ToolAI.io · Kênh GitHub

Các dự án AI nổi bật trên GitHub

Theo dõi các kho lưu trữ AI mã nguồn mở đang hoạt động trong các chủ đề LLM, tác nhân, MCP, RAG và lập trình, kèm số sao và thông tin dự án đã xác minh.

Dữ liệu kho lưu trữ công khai

Mục lục dự án

75 Dự án
Ảnh chụp màn hình của Hugging Face Transformers
Suy luận, Triển khai & Thời gian chạy

Hugging Face Transformers

huggingface/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⑂ 34,1KPython
Apache-2.0Q98
Ảnh chụp màn hình của CSGHub: Open-Source LLM Asset Management Platform
Tác nhân & Đa tác nhân

CSGHub: Open-Source LLM Asset Management Platform

opencsgs/csghub

CSGHub is an open-source, on-premise platform for managing the full lifecycle of Large Language Model assets, including models, datasets, spaces, and code, offering functionality comparable to a private Hugging Face.

★ 4,2K⑂ 525Vue
Apache-2.0Q98
Ảnh chụp màn hình của Lemonade: Local AI Server for GPU and NPU Inference
MCP & Gọi công cụ

Lemonade: Local AI Server for GPU and NPU Inference

lemonade-sdk/lemonade

Lemonade is an open-source local AI server that enables users to run optimized Large Language Models (LLMs), speech, and image generation models directly on their own GPUs and NPUs, providing a free and private alternative to cloud APIs.

★ 5,2K⑂ 436C++
Apache-2.0Q98
Ảnh chụp màn hình của Graphiti: Build Temporal Context Graphs for AI Agents
Tác nhân & Đa tác nhân

Graphiti: Build Temporal Context Graphs for AI Agents

getzep/graphiti

Graphiti is an open-source Python framework by Zep for building and querying temporal context graphs. It autonomously transforms structured and unstructured data into a dynamic knowledge graph that tracks fact validity over time, preserving provenance and enabling hybrid retrieval for AI agents.

★ 29,5K⑂ 3KPython
Apache-2.0Q98
Tác nhân & Đa tác nhân

Opik: Open-Source LLM Observability, Evaluation and Agent Tracing

comet-ml/opik

Opik is an Apache-2.0-licensed platform for tracing, evaluating, debugging and monitoring LLM applications, RAG systems and multi-step agent workflows. It supports self-hosting, a hosted Comet.com option, client SDKs, a REST API, automated evaluations, prompt experimentation and production dashboards.

★ 21,1K⑂ 1,7KPython
Apache-2.0Q98
Tác nhân & Đa tác nhân

RAGFlow

infiniflow/ragflow

RAGFlow is an open-source Retrieval-Augmented Generation engine that combines document ingestion, retrieval, grounded citations, configurable language and embedding models, and agent capabilities to provide context for LLM applications.

★ 86,7K⑂ 10,2KGo
Apache-2.0Q98
Suy luận, Triển khai & Thời gian chạy

Mooncake: KVCache-Centric Infrastructure for Distributed LLM Serving

kvcache-ai/mooncake

Mooncake is a C++ infrastructure project for large-scale LLM inference and training. It separates prefill, decode, and storage resources while providing high-performance transfer, distributed KV-cache storage, and fault-tolerant expert-parallel communication.

★ 6,1K⑂ 1KC++
Apache-2.0Q98
Tác nhân & Đa tác nhân

MLflow

mlflow/mlflow

An open-source AI engineering platform for tracing, evaluating, monitoring, optimizing, governing, and deploying agents, LLM applications, and machine-learning models.

★ 27,3K⑂ 6,1KPython
Apache-2.0Q98
Tinh chỉnh, huấn luyện & dữ liệu

Langfuse

langfuse/langfuse

An open-source LLM engineering platform for tracing, evaluating, debugging, and improving AI applications, with prompt management, datasets, metrics, a playground, APIs, and managed or self-hosted deployment options.

★ 32,4K⑂ 3,5KTypeScript
NOASSERTIONQ98
Suy luận, Triển khai & Thời gian chạy

llm-d: Distributed LLM Inference on Kubernetes

llm-d/llm-d

llm-d is an open-source serving stack that adds distributed orchestration, routing, cache management, autoscaling, and batch processing around model servers such as vLLM and SGLang. It targets high-scale production inference on Kubernetes and modern hardware accelerators.

★ 4K⑂ 649Shell
Apache-2.0Q98
Tác nhân & Đa tác nhân

OpenCodeReview

alibaba/open-code-review

An open-source AI code review CLI from Alibaba that combines deterministic review pipelines with an LLM agent to produce structured, line-level feedback.

★ 18K⑂ 1,2KGo
Apache-2.0Q98

Trang 5 / 7 · 75 dự án

Đã cập nhật gần đây

qwen-code — Command-line coding agentQwenLM/qwen-code★ 27,1K SBproxysoapbucket/sbproxy★ 49 XERJxerj-org/xerj★ 1,4K PwrAgentpwrdrvr/pwragent★ 29 OpenGenicloudgeni-ai/opengeni★ 56 NemoClaw — Agent runtime and deployment toolingNVIDIA/NemoClaw★ 22,2K

Được gắn sao nhiều nhất

Hermes Agentnousresearch/hermes-agent★ 227,1K markitdown — Document conversion and extractionmicrosoft/markitdown★ 174,3K skills — Reusable agent skills and workflowsanthropics/skills★ 170,1K Hugging Face Transformershuggingface/transformers★ 163,3K Firecrawlfirecrawl/firecrawl★ 161,1K LangChainlangchain-ai/langchain★ 143,6K