The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

A visual playground for agentic workflows: Iterate over your agents 10x faster

Build and run agents you can see, understand and trust.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

No fortress, purely open ground. OpenManus is Coming.

MS-Agent: a lightweight framework to empower agentic execution of complex tasks

Python scraper based on AI

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

keras implement of transformers for humans

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Embedded property graph database built for speed. Vector search and full-text search built in. Implements Cypher.

A modular graph-based Retrieval-Augmented Generation (RAG) system

LlamaIndex is the leading document agent and OCR platform

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-re…

The agent engineering platform

Locally run an Instruction-Tuned Chat-Style LLM

Making large AI models cheaper, faster and more accessible

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

ChatGLM-6B：开源双语对话语言模型

Deploy headless browsers in Docker. Run on our cloud or bring your own. Free for non-commercial uses.