Orchestration tools for running multiple Hermes agents together. Fleet management dashboards, swarm coordinators, and multi-agent delegation systems.
A self-hosted orchestration platform that manages multi-agent workflows across frameworks like CrewAI and LangGraph. It features a zero-dependency SQLite backend and the Aegis review system for human-in-the-loop task sign-off.
A TUI and web-based control surface designed for monitoring multiple coding agents in parallel. It utilizes Docker, Podman, and Apple Containers to sandbox agents across git worktrees and multi-repo workspaces.
A control-plane template that scales Hermes agents from single VPS instances to orchestrated specialist teams. It employs task bus patterns to facilitate structured delegation between orchestrators and specialists.
A supervision interface for Hermes agents featuring a Kanban board for tracking autonomous task status. It provides live streaming of agent reasoning and requires human verification for all proposed completions.
A framework for building autonomous agent swarms with durable memory and support for over 23 LLM providers. It includes a visual protocol builder for designing structured multi-agent workflows.
A scaling template that uses a level-based architecture to transition from single agents to automated teams. It bundles specialized skills for security auditing, VPS provisioning, and backup management.
A coordinated system of 17 specialized agents divided across six functional domains. It automates task routing through predefined pipelines and enforces mandatory security and quality gates for all code changes.
A local collaboration system that manages the task lifecycle through Leader and Specialist agents. It integrates MCP and ACP protocols with a real-time Web UI for monitoring dialogues and Kanban flows.
A meta-optimization harness that uses an automated outer-loop search to refine agent code. It orchestrates TBLite and TB2 benchmark evaluations to track performance frontiers via candidate mutation.
An agent-vs-agent arena where autonomous AI companies compete for GitHub stars. It orchestrates nine agents using Paperclip and Hermes Agent, visualizing the competition via a real-time scoreboard.
An ACP-style delegation tool that routes tasks between Hermes subagents, Codex, and Claude Code. It prevents parent context pollution through isolated workflows and enforces safety via configurable timeouts.
A local-first coordination layer that uses an append-only Markdown channel for git-visible audit trails. It offers three distinct autonomy modes—MANUAL, COPILOT, and AUTOPILOT—via a universal adapter.