Live trending repositories
Repositories caught as they rise — ranked by stars gained this week. An alternative to GitHub Trending.
cactus-compute/needle
14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
35 Python repos in this week's snapshot · fastest riser: cactus-compute/needle +2985 stars
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
Graph-Native Infrastructure for Context and Accountable AI Systems
Use Claude Code, Codex, Pi, and OpenCode and more for free (1.3B+ free tokens) from your terminal, app, IDE, or phone like OpenClaw (voice supported + ToS friendly)
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
Open-source personal finance manager. Self-hosted, privacy-first.
Official, Anthropic-managed directory of high quality Claude Code Plugins.
RL training environments for Microduck (mjlab)
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Community plugin marketplace for Claude Cowork and Claude Code. Read-only mirror — submit plugins at clau.de/plugin-directory-submission.
Learn it. Build it. Ship it for others.
🧠 Train a 64M-parameter LLM from scratch in just 2h!
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.
🦔 PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
A collective list of free APIs
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
中国专利.skill：专利点挖掘与交底书（发明/实用/外观）编写，通俗解读专利，嗅探政策动向，辅助审查答复。
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Removes 20+ patterns of AI slop from any piece of writing.
Fully automatic censorship removal for language models
GEO-first SEO skill for Claude Code. Comprehensive AI search optimization for any website — citability scoring, AI crawler analysis, brand authority, schema markup, platform-specific optimization, and PDF reports. If you want learn how to sell this to real businesses, check out the skool community
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Agent skill that removes signs of AI-generated writing from text
Skills Catalog for Codex
Python tool for converting files and office documents to Markdown.
The agent that grows with you
Public repository for Agent Skills
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Snapshot 2026-09-12 · 35 repos
How the ranking works
Every day at 00:00 UTC Hotfork takes a snapshot of public GitHub repositories and records each repo's star count. The trending score is the raw difference between the current count and the snapshot — no votes, no editor picks, no sponsored slots. Repos with the largest star gain this week rank highest.
This weekly snapshot tracks 35 repositories across 16 languages. The score counts stars only — forks, issues, and pull requests are shown on repo pages but never change a repo's rank. The same snapshots power the free Hotfork iOS app.
FAQ
How is this different from GitHub Trending?
Hotfork ranks by raw stars gained since the daily snapshot (00:00 UTC) — a transparent, reproducible number. GitHub Trending's ordering isn't publicly documented, so its results can't be checked or reproduced.
When is the feed updated?
A new snapshot is taken daily at 00:00 UTC. The page you are reading is served from the most recent snapshot, so the ranking is stable within the day instead of flickering while you browse.
Is Hotfork free?
Yes. The web feed and the Hotfork iOS app are both free, with no account required and no ads.
Does Hotfork track me?
No. There is no sign-in, no analytics and no advertising identifiers. Your bookmarks in the iOS app live on your device only.