A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

Modern protocol-side framework based on NTQQ

✨ Agentic IM ChatBot Infrastructure — 聊天智能体基础设施 ✨ 多消息平台集成（QQ / Telegram / 企微 / 飞书 / 钉钉等），强大易用的插件系统，支持 OpenAI / Gemini / Anthropic / Dify / Coze / 阿里云百炼 / 知识库 / Agent 智能体

The HELMET Benchmark

MemVerse: Multimodal Memory for Lifelong Learning Agents

EverMemOS is an open-source, enterprise-grade intelligent memory system. Our mission is to build AI memory that never forgets, making every conversation built on previous understanding.

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex & Gemini CLI.

(WIP) Open Knowledge Layer(OpenKL): The Advance Knowledge and Memory for Personal Agents.

Verify Precision of all Kimi K2 API Vendor

AgentEvolver: Towards Efficient Self-Evolving Agent System

A framework for efficient model inference with omni-modality models

A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.

Public repository for Agent Skills

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

Open-source Next.js template for building apps that are fully generated by AI. By E2B.

An open source implementation of code execution with MCP (Programatic Tool Calling)

Effortless data labeling with AI support from Segment Anything and other awesome models.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

🔥 OneThinker: All-in-one Reasoning Model for Image and Video

Memory infrastructure for LLMs and AI agents

Open Source Metering and Usage Based Billing API ⭐️ Consumption tracking, Subscription management, Pricing iterations, Payment orchestration & Revenue analytics

Tora: Torchtune-LoRA for RL

A modern web interface for managing and interacting with vLLM servers (www.github.com/vllm-project/vllm). Supports both GPU and CPU modes, with special optimizations for macOS Apple Silicon and ent…

An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions con…

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

Easy and Efficient dLLM Fine-Tuning

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

Context Data Platform for Agents. Join the community❤️: https://discord.acontext.io