Awesome Infra for AI › Workflow Orchestration for AI

apache/burr

⭐ 2566 Python repository created 2024-01-29

Apache Burr is an incubating Apache project designed to facilitate the development and operation of stateful AI applications, such as chatbots, AI agents, and simulations. It enables developers to express application logic as a state machine (graph/flowchart) using simple Python building blocks, which is particularly useful for managing complex decisions, tracking state, and incorporating human feedback. The framework is designed to be agnostic to specific LLMs or other AI frameworks, allowing integration with various preferred tools. Key features include a lightweight Python library for state machine management, a built-in UI for real-time execution telemetry, introspection, and debugging, and a set of integrations for state persistence and connection to observability tools. Burr focuses on the operational aspects of AI applications, helping to tie together different components and ensure traceability, rather than dictating model building or API querying. It provides examples for various use cases, including RAG-based chatbots and interactive assistants, and aims to scale with evolving application needs.

https://github.com/apache/burr

AI agentsLLM applicationsstate managementworkflow orchestrationobservabilitytracingchat applications

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.