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
wecode-ai/Wegent
Wegent is an open-source, self-hostable platform for building and operating teams of AI agents that perform work across chat, coding, knowledge retrieval and scheduled automation. Its model is compositional: models, knowledge bases, tools and skills are configured once and then combined into agents, and multiple bots can be organised so that research, analysis, coding and review are divided between them. The system has two halves. Wegent Web is the shared control plane where a team creates and shares agents, models, knowledge bases and automations, manages users, permissions and execution devices, and reaches agents through the browser, HTTP APIs, MCP or instant-messaging bots. Wework is a companion macOS desktop application that opens a local project and lets an agent use files, terminals, CLIs and development environments directly, including local Codex and locally hosted models; it can connect to a team Wegent deployment to reuse shared models, cloud devices and remote tasks. Documented scenarios include private team assistants with group collaboration and file handling, AI coding that edits code, runs tests, commits and opens pull requests in isolated or local environments, knowledge assistants that parse and index documents, webpages and enterprise data for grounded answers, continuous automation driven by schedules and events, and execution inside private networks where the code or data cannot leave. Tasks can be placed on cloud infrastructure, in containers, on local devices or in private environments depending on where the relevant data lives. Wework surfaces a live tool-activity timeline while a task runs, with expandable command output, search details and file changes, collapsing into a summary once the final answer begins. Deployment is a single Docker container backed by SQLite via an install script, with a wegent-standalone helper command for status, logs and restarts.
https://github.com/wecode-ai/Wegent
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.