Agents & Multi-Agent
smolagents
huggingface/smolagents
A lightweight Python library for building agents that use tools and execute code to solve tasks.
★ 29.8K⑂ 3.1KPython
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.
Featured
Browse list →markitdown — Document conversion and extraction
Python tool for converting files and office documents to Markdown
★ 174.9K · Pythonskills — Reusable agent skills and workflows
Public repository for Agent Skills
★ 170.6K · Markdownclaude-code — Agentic coding in the terminal
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
★ 142.1K · TypeScriptwhisper — Speech recognition and transcription
Robust Speech Recognition via Large-Scale Weak Supervision
★ 107.7K · PythonDeepSeek-V3 — Large language model research and inference
An open-source project focused on large language model research and inference.
★ 104.4K · PythonDeepSeek-R1 — Reasoning model research and evaluation
An open-source project focused on reasoning model research and evaluation.
★ 92K · PythonHermes Agent
A self-improving AI agent built by Nous Research that features a closed learning loop, multi-platform messaging integration, and flexible model provider switching. It is designed to run on low-cost VPS, GPU clusters, or serverless infrastructure.
★ 227.1K · PythonHugging Face Transformers
A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal domains, supporting both inference and training.
★ 163.3K · PythonFirecrawl
An open-source web context API to search, scrape, and interact with the web at scale, converting web data into clean Markdown or structured JSON for AI agents and LLMs.
★ 161.1K · TypeScript MCP & Tool CallingDify: Collaborative Platform for Agentic Workflows and RAG Applications
Dify is an LLM application development platform for visually building workflows, RAG pipelines, and tool-using agents. It combines model management, prompt development, observability, and application APIs in a collaborative workspace that can be used as a hosted service or self-hosted.
★ 151.2K · TypeScriptLangChain
An open-source Python framework for building LLM-powered applications and agents through interoperable, chainable components and third-party integrations.
★ 143.6K · PythonGraphify: Turn Any Codebase into a Queryable Knowledge Graph
Graphify is a local-first CLI tool and AI assistant skill that parses codebases, docs, SQL schemas, and PDFs into a queryable knowledge graph using deterministic AST parsing, eliminating the need for vector stores or embeddings.
★ 104K · PythonPublic repository data
Project index
Fine-tuning, Training & Data
TRL
huggingface/trl
A library for post-training transformer models with supervised fine-tuning and preference-optimization methods.
★ 19.5K⑂ 3.1KPython
Agents & Multi-Agent
Claude Quickstarts: support, browser and agent reference applications
anthropics/claude-quickstarts
Anthropic’s reference application collection covers knowledge-backed support, data analysis, browser use and desktop interaction as starting points for development.
★ 17.7K⑂ 3KTypeScript
LLM & Foundation Models
Outlines
dottxt-ai/outlines
A library for generating structured, constrained outputs from language models.
★ 15.9K⑂ 901Python
Agents & Multi-Agent
Microsoft Agent Framework
microsoft/agent-framework
An open-source framework for building, orchestrating, and evaluating AI agents across Python and .NET.
★ 14K⑂ 2.4KPython
Speech, Audio & Voice
Qwen3-TTS: multilingual speech, voice design and cloning
QwenLM/Qwen3-TTS
An open speech model family from Qwen with preset speakers, text-driven voice design and reference-audio cloning for narration and speech applications.
★ 13.4K⑂ 1.7KPython
Computer Vision
DINOv2: visual features for classification and retrieval
facebookresearch/dinov2
Meta’s self-supervised vision models provide pretrained backbones and task heads for feature extraction, visual retrieval and downstream adaptation.
★ 13.3K⑂ 1.3KPython
Multimodal AI
TRELLIS.2: image-to-3D assets with materials
microsoft/TRELLIS.2
Microsoft’s 3D generation project with image-to-3D inference, PBR texturing and GLB export for GPU-equipped asset workflows.
★ 11.2K⑂ 1.4KPython
MCP & Tool Calling
mcp-use
mcp-use/mcp-use
A full-stack TypeScript framework for building MCP servers, clients, and interactive MCP apps.
★ 10.7K⑂ 1.5KTypeScript
AI Coding & Developer Tools
Claude Code Action: coding assistance in GitHub issues and PRs
anthropics/claude-code-action
Integrates Claude Code with GitHub Actions for comment-driven assistance, pull-request reviews and prompted maintenance tasks across supported providers.
★ 8.9K⑂ 2.1KTypeScript
Evaluation, Observability & Safety
garak — LLM vulnerability scanning
NVIDIA/garak
the LLM vulnerability scanner
★ 8.9K⑂ 1.2KPython
Multimodal AI
Qwen-Image: text-to-image generation and multi-image editing
QwenLM/Qwen-Image
Qwen image generation and editing models with Diffusers examples for text-rich artwork, product imagery and reference-guided edits.
★ 8.3K⑂ 546Python
Page 23 / 26 · 305 projects