ComposioHQ/composio
Composio provides SDKs for building AI agents capable of interacting with over 1000 tools, offering capabilities like tool search, context management, and authentication across various AI frameworks.
Awesome Infra for AI › Workflow Orchestration for AI
hanyeol/model-compose
model-compose lets developers define an AI service, such as a chat API, a RAG pipeline, an autonomous ReAct agent, or an MCP server, in a single YAML file and deploy the same file locally, in Docker, or in production without writing application code, in the spirit of docker-compose. A component block wires up models (OpenAI, Anthropic, Google, xAI, HuggingFace, vLLM or local llama.cpp), vector and graph stores (Chroma, Milvus, Qdrant, FAISS, Neo4j, ArangoDB, Redis), HTTP/WebSocket clients, shell commands and browser automation, while a workflow block chains components into multi-step jobs; a controller block exposes the workflow over an HTTP server, a Gradio web UI, or, by changing one adapter type, an MCP server that Claude, ChatGPT or Cursor can call directly. Streaming is a first-class concept across every stage, so tokens, audio chunks and video frames can flow through a workflow rather than only appearing in a final response. The same configuration scales from local development, with an included web UI for iteration, to a containerized deployment by adding a runtime block, to horizontal scaling by adding a Redis-backed job queue that lets additional subscriber processes pick up work with no shared filesystem. Over 90 built-in components cover model providers, model tasks like embedding and TTS, media processing, live broadcasting and web automation, with runnable examples for agents, RAG assistants and MCP servers. It targets developers who want to compose and redeploy AI systems across providers and runtimes without being locked into a single vendor's SDK or a heavyweight orchestration framework.
https://github.com/hanyeol/model-compose
Also in Workflow Orchestration for AI
TencentCloud/TencentDB-Agent-Memory
TencentDB Agent Memory is a memory management system for AI agents, featuring a 4-tier progressive pipeline to improve efficiency and reasoning by categorizing and condensing agent memories without...
TransformerOptimus/SuperAGI
SuperAGI is an open-source framework designed for building, managing, and running autonomous AI agents, offering tools for deployment, capability extension, and performance monitoring.
dataelement/bisheng
BISHENG is an open LLM application DevOps platform focusing on enterprise scenarios, providing comprehensive features for GenAI workflows, RAG, agents, model management, evaluation, and enterprise-...
iflytek/astron-agent
Astron Agent is an enterprise-grade platform for building, orchestrating, and deploying AI agent applications with integrated RPA, model management, and high-availability features.
0xPlaygrounds/rig
Rig is a Rust library designed for building modular and scalable LLM-powered applications, offering a unified interface for multiple model providers and vector stores.
plastic-labs/honcho
Honcho is a memory infrastructure for building stateful AI agents, enabling them to understand and retain information about people, agents, groups, projects, and ideas over time.
julep-ai/julep
Julep is an open-source platform for building, orchestrating, and self-hosting agent-based AI workflows with persistent memory and tool integration.