Open-source agentic data engineering harness for dbt, SQL, and cloud warehouses. 100+ tools, 10 warehouses, AI-powered.
Repository Index
132,218 visible repositories in the index
2,377–2,400 of 3,493 · Most stars
An agent benchmark with tasks in a simulated software company.
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
- large-language-models
- llm
- mixture-of-experts
- deep-learning
Tencent Hunyuan A13B (short as Hunyuan-A13B), an innovative and open-source LLM built on a fine-grained MoE architecture.
pi extension: /purge swaps pi's built-in assistant persona for your own prompt file
A shell script utility that automatically resumes Claude CLI tasks when usage limits are lifted.
- auto-resume
- claude
- claude-ai
- claude-code
RDNA-native LLM inference engine in Rust.
- amd-gpu
- gpu-computing
- hip
- llm-inference
The most easy-to-understand tutorial for using LoRA (Low-Rank Adaptation) within diffusers framework for AI Generation Researchers🔥
- aigc
- diffusers
- fine-tuning
- guidebook
📱 Real-time mobile monitor & remote control for Antigravity AI sessions. Mirrors your desktop chat to your phone via Chrome DevTools Protocol (CDP) with sub-100ms snapshots, secure global tunnel access (ngrok/Cloudflare/Pinggy), HTTPS, and full remote control.
- ai
- antigravity
- cdp
- chrome-devtools-protocol
Open-source, multi-platform harness for AI agents - a native, multi-threaded operator's console (JVM, not Electron) to run Claude Code, Codex, Gemini or OpenCode with a real browser, terminal, editor, secrets & 200+ MCP tools. Built for enterprises, science & research.
- agent-harness
- ai-agents
- browser
- claude-code
[Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.
Train a 1B LLM with 1T tokens from scratch by personal
Content for the Udemy Prompt Engineering Course
A test runner for agentskills.io-style AI agent skills
- agent-evals
- agent-skills
- agentskills
- ai-agents
An native MCP server extension for Ghidra
- ghidra
- ghidra-extension
- ghidra-plugin
- llm
发布前审|发抖音/小红书/视频号前先让 AI 审一遍:哪句踩线、依据哪条官方规则、给能直接用的改法。38 篇真实样本校准判定尺度,80+ 条官方原文引文可查证,你踩过的坑沉淀成本地规则库越用越准。不承诺过审,不教绕审。
- agent-skills
- ai
- chinese
- claude
Curated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.
🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.
An open-source, macOS text action popup for running custom scripts, AI actions, and extensible workflows on selected text.
- app-kit
- apple-intelligence
- applescript
- clipboard
Llama 3+ inference in pure Java
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
- ai-gateway
- mcp-gateway
- mcp-security
- ai-governance
FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST. Also support llm e.g, qwen3.6-27B
- cuda
- cuda-kernels
- realtime-inference
- realtime-vla
🤖 GPT( Deepseek and more ) Code Review for Gitlab (针对于 Gitlab 的 LLM 辅助 Code Review 工具)项目详细文档 👇🏻
AI multi-agent tool that turns research papers into cited commercialization and tech-transfer assessments: TRL, patent landscape, market and risks. CrewAI + FastAPI, with a reproducible benchmark.
- academic-research
- ai-agent
- commercialization
- crewai