affaan-m/ECC
ECC is a harness-native operator system designed for agentic AI work, providing a comprehensive solution with skills, memory optimization, security, and research-first development across multiple A...
Awesome AI Agents › Multi-Agent Frameworks
liquidos-ai/AutoAgents
AutoAgents is a modular multi-agent framework written in Rust for building LLM-driven intelligent systems. It combines a type-safe agent model with structured tool calling, configurable memory and pluggable LLM backends, and is designed to run across server and edge targets. Agents are executed by interchangeable executors: a basic executor for single-shot work and a ReAct executor for reasoning-and-acting loops, both supporting streaming responses and structured outputs. Tools are declared with derive macros that generate the schema and dispatch code, and can optionally run inside a sandboxed WebAssembly runtime so untrusted tool code stays isolated. Memory is provided as a sliding-window implementation over an extensible backend trait. The LLM layer puts a single unified interface in front of many providers. Cloud backends include OpenAI, OpenRouter, Anthropic, DeepSeek, xAI, Phind, Groq, Google, Azure OpenAI and MiniMax, with a documented matrix of which ones support chat, streaming, tool calls, structured output and multimodal input. Local inference is available through Ollama, an embedded Mistral-rs runtime and an embedded llama.cpp runtime, with vision models supported where the backend allows it; experimental Burn and ONNX backends live in a separate repository. Around inference the framework adds guardrails for safeguarding model calls and optimization passes such as caching and retry to make pipelines faster and more reliable. For multi-agent work it supplies typed publish/subscribe communication and an environment abstraction that manages the set of running agents. Speech processing with local text-to-speech and speech-to-text is included, and observability is handled through OpenTelemetry tracing and metrics with pluggable exporters. The project publishes crates on crates.io plus Python bindings on PyPI built with maturin, so it targets Rust engineers who want a performance-oriented agent runtime and Python users who want to call it.
https://github.com/liquidos-ai/AutoAgents
Also in Multi-Agent Frameworks
paperclipai/paperclip
Open-source Node.js server and React dashboard that orchestrates teams of AI coding agents (Claude Code, Codex, Cursor, OpenCode and others) with org charts, budgets, goals and audit trails.
ruvnet/ruflo
Ruflo is a leading agent orchestration platform for Claude, enabling the deployment of intelligent multi-agent swarms, coordination of autonomous workflows, and building conversational AI systems.
Yeachan-Heo/oh-my-claude-sisyphus
Oh My Claude Sisyphus (OMC) is a multi-agent orchestration framework for Claude Code, simplifying complex AI agent workflows without a steep learning curve.
microsoft/JARVIS
JARVIS is a collaborative AI system that connects large language models with expert AI models from HuggingFace to autonomously plan, execute, and integrate complex AI tasks.
rowboatlabs/rowboat
Rowboat is an AI-powered platform that enables users to build and manage multi-agent swarms using natural language, integrating tools and knowledge for automated workflows and deployment via API or SDK.
MemoriLabs/Memori
Memori is a versatile SQL native memory layer designed to enhance LLMs, AI agents, and multi-agent systems with advanced memory management, seamless integration, and high performance.
xbtlin/ai-berkshire
AI Berkshire is an investment research framework leveraging AI agents (Claude Code/Codex) to automate value investment analysis, synthesizing methodologies from renowned investors like Buffett and ...