for compressing and accelerating models: quantization, pruning, distillation, NAS and speculative decoding with export to TensorRT-LLM, vLLM, SGLang. For ML engineers preparing models for deployment.
-
4.6
pch/rawmakase
Non-destructive RAW photo developer for Linux and macOS written in Rust: opens RAW files via LibRaw, edits with Lightroom-style controls, and exports JPEG or 16-bit TIFF. Imports Lightroom Classic catalogs with…
-
4.6
SecFathy/xss-specialist
Research prototype for XSS discovery: an offline study on specializing a small LLM via KEV-gated continual learning plus a live authorized assessment system where findings are confirmed only by execution in a headless…
-
4.6
wangmingxuan666/Tiersense
TierSense hub repository with documentation and integration examples for three agent modules: task difficulty scoring, selecting history steps to compress, and deciding whether to compress or recall memory.
-
4.6
willfaust/Madeira
A research project for running x86-64 Windows games on a non-jailbroken iPhone by combining Wine, FEX-Emu (x86-64 → ARM64 translation) and DXMT (D3D11 → Metal) in a single Mach process.
-
4.5
actions/runner-images
Source code for VM images of GitHub-hosted runners in GitHub Actions and Microsoft-hosted agents in Azure Pipelines: Ubuntu, Windows, macOS with preinstalled software.
-
4.5
Altimor/flo-state
A Swift/AppKit/TextKit 2 rewrite of the Flo State markdown editor that matches the web app's live-preview rendering, including tables, KaTeX, Mermaid, HTML blocks and wiki links. Replaces the Tauri app with no web view…