LLM相关开源项目

1. 模型管理

fastchat GitHub - lm-sys/FastChat: An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

generate GitHub - wangyuxinwhy/generate: A Python Package to Access World-Class Generative Models

模型部署

​​​​​​GitHub - mudler/LocalAI: :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.

模型微调

GitHub - hiyouga/LLaMA-Factory: Unify Efficient Fine-tuning of 100+ LLMs

强化学习

GitHub - lucidrains/toolformer-pytorch: Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

2. 知识管理

GitHub - FlagOpen/FlagEmbedding: Retrieval and Retrieval-augmented LLMs

GitHub - chroma-core/chroma: the AI-native open-source embedding database

GitHub - jina-ai/clip-as-service: 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

GitHub - facebookresearch/ImageBind: ImageBind One Embedding Space to Bind Them All

3. 文档管理

GitHub - paperless-ngx/paperless-ngx: A community-supported supercharged version of paperless: scan, index and archive all your physical documents

GitHub - Layout-Parser/layout-parser: A Unified Toolkit for Deep Learning Based Document Image Analysis

4. 知识库

GitHub - neuml/txtai: 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

GitHub - infiniflow/infinity: The AI-native database built for LLM applications, providing incredibly fast full-text and vector search

GitHub - vanna-ai/vanna: 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

GitHub - Mintplex-Labs/anything-llm: A multi-user ChatGPT for any LLMs and vector database. Unlimited documents, messages, and storage in one privacy-focused app. Now available as a desktop application!

GitHub - Sinaptik-AI/pandas-ai: Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

5. Agent框架

GitHub - reworkd/AgentGPT: 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

GitHub - geekan/MetaGPT: 🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

GitHub - OpenBMB/AgentVerse: 🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

GitHub - microsoft/autogen: A programming framework for agentic AI. Join our Discord: https://discord.gg/pAbnFJrkgZ

GitHub - Forethought-Technologies/AutoChain: AutoChain: Build lightweight, extensible, and testable LLM Agents

GitHub - TransformerOptimus/SuperAGI: <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

6. ASR+TTS

GitHub - alibaba-damo-academy/FunASR: A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.

GitHub - coqui-ai/TTS: 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

GitHub - babysor/MockingBird: 🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time

GitHub - CorentinJ/Real-Time-Voice-Cloning: Clone a voice in 5 seconds to generate arbitrary speech in real-time

GitHub - myshell-ai/OpenVoice: Instant voice cloning by MyShell.

7. 流程、节点可视化

GitHub - comfyanonymous/ComfyUI: The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

GitHub - jagenjo/litegraph.js: A graph node engine and editor written in Javascript similar to PD or UDK Blueprints, comes with its own editor in HTML5 Canvas2D. The engine can run client side or server side using Node. It allows to export graphs as JSONs to be included in applications independently.

GitHub - thedmd/imgui-node-editor: Node Editor built using Dear ImGui

GitHub - paceholder/nodeeditor: Qt Node Editor. Dataflow programming framework

8. 大模型测试、评估

GitHub - microsoft/promptflow: Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

GitHub - Giskard-AI/giskard: 🐢 Evaluation, testing & monitoring framework for LLMs and ML models

GitHub - ianarawjo/ChainForge: An open-source visual programming environment for battle-testing prompts to LLMs.

GitHub - promptfoo/promptfoo: Test your prompts, models, RAGs. Evaluate and compare LLM outputs, catch regressions, and improve prompt quality. LLM evals for OpenAI/Azure GPT, Anthropic Claude, VertexAI Gemini, Ollama, Local & private models like Mistral/Mixtral/Llama with CI/CD

GitHub - hegelai/prompttools: Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).

GitHub - Forethought-Technologies/AutoChain: AutoChain: Build lightweight, extensible, and testable LLM Agents