RightNow-AI/openfang
OpenFang is an open-source agent operating system, built in Rust, designed to facilitate the management and orchestration of AI agents.
Awesome AI Agents › AI Agent Operating System
langchain-ai/langserve
LangServe is a developer-focused library designed to facilitate the deployment of LangChain runnables and chains as REST APIs. It integrates seamlessly with FastAPI and uses Pydantic for robust data validation, ensuring that input and output schemas are automatically inferred and enforced with detailed error messages. This makes it easier for developers to expose their LangChain objects as web services with minimal effort. The project offers a variety of efficient API endpoints such as /invoke, /batch, and /stream, which support concurrent requests, as well as specialized endpoints like /stream_log and /stream_events for streaming intermediate steps and events from chains or agents. LangServe also includes a user-friendly playground page for interactive testing and debugging. It supports built-in optional tracing to LangSmith, enhancing observability and debugging capabilities. The client SDK allows calling a LangServe server as if it were a local Runnable, simplifying integration. While LangServe is primarily aimed at deploying simple Runnables and well-known LangChain primitives, it is recommended to use the LangGraph Platform for new projects or more complex deployments. The project is built on battle-tested open-source Python libraries such as FastAPI, Pydantic, uvloop, and asyncio, ensuring performance and reliability. It also provides a JavaScript client through LangChain.js for frontend integration. The repository includes comprehensive examples demonstrating usage with LLMs, retrievers, conversational retrievers, and agents, showcasing its versatility. Installation is straightforward via pip, and the LangChain CLI tool helps bootstrap LangServe projects quickly. The project maintains security by addressing vulnerabilities promptly and provides clear documentation and migration guides. Overall, LangServe is a powerful tool for developers looking to deploy LangChain-based applications as scalable, validated REST APIs with rich features and developer-friendly tooling.
https://github.com/langchain-ai/langserve
Also in AI Agent Operating System
Arindam200/awesome-ai-apps
A comprehensive repository showcasing practical examples, tutorials, and tools for building powerful AI applications using large language models and various AI agent frameworks.
OpenByteInc/QuantDinger
QuantDinger is an open-source AI trading operating system designed for independent traders, Python strategy authors, and small teams, offering backtesting, live trading, and multi-agent research ca...
MemTensor/MemOS
MemOS is an operating system for Large Language Models that enhances their capabilities with long-term memory, enabling more context-aware, consistent, and personalized AI interactions through a modular and extensible memory architecture.
holaboss-ai/holaOS
HolaOS is a local-first, AI-powered desktop agent that learns your work context, integrates with over 100 workplace tools, and manages memory efficiently to provide proactive assistance without for...
mcp-use/mcp-use
mcp-use is an open-source unified client library that enables seamless integration of any LangChain-supported LLM with MCP servers to build custom agents with tool access.
astrid-runtime/astrid
Astrid is a portable, capability-secure operating system for composable software components, providing an OS-grade boundary for AI agents and other untrusted code via WebAssembly capsules.
HKUDS/AutoAgent
AutoAgent is a fully-automated, zero-code framework for creating and deploying LLM agents using natural language, featuring top GAIA benchmark performance and broad LLM support.