A team managing client communication across Slack, Telegram, and email runs three separate agent setups. Each has its own configuration. Skills learned on Slack do not carry to Telegram. An update to one does not affect the others. Three deployments, three maintenance burdens, no shared memory. Hermes is built to solve exactly this: one agent instance that runs across all connected platforms, builds skills from every task it completes, and gets more capable over time — not just on one platform, but across all of them.
What is Hermes?
Hermes is a self-improving AI agent built by Nous Research, the AI research lab focused on open-weight foundation models and agent architectures.¹ Hermes runs across 20+ messaging and collaboration platforms — including Slack, Telegram, Discord, WhatsApp, Microsoft Teams, and Gmail — from a single deployment.
The core distinction from other agents is how Hermes handles experience. Nous Research describes it as "an intelligent personal assistant that gets more capable the longer it runs" — not through manual retraining, but by creating reusable skills from tasks it completes.²
Hermes is not a coding copilot, not a chatbot wrapper around a single API, and not a platform-specific tool. It is a general-purpose agent that improves as it works.
How does Hermes learn?
Hermes creates skills from completed tasks. When Hermes finishes a task — drafting a client update, triaging a support queue, pulling a weekly report — it stores the approach as a Skill object: code, tests, and examples that define how to handle that task category in the future.³
Skills are stored at agentskills.io, an open standard for agent skill exchange. Skills can be reused across instances, shared between teams, and improved through use. The registry is compatible with other agent systems, including Cursor, GitHub Copilot, and Claude Code.
Hermes does not require manual retraining when workflows change. Skills update from experience — each completed task is an opportunity for the agent to encode a better approach for the next time.
The practical effect: a Hermes instance handling client follow-up for a recruiting agency in month three will handle more edge cases correctly than it did in month one — because it has accumulated skills from every follow-up task it has completed.
Where does Hermes run?
Hermes runs across 20+ platforms from a single instance. Supported platforms include Slack, Telegram, Discord, WhatsApp, Microsoft Teams, Gmail, Signal, IRC, and others.² A single Hermes deployment covers the entire communication stack — not a different agent for each platform.
Hermes integrates with 70+ tools: task managers (Linear, Asana, Jira), knowledge bases (Notion, Confluence), development tools (GitHub), and calendar and email systems. The agent can read from and write to these tools as part of its task execution.
Most agents stay fixed after deployment. Hermes gets more capable every time it works.
Hermes is self-hosted under an MIT licence. Teams deploy it on their own infrastructure — no data sent to a third-party agent service. Configuration is managed through a standard setup process, and the same instance handles all platforms once deployed.
What is Hermes built for?
Hermes suits teams managing high-volume communication across multiple platforms, where agent capability needs to improve over time rather than stay fixed.
Recruiting agencies use Hermes to coordinate candidate communication across Slack (internal) and Gmail (external), with skills building from every candidate interaction. HR consultancies use Hermes to manage client reporting workflows across Notion and email. Fractional CFO practices use Hermes to handle client update requests that arrive via Slack, Teams, and email simultaneously.
The common thread: workflows that span multiple platforms, repeat at volume, and benefit from the agent getting better at them as it accumulates experience. Off-the-shelf static agents and rule-based automations cannot improve themselves — Hermes is built for the teams that need an agent that does.
For teams whose workflows don't map to Hermes's defaults, a custom agent is the alternative. For a broader understanding of what agents do, see what is an AI agent.
Frequently asked questions
What is Hermes? Hermes is a self-improving AI agent built by Nous Research. It runs across 20+ platforms — Slack, Telegram, Discord, WhatsApp, Teams, Gmail — from a single deployment, and builds reusable skills from tasks it completes, becoming more capable the longer it operates.
How does Hermes learn new skills? Hermes creates a Skill object after completing each task — code, tests, and examples that define how to handle that task category in the future. Skills are stored at agentskills.io and reused automatically the next time a similar task appears. No manual retraining is required.
What platforms does Hermes run on? Hermes runs on 20+ platforms including Slack, Telegram, Discord, WhatsApp, Microsoft Teams, Gmail, and Signal. A single Hermes deployment handles all connected platforms simultaneously, with shared skills and context across channels.
Who built Hermes? Hermes was built by Nous Research, an AI research organisation focused on open-weight foundation models and agent architectures. Hermes is released under an MIT licence and is self-hosted.
Notes
- Nous Research, company overview. https://nousresearch.com
- Nous Research, Hermes documentation. https://hermes-agent.nousresearch.com/docs/
- agentskills.io, open standard for agent skills. https://agentskills.io