开发者工具、SDK、API、测试框架
openai
The official Python library for the OpenAI API
oobabooga
The original local LLM interface. Text, vision, tool-calling, training, and more. 100% offline.
vllm-project
A high-throughput and memory-efficient inference and serving engine for LLMs
ggml-org
llama.cpp is a high-performance LLM inference engine written in C/C++, enabling efficient local deployment of large language models on consumer hardware with support for multiple quantization formats.
mark3labs
A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
ollama
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
steel-dev
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
CopilotKit
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
allenai
Toolkit for linearizing PDFs for LLM datasets/training
microsoft
Python tool for converting files and office documents to Markdown.
modelcontextprotocol
Model Context Protocol Servers
Portkey-AI
A blazing fast AI Gateway with integrated guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
vercel
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
bentoml
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
The official Python SDK for Model Context Protocol servers and clients
stacklok
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
pydantic
Data validation using Python type hints
abetlen
llama-cpp-python provides Python bindings for llama.cpp, enabling high-performance LLM inference in Python with support for OpenAI-compatible API server, LangChain integration, and multiple hardware acceleration backends.
huggingface
🤗 smolagents: a barebones library for agents that think in code.
The official TypeScript SDK for Model Context Protocol servers and clients
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
e2b-dev
Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app
cvs-health
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection
Specification and documentation for the Model Context Protocol
mlc-ai
Universal LLM Deployment Engine with ML Compilation
NVIDIA-NeMo
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
JetXu-LLM
Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Solutions to conduct Agentic RAG from actively selected GitHub public projects. It Augments through LL
TypeChat is a library that makes it easy to build natural language interfaces using types.
mistralai
Official inference library for Mistral models
nlmatics
Developer APIs to Accelerate LLM Projects
CatchTheTornado
Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSO
muellerberndt
MiniAGI is a simple general-purpose AI agent based on the OpenAI API.
smol-ai
the first library to let you embed a developer agent in your own app!
a16z-infra
A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs
OpenAPI specification for the OpenAI API
togethercomputer
OpenChatKit is an open-source toolkit for building specialized and general-purpose chatbots, providing a 20 billion parameter model, customization recipes, and evaluation tools for creating production-ready conversational AI.
minimaxir
Python package for easily interfacing with chat apps, with robust features and minimal code complexity.
different-ai
A dead-simple API to build LLM-powered apps
mattt
MCP generator for OpenAPIs 🫳🎤💥
protectai
The Security Toolkit for LLM Interactions
abhiz123
MCP server for Todoist integration enabling natural language task management with Claude
bigscience-workshop
Toolkit for creating, sharing and using natural language prompts.
Mistral Finetune is an open-source library for fine-tuning Mistral AI models, providing efficient training pipelines with LoRA, QLoRA, and full fine-tuning support, along with data preparation and evaluation tools.
srush
A tiny library for coding with large language models.
neurocult
🕵️♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach.
whylabs
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance m
Dicklesworthstone
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
vaibkumr
Minimize LLM token complexity to save API costs and model computations.
aymenfurter
Agents Capable of Self-Editing Their Prompts / Python Code
BlackHC
Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types
datastax
Drop in replacement for the OpenAI Assistants API
pleisto
Production-Ready LLM Agent SDK for Every Developer
Mindinventory
MindSQL: A Python Text-to-SQL RAG Library simplifying database interactions. Seamlessly integrates with PostgreSQL, MySQL, SQLite, Snowflake, and BigQuery. Powered by GPT-4 and Llama 2, it enables nat
tjmlabs
The easiest, and fastest way to run AI-generated Python code safely
LangFair is a Python library for conducting use-case level LLM bias and fairness assessments
sullyo
Prompt2UI is an experimental tool that generates UI components from natural language prompts, enabling rapid prototyping of user interfaces by describing desired functionality and layout in conversational text.