LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Repository Index
47,133 repositories indexed
25–48 of 298 · Most stars
7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
- llamacpp
- localai
- self-hosted
- gpt
免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！
🦍 The API and AI Gateway
- api-gateway
- microservices
- api-management
- serverless
The repository host gives no description.
AirLLM 2.8T LLM inference with single 4GB GPU
- chinese-nlp
- finetune
- generative-ai
- instruct-gpt
Official inference framework for 1-bit LLMs
An AI prompt optimizer for writing better prompts and getting better AI results.
- llm
- prompt
- prompt-engineering
- prompt-optimization
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
- knowledge-graph
- large-language-models
- retrieval-augmented-generation
- genai
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- abliteration
- llm
- transformer
- censorship-resistance
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
TranslatedLangchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
- chatglm
- langchain
- llm
- knowledge-base
Hundreds of models & providers. One command to find what runs on your hardware.
- llm
- skill
- localai
- gguf
SGLang is a high-performance serving framework for large language models and multimodal models.
Vane is an AI-powered answering engine.
- ai-search-engine
- search-engine
- open-source-ai-search-engine
- perplexica
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
- semantic-search
- emacs
- obsidian-md
- chat
TranslatedLLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI. Supports mainstream models such as OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, 字节豆包 (Doubao, "bean bun", from ByteDance), ChatGLM, 文心一言 (Wenxin Yiyan, "literary heart, one utterance"), 讯飞星火 (Xunfei Xinghuo, "iFlytek Spark"), 通义千问 (Tongyi Qianwen, "Tongyi thousand questions"), 360 智脑 (360 Zhinao, "360 smart brain") and 腾讯混元 (Tencent Hunyuan, "primordial chaos"), with unified API adaptation, usable for key management and secondary distribution. One-click deployment, ready to use out of the box.
🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
A modular graph-based Retrieval-Augmented Generation (RAG) system
LLM Frontend for Power Users.