xcrawl-skills defines standardized AI agent skills with normalized inputs/outputs for web data tasks like scraping and crawling via the XCrawl API. It enables multi-agent orchestration with minimal integration.
TinyAGI is a TypeScript platform for solo operators managing multiple AI agent teams. It uses a SQLite queue with atomic transactions for reliable async task processing and supports multi-channel messaging.
agentic-stack provides a harness-agnostic shared memory layer for AI coding agents, enabling seamless context persistence and migration across tools like Claude Code and Cursor.
ClawSync offers a multi-agent AI platform using Convex backend, with shared soul documents for reusable personalities and per-agent model routing across popular LLMs. Explore its architecture and setup.
llm-wiki is a shell-based orchestration layer that turns LLM agents into a persistent, multi-agent research wiki. Supports up to 10 agents, deep investigations, and durable provenance tracking.
Agent Kanban is a TypeScript multi-agent platform that uses Ed25519 cryptographic identities to manage AI coding agents in a leader-worker workflow with atomic task claiming and real-time collaboration.
AgentOps provides a Go-based local operating layer for AI coding agents, enabling persistent memory, validation gates, and multi-agent review across vendors with zero cloud dependency.
AutoHedge implements a four-agent sequential pipeline for autonomous trading on Solana, using a risk-first design and structured JSON outputs for reliable multi-agent coordination.
A practical 18-step tutorial progressively builds a minimal AI agent into a production-ready multi-agent system with event-driven architecture and concurrency control.
Council of High Intelligence is a Shell tool coordinating 18 AI personas across Claude, OpenAI, Gemini, and Ollama, enforcing true disagreement via structured multi-round deliberations.
anthropics/claude-cookbooks offers Jupyter Notebook recipes demonstrating practical Claude API usage, including sub-agent orchestration, multimodal vision, and RAG patterns.
claude-plugins is a TypeScript-based plugin marketplace for Claude Code, featuring a multi-agent consultant plugin that runs parallel LLMs like GPT-5, Gemini, Grok, Perplexity, and Claude for AI consultation.
llm-wikid uses a CLAUDE.md schema to control a multi-phase ingest pipeline compiling markdown wiki pages for Obsidian, offering better Q&A at scale than RAG. Supports multiple AI agents and quality checks.
A curated catalog of 20+ LLM agent frameworks and tools organized by agent type and capabilities. Understand architectural differences and trade-offs in LLM agent design.
Memex is a Flutter-based local-first personal knowledge app using multi-agent AI to organize and extract insights. It supports custom agents with event-driven triggers and 14+ LLM providers.
MultiWorld offers a unified framework for multi-agent multi-view video world modeling using a frozen VGGT backbone for implicit 3D understanding. It supports scalable multi-agent control and autoregressive inference.
Open Computer Use enables AI agents to control real computers using specialized Browser, Terminal, and Desktop agents running in isolated Docker VMs. It achieves 82% on the OSWorld benchmark.
PAI-OpenCode offers a modular AI infrastructure with 16 specialized agents and smart model routing across 75+ providers, optimizing performance and cost with a minimal 20KB core.
Paper2Agent automates converting research paper codebases into interactive MCP servers for AI coding agents, handling tutorial extraction, tool generation, and test coverage with minimal human input.
