ToolAI.io · GitHub Channel

Open-source AI Projects on GitHub

An objective, fact-checked index of LLM, agent, MCP, RAG and AI development projects. Each entry includes license, setup, download, screenshots and related resources, with human review before publication.

30 published projects 10 editorial categories AI facts first

Editor reviewed

Browse list →

Public repository data

Project index

30 projects
ai development 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

★ 139.1K⑂ 22.3KTypeScript
License not detectedQ@project.QualityScore
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

★ 86.3K⑂ 11.1KPython
Apache-2.0Q@project.QualityScore
rag knowledge

faiss — Vector similarity search

facebookresearch/faiss

A library for efficient similarity search and clustering of dense vectors

★ 40.6K⑂ 4.5KC++
MITQ@project.QualityScore
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

★ 21.9K⑂ 3KPython
Apache-2.0Q@project.QualityScore
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
evaluation safety

evals — Model evaluation framework

openai/evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks

★ 19K⑂ 3KPython
NOASSERTIONQ@project.QualityScore
inference runtime

tiktoken — Fast tokenization

openai/tiktoken

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

★ 18.8K⑂ 1.6KRust
MITQ@project.QualityScore

Recently updated

NemoClaw — Agent runtime and deployment toolingNVIDIA/NemoClaw★ 21.9K qwen-code — Command-line coding agentQwenLM/qwen-code★ 26.3K openai-agents-python — Python agent orchestrationopenai/openai-agents-python★ 28.2K codex — Coding agent and developer workflowsopenai/codex★ 101.5K claude-plugins-official — Official agent pluginsanthropics/claude-plugins-official★ 32.7K TensorRT-LLM — Optimized LLM inferenceNVIDIA/TensorRT-LLM★ 14.2K

Most starred

markitdown — Document conversion and extractionmicrosoft/markitdown★ 169K skills — Reusable agent skills and workflowsanthropics/skills★ 164.2K claude-code — Agentic coding in the terminalanthropics/claude-code★ 139.1K whisper — Speech recognition and transcriptionopenai/whisper★ 105.6K DeepSeek-V3 — Large language model research and inferencedeepseek-ai/DeepSeek-V3★ 104K codex — Coding agent and developer workflowsopenai/codex★ 101.5K