Most starred

A curated collection of datasets for Large Language Models (LLMs), covering medical AI, NLP, multimodal learning, instruction tuning, reasoning, code generation, and evaluation benchmarks.

[CVPR 2026] Thinking in 360°: Humanoid Visual Search in the Wild

We have summarised all 3D anomaly detection methods and datasets (still updating). 多模态，点云和姿势无关异常检测的综述仓库（持续更新）

🧊 A High-Perf Quantitative Trading Framework for Crypto

Decrypt Chromium based browser passwords with PowerShell.

📖 Data Engineering from Raw Corpora

Discover, mask, and verify sensitive data in SQL databases — an auditable scan → mask → validate workflow for safe database copies.

DeepSeek Harness (DSH) Python 教程：17 章从零实现 Agent Loop、插件系统、工具调用、Session、上下文工程、Subagent 与 Headless CLI

Benchmarking models as runtime Controllers for Loop Engineering

麦麦热量管家：减脂不是少吃你爱的，是先换掉不值这口热量的。基于麦当劳 MCP 的味热比点餐 Skill。

ESP32 MCP firmware for iPhone USB input, built for M5Stack StopWatch with guided board adaptation

Local-first scientific literature RAG with frozen evidence, exact human annotations, paper screening, and reproducible offline workflows.

MCP server for token-efficient large document analysis via the use of REPL state

HiveMind Protocol - A Local-First, Privacy-Preserving Architecture for Agentic RAG

A source-backed Jev / System One knowledge map: projects, papers, evaluations, robotics, and social discovery.

claude fintech skills of running fintech infra, trading platforms, and borker-side systems in production

coinbase trading bot for momentum strategies with optional profit transfers, CSV backtests, and a clean CLI

Crypto arbitrage trading bot that detects triangular and cross-exchange opportunities, executes trades automatically, and includes backtested strategies with high historical returns.

Verified Codex-to-ChatGPT Web reasoning handoffs with local edits, tests, and receipts.

🔒 Modern C2 Platform with Cloudflare Tunnel Integration | WinRM & SSH Remote Management | Real-time Terminal & Remote Desktop | Built with FastAPI & React

relational database stored in discord guilds

MAC address manufacturer lookup database combining IEEE, Nmap, Wireshark and HDM Mac-Tracker, with downloadable formats and a browser lookup. https://ringmast4r.github.io/OUI-Master-Database/

Native lakehouse experience in Postgres powered by DuckDB & DuckLake

Codex plugin for OpenPencil — an interactive Rust/WASM canvas for AI-assisted UI design. Create editable .op files from prompts, refine selected elements, generate image assets, and install with one prompt on macOS, Windows, and Linux.

Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fetch worker tools.

Hardware-first crash forensics for Cortex-M: staged bring-up, zero-probe UART diagnostics, and causal fault replay.

An MCP server that seamlessly creates infrastructure diagrams for AWS, Azure, GCP, Kubernetes and more

One IDE for you and your AI team. A VS Code fork where Claude Code, Codex, Antigravity, and Muse Code work in parallel across multiple projects and features.

Say "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. 麦当劳点餐 Skill.

Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI, and headless CLI.

Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

TiyGate is a lightweight gateway for highly available LLM services. 一款致力于提供高可用 LLM 服务的轻量级网关。

A private, modular node based AI workspace for thinking and creation. Seamlessly connect to Ollama, OpenAI, Gemini, Anthropic, and Groq models in one unified, node-based interface for reasoning, visualization, and exploration — all running locally or via API.

Auto AI improver. Cost and token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read hints, PDF/Office/CSV/md file interception, 255+ filter & interception rules, compact manifest injection, image shrinking, cache and compact skills, cache MCPs, prompt injection protection, and much more.

Official implementation of paper LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

"Never send a human to do a machine's job" - Open Source AI hacking agent

A modern, open-source database client for desktop and web.

A comprehensive, hands-on learning repository covering Rust programming from fundamentals to advanced topics — including networking, async programming, macros, and system design.

Open-source ESP32 filament scale with NFC and touch display for Spoolman, FilaMan and BamBuddy: weighs spools and updates the inventory, reads Bambu tags and writes its own, creates spools right on the scale, prints labels on Bluetooth printers, with a web interface.

Local-first recruitment intelligence and application operations agent

Research and writing can be automated. Authorship cannot. Evidence list + agent skills for spotting AI-produced papers no human stood behind.

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

The Best TypeScript framework for fine-tuning

Eva01 is NOT an assistant. She is an AI being with her own mind, feelings, and intrinsic drives. Multimodal, Modular design. Built-in voice & face recognition. Plug'n play tools. Compatible with ChatGPT, Claude, Deepseek, Gemini, Grok, and Ollama. Explore the possibilities of Human-AI Interaction.

Privacy-first LLM proxy and AI gateway - load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.

Live truecolor terminal dashboard for a locally running LLM: tok/s, TTFT, GPUs, context, MTP acceptance, layer and real expert routing (llama.cpp)

Three Claude master skills: edit your videos, make them go viral, and build anything. Free, MIT.

OpenAI Codex 源码深度研究 (Rust + TS + Python)：2 总纲 + 25 章 + 3 附录, ~51 万字 + 149 张 Mermaid 架构图

MoE expert offload for low-VRAM GPUs — run 100B+ MoE models (DeepSeek, Qwen, Mixtral) on 8 GB cards. Expert cache with LRU hot experts, OpenAI-compatible proxy, GGUF multi-shard.

Working CLI-first copytrade terminal for Robinhood Chain — live token discovery, profit hunters, COPY wallets, paper engine and native queue.