ToolAI.io · GitHub Channel

Open-source AI Projects on GitHub

A fact-based index of LLM, agent, MCP, RAG and AI development projects, with license, setup, download, screenshots and related resources for each entry.

30 published projects 16 topic categories AI facts first

Featured projects

Browse list →

Public repository data

Project index

30 projects
claude-code — Agentic coding in the terminal screenshot
ai coding devtools Featured

claude-code — Agentic coding in the terminal

anthropics/claude-code

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands

★ 139.9K⑂ 22.5KTypeScript
License not detectedQ@project.QualityScore
PaddleOCR — OCR and document intelligence screenshot
multimodal ai

PaddleOCR — OCR and document intelligence

PaddlePaddle/PaddleOCR

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages

★ 86.7K⑂ 11.1KPython
Apache-2.0Q@project.QualityScore
faiss — Vector similarity search screenshot
rag knowledge systems

faiss — Vector similarity search

facebookresearch/faiss

A library for efficient similarity search and clustering of dense vectors

★ 40.6K⑂ 4.5KC++
MITQ@project.QualityScore
NemoClaw — Agent runtime and deployment tooling screenshot
agents multi agent

NemoClaw — Agent runtime and deployment tooling

NVIDIA/NemoClaw

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

★ 22K⑂ 3KPython
Apache-2.0Q@project.QualityScore
Qwen3-VL — Vision-language models screenshot
multimodal ai

Qwen3-VL — Vision-language models

QwenLM/Qwen3-VL

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud

★ 19.7K⑂ 1.8KPython
Apache-2.0Q@project.QualityScore
tiktoken — Fast tokenization screenshot
inference deployment runtime

tiktoken — Fast tokenization

openai/tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models

★ 18.9K⑂ 1.6KRust
MITQ@project.QualityScore
Qwen-Agent — Tool-using and RAG agents screenshot
agents multi agent

Qwen-Agent — Tool-using and RAG agents

QwenLM/Qwen-Agent

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc

★ 16.9K⑂ 1.7KPython
Apache-2.0Q@project.QualityScore
SkillOpt — Skill optimization for agents screenshot
agents multi agent

SkillOpt — Skill optimization for agents

microsoft/SkillOpt

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts

★ 15.5K⑂ 1.4KPython
MITQ@project.QualityScore

Recently updated

qwen-code — Command-line coding agentQwenLM/qwen-code★ 26.5K openai-agents-python — Python agent orchestrationopenai/openai-agents-python★ 28.3K NemoClaw — Agent runtime and deployment toolingNVIDIA/NemoClaw★ 22K codex — Coding agent and developer workflowsopenai/codex★ 103.2K TensorRT-LLM — Optimized LLM inferenceNVIDIA/TensorRT-LLM★ 14.3K faiss — Vector similarity searchfacebookresearch/faiss★ 40.6K

Most starred

markitdown — Document conversion and extractionmicrosoft/markitdown★ 170.7K skills — Reusable agent skills and workflowsanthropics/skills★ 165.7K claude-code — Agentic coding in the terminalanthropics/claude-code★ 139.9K whisper — Speech recognition and transcriptionopenai/whisper★ 106.4K DeepSeek-V3 — Large language model research and inferencedeepseek-ai/DeepSeek-V3★ 104.1K codex — Coding agent and developer workflowsopenai/codex★ 103.2K