Awesome Infra for AI › Workflow Orchestration for AI

operand/agency

⭐ 490 Python repository created 2023-05-23

Agency is a Python library designed to facilitate the creation of agent-integrated systems using an Actor model. It provides a foundational framework for developing custom agent-based applications by enabling flexible and scalable communication between various entities through an easy-to-use API. In Agency, all communicating entities, including AI-driven agents, software interfaces, and human users, are represented as instances of the `Agent` class. Agents can expose 'actions' that other agents can discover and invoke at runtime, supporting structured inter-agent communication. The framework includes features for performance and scalability, with support for multiprocessing, multithreading, and AMQP for networked agent systems. Observability and control are built-in through action and lifecycle callbacks, access policies, permission callbacks, and detailed logging. Agency offers `LocalSpace` for agents within the same application and `AMQPSpace` for networked agents. Its primary goal is to provide a minimal, yet robust, foundation for developers to experiment with and build custom agent systems, making it suitable for orchestrating AI agents and LLM application workflows in production environments.

https://github.com/operand/agency

actor-modelagentsagiaillmopsworkflow-orchestrationpythonframeworkagentic systemsdistributed systems

Also in Workflow Orchestration for AI

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.

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.