DeepDiagram uses a streaming XML tag output pattern with LangGraph multi-agent orchestration to transform natural language into diagrams in real-time. It features React 19 + FastAPI and supports multimodal inputs.
Explore a curated marketplace of 14 Python plugins that extend Claude Code through multi-agent orchestration, hook-based workflows, and integrations. Modular, standalone, and easy to install.
opencode-power-pack translates Anthropic’s Claude Code plugins into OpenCode SKILL.md files, enabling multi-agent AI coding workflows across platforms. Here’s how it works under the hood.
ECC is a performance optimization system for AI coding agents, now evolving into a Rust-based orchestration runtime managing 60 agents and 232 skills across 12 languages.
Explore Google Cloud AI’s Agent Platform, a full-stack solution spanning foundation models, development kits, open protocols, and governance for enterprise AI agents.
PicoAgents is a Python multi-agent framework built from scratch, offering transparent agent orchestration, LLM provider abstraction, streaming UI, and production-ready benchmarks.
Kodo is a Python multi-agent orchestration layer coordinating AI coding agents via a plain API orchestrator, improving autonomous coding accuracy by 24% over single-agent setups.
LuaN1aoAgent uses a P-E-R multi-agent framework and causal graph reasoning to achieve 90.4% autonomous success on penetration tests with low exploit cost. Key for AI-driven pentesting.
A curated and frequently updated bibliography accompanying the IJCAI 2024 survey paper on LLM-based multi-agent systems, organizing research into five key categories and revealing emerging trends.
oh-my-product extends Google’s Gemini CLI with multi-agent orchestration using tmux and slash commands for parallel AI workflows, offering persistent state and lifecycle controls.
OpenAgents hosts three specialized LLM agents—Data, Plugins, Web—via a Flask API and Next.js UI, integrating sandboxed code execution, plugin selection, and browser automation.
OpenAgentsControl enforces plan-first, approval-gated AI code generation using a multi-agent pipeline and context-aware pattern loading to produce consistent, project-specific code across TypeScript, Python, Go, and Rust.
OptiLLM is an OpenAI-compatible inference proxy that boosts LLM reasoning with 20+ techniques like Mixture of Agents and MCTS, requiring no model retraining. Use a simple prefix to improve accuracy 2-10x.
pentest-agents deploys 50 specialized AI agents across 7 coding tools with a multi-IDE portability layer, autonomous exploit chains, endpoint brain, and MCP servers for bug bounty hunting.
pm-claude-skills is a large open-source library of 135 markdown skills for Claude AI, spanning 16 professions and multi-agent templates with data connectors for automated workflows.
This repo reverse-engineers Claude Code’s AI coding agent prompts into reusable templates covering safety, tool routing, multi-agent coordination, and memory management for practical prompt engineering.
Claude Code From Scratch distills Anthropic’s 500K+ line coding agent into ~8,000 lines of Python and TypeScript, revealing core architecture like the Agent Loop, semantic memory, multi-agent skills, and context compression.
Goal-Driven offers a prompt-based master-subagent architecture to sustain long-running AI problem-solving sessions through a verification-driven orchestration loop without code or frameworks.
Kiln implements a 7-step multi-agent AI pipeline entirely through markdown files and Claude Code’s native primitives, avoiding any runtime or package dependencies.
Orca is a cross-platform IDE that runs multiple AI coding agents in isolated Git worktrees, enabling parallel development without branch conflicts. Subscription-agnostic and feature-rich.
