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
christopherkarani/SwiftAgents
Swarm, published from the SwiftAgents repository, is a Swift framework for building LLM agents and composing them into multi-agent workflows on Apple platforms and Linux. Agents are declared with instructions, a configuration and a set of tools; the @Tool macro reads a Swift struct and generates the JSON schema for tool calling at compile time, so argument types are checked by the compiler rather than at run time, and a FunctionTool type covers projects that disable macros. Workflows chain agents as steps and compile to a directed acyclic graph, and Swift 6.2 strict concurrency is enabled across the package so data race safety is enforced statically. Inference has two built-in paths: Apple Foundation Models running on device without an API key on supported hardware, and any OpenAI-compatible remote endpoint, with the agent loop unchanged between them. The package is organised around traits so the default build stays lean, linking only the core and on-device inference, while an Integrations trait pulls in durable workflow checkpointing that allows resuming from a checkpoint after a crash, semantic agent memory backed by a CoreML embedding model downloaded on demand, graph and web helpers, and Membrane adapters. Additional products cover MCP support and OpenTelemetry export. Declarative agent specifications are read from AGENTS.md and reusable skills from SKILL.md files, giving a file-based workspace layout alongside the programmatic API. Installation is through Swift Package Manager, with documented build commands for both the lean and full configurations and a capability showcase executable demonstrating the feature matrix. It is intended for iOS and macOS developers who want agent orchestration expressed in idiomatic Swift, using actors, async streams, result builders and macros, instead of calling into a Python runtime.
https://github.com/christopherkarani/SwiftAgents
Also in Multi-Agent Frameworks
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.
cft0808/edict
Edict is an OpenClaw Multi-Agent Orchestration System featuring 9 specialized AI agents, a real-time dashboard, model configuration, and full audit trails, inspired by ancient Chinese imperial gove...
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.
HKUDS/DeepCode
DeepCode is an open-source project that uses multi-agent AI systems to convert research papers and natural language into production-ready code through both CLI and web interfaces.