ruvnet/claude-flow
Claude-Flow is an enterprise-grade AI orchestration platform that enables deployment and coordination of intelligent multi-agent swarms and autonomous workflows for building advanced conversational AI systems.
Awesome AI Agents › AI Agent Orchestration
zou-group/avatar
AvaTaR is a cutting-edge framework designed to optimize large language model (LLM) agents for effective tool usage, enhancing their performance on specific tasks or domains. Presented at NeurIPS 2024, this framework introduces a novel approach by incorporating a comparator module that iteratively provides insightful and holistic prompts to the LLM agent. This is achieved through contrastive reasoning, where the agent reasons between positive and negative examples sampled from training data, allowing it to learn optimal strategies for tool utilization. The framework is integrated with DSPy, a toolkit for developing and optimizing LLM agents, making it accessible for practical use. Users can define task signatures and provide a list of tools in the LangChain tool format, enabling the creation of customized agents tailored to their specific question-answering or other task needs. The Avatar module facilitates agent execution, while the AvatarOptimizer module enables the optimization of the agent's behavior using the comparator module. AvaTaR supports various datasets such as STaRK and Flickr-30kEntities for benchmarking and reproducing results. The framework includes scripts for data preparation, optimization, and evaluation, making it straightforward to apply and test. Additionally, it offers a baseline implementation of the ReAct method for comparison. The project emphasizes ease of integration and extensibility, allowing researchers and developers to optimize LLM agents for better tool usage through a systematic and automated process. The detailed documentation, example notebooks, and integration with popular APIs like Google Serper and Arxiv further enhance its usability. AvaTaR represents a significant advancement in the field of LLM agent optimization, focusing on improving the interaction between agents and external tools through contrastive reasoning techniques.
https://github.com/zou-group/avatar
Also in AI Agent Orchestration
code-yeongyu/oh-my-openagent
Oh-My-OpenAgent (OmO) is an advanced AI agent harness designed for complex codebases, orchestrating various AI models like Codex and OpenCode for software engineering tasks.
herdrdev/herdr
Herdr is an agent multiplexer that provides a runtime environment for coding agents directly within your terminal, offering a comprehensive view of agent activities and persistent sessions.
Donchitos/Claude-Code-Game-Studios
Transforms Claude Code into a comprehensive game development studio powered by 49 AI agents, 73 workflow skills, and a hierarchical coordination system for structured game creation.
BloopAI/vibe-kanban
Vibe Kanban is a Kanban board tool designed to manage and orchestrate AI coding agents, enabling efficient task tracking and workflow optimization in AI-assisted software development.
slopus/happy
Happy is an open-source harness orchestrating Claude Code, Codex and Grok sessions from one mobile/desktop app, reusing existing subscriptions, with end-to-end encrypted, multiplayer sessions.
getpaseo/paseo
Paseo is a self-hosted platform that orchestrates multiple coding agents like Claude Code, Codex, and Copilot across desktop and mobile devices, providing a unified interface for parallel execution...
NVIDIA/NemoClaw
NVIDIA NemoClaw is an open-source reference stack enabling the secure and sandboxed operation of AI agents like OpenClaw and Hermes within NVIDIA OpenShell environments, offering managed inference ...