A cleaner path through the Hermes world: the core runtime, the operator surfaces, the integrations that make it strange, and the patterns worth borrowing.
These three explain the center of gravity fastest: the runtime itself, the official docs, and the skills layer that makes the ecosystem portable.
The core project. Self-improving AI agent with a closed learning loop, multi-platform gateway (Telegram, Discord, Slack, WhatsApp, Signal, Feishu/Lark, WeCom), six terminal backends, cron scheduling, MCP integration, profiles (multi-instance), and fallback providers. 23k+ stars. Includes automatic migration from OpenClaw.
Why check it out: This is the product worldview everything else orbits around.
Comprehensive docs covering quickstart, CLI, configuration, messaging gateway, security, tools, skills, memory, MCP, cron, ACP, API server, and architecture.
Why check it out: The docs are the shortest route to understanding memory, gateways, skills, and deployment patterns correctly.
The open standard for agent skills. Compatible across Hermes, Claude Code, Cursor, Codex, and other agents.
Why check it out: Skills explain why Hermes feels more like a capability system than a prompt library.
These are the projects that most directly improve everyday operating experience once you actually start running Hermes.
Web-based workspace with chat, terminal, memory browser, skills manager, and inspector. The most complete GUI for Hermes. Built during the Nous Hackathon 2026.
Why check it out: A visual workspace is one of the most immediately useful additions around a live Hermes instance.
Turn your Obsidian vault into an identity layer any AI agent can read in under 30 seconds
Why check it out: Packaging personal tools as a reusable Hermes skill is a very practical pattern.
Plugin that intercepts shell commands via pretoolcall and rewrites output through RTK, compressing terminal output before it reaches the LLM context window. 60-90% token reduction on shell commands, 96.6% efficiency across 11M+ tokens processed. Zero config — auto-loads on gateway boot. Real benchmarks: cargo test 90-99%, git log --stat 87%, ls -la 78%.
Why check it out: Context compression at the terminal layer is a concrete fix for long-session pain.
These point toward the branch where Hermes stops being a single agent and starts acting like part of a broader operating system.
Open-source dashboard for AI agent orchestration. Manage agent fleets, dispatch tasks, track costs, and coordinate multi-agent workflows. Self-hosted, SQLite-powered. 3.7k+ stars.
Why check it out: This is the clearest multi-agent coordination surface in the set.
Skill giving agents access to 300+ premium APIs and a wallet balance to pay for them through x402 or MPP. A fresh Hermes install with only AgentCash is actually powerful — from web scraping to image generation to email sending, all through one skill with free USDC for trying out.
Why check it out: Giving agents access to paid APIs and wallet-style capabilities pushes the ecosystem into more autonomous territory.
Community migration tool from OpenClaw to Hermes. Built when the native hermes-migrate had critical bugs. For Hermes v0.3.0+, prefer the native hermes claw migrate command — it now covers the full migration path.
Why check it out: Bridge projects show how Hermes gets pulled into larger heterogeneous agent stacks.
These are the projects that best show the ecosystem getting delightfully specific or unconventional.
Solana blockchain intelligence MCP server. Provides on-chain analytics and wallet data to Hermes via MCP.
Why check it out: A blockchain-intelligence MCP surface is exactly the kind of niche branch that reveals ecosystem elasticity.
Lightweight process monitoring and configuration dashboard. Simpler alternative to hermes-workspace, focused on ops.
Why check it out: A community web UI shows the demand for very different operator experiences around the same core runtime.
753+ structured cybersecurity skills mapped to MITRE ATT&CK. The most comprehensive security skills collection available. 4k+ stars.
Why check it out: A huge domain pack makes the skills layer feel less like prompts and more like a specialized operating environment.
These are strong reference implementations for patterns that can transfer into other agent systems too.
The open standard for agent skills. Compatible across Hermes, Claude Code, Cursor, Codex, and other agents.
Why check it out: The shared skill-distribution concept is bigger than Hermes itself.
Plugin that intercepts shell commands via pretoolcall and rewrites output through RTK, compressing terminal output before it reaches the LLM context window. 60-90% token reduction on shell commands, 96.6% efficiency across 11M+ tokens processed. Zero config — auto-loads on gateway boot. Real benchmarks: cargo test 90-99%, git log --stat 87%, ls -la 78%.
Why check it out: Context-thinning around tool output is a generally useful agent pattern.
Open-source dashboard for AI agent orchestration. Manage agent fleets, dispatch tasks, track costs, and coordinate multi-agent workflows. Self-hosted, SQLite-powered. 3.7k+ stars.
Why check it out: Operator-facing control planes are increasingly relevant across many agent stacks.