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
parcadei/Continuous-Claude
Continuous Claude is an advanced development environment built upon Anthropics Claude Code, designed to address the inherent context compaction problems faced by large language models. This system transforms Claude Code into a continuously learning and persistent entity that retains context across sessions, enabling more sophisticated and prolonged development workflows. It achieves this by employing strategies like YAML handoffs for token-efficient state transfer, a robust memory system that extracts and recalls learnings, and a five-layer code analysis engine with a semantic index to avoid token waste when reading large files. The project emphasizes 'compounding' intelligence, where each interaction makes the system smarter. It features a comprehensive skill activation system that allows users to interact with Claude using natural language, dynamically suggesting and activating relevant skills, agents, and workflows based on the user's intent and priority levels (Critical, Recommended, Suggested, Optional). This reduces cognitive load and makes the system highly discoverable. The architecture includes 32 specialized agents, 109 skills, and 30 hooks, all designed to optimize Claude's problem-solving capabilities by orchestrating complex tasks and preventing prompt/tool clashes. Design principles prioritize anti-complexity, aiming for a system that learns and recovers from failures rather than relying on an ever-growing sprawl of plugins. Installation is streamlined with a comprehensive wizard that handles prerequisites, database setup, and integration of various modules like math features and TLDR code analysis. It provides robust uninstallation and backup mechanisms to ensure user data safety.
https://github.com/parcadei/Continuous-Claude
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 ...