Hermes Agent
A persistent, extensible agent with skills, plugins, memory, scheduled jobs, messaging integrations, and local or hosted model support.
By Nous Research · reviewed 2026-10-21
What Hermes Agent does
Hermes Agent is Nous Research's open-source agent runtime for terminal, messaging, API, and automation workflows. It supports persistent sessions, skills and plugins, scheduled work, browser and workspace tools, and multiple model providers. Its flexibility is useful for personal automation, but permissions and model quality still determine reliability and risk.
Pricing model
Free and open source; model and tool-provider costs may apply
Position in the stack
Where Hermes Agent fits
Hermes Agent is a persistent agent runtime and interface layer. It combines sessions, memory, plugins, tools, messaging, scheduled jobs, and an optional API while delegating inference to configured providers.
Typical deployment flow
A practical sequence for evaluating Hermes Agent before making it part of a permanent stack.
- STEP 1
Install and initialize
Use the official installer and create an isolated workspace.
- STEP 2
Configure model and tools
Select a capable provider, then enable only required plugins and permissions.
- STEP 3
Verify persistence
Test recovery, scheduled jobs, updates, logging, and backups before unattended use.
Best for
- A customizable personal agent with persistent sessions
- Building skills and plugins around agent workflows
- Running one agent through terminal, API, and messaging interfaces
Not the right layer for
- Turnkey enterprise access control
- Direct model inference without a provider or local runtime
Capabilities
Capabilities refer to the tool's application layer. Hardware and model support can still depend on a connected inference engine.
Deployment and compatibility
- Deployment
- Desktop / localSelf-hosted
- Platforms
- macOS · Windows · Linux
- Hardware backends
- Uses connected model provider
- Install methods
- Installer · Python package · Docker · Build from source
Models and integrations
- Model formats
- Uses connected local or hosted model provider
- Common integrations
- Hermes pluginsMessaging platformsOpenAI-compatible APIsOllamaBrowser toolsLocal workspace
Strengths
- MIT-licensed and actively developed
- Broad provider and plugin architecture
- Persistent automation and messaging workflows
Limitations
- Depends on a separate model provider
- Tool permissions and rapid release cadence require operational discipline
Planning checklist
Before you choose Hermes Agent
Answer these questions with the exact models, hardware, users, and data you expect to operate.
- Which model will power tool use?
- Which plugins are required?
- What actions need explicit approval?
- Can release and plugin versions be pinned?
Hermes Agent FAQ
Can Hermes Agent use local models?
Yes, through supported local or OpenAI-compatible providers, subject to model capability.
Does it include a model?
No. A model provider is a separate dependency.
Can it expose an API?
Yes. Its gateway can expose an OpenAI-compatible endpoint for agent-backed requests.
Official sources
Use these links to confirm current compatibility and installation requirements.
Related tools
A desktop and self-hosted workspace for document chat, RAG, and AI agents.
A node-based workflow engine and interface for local generative image and media models.
An open-source, plugin-first agent harness with local Web UI, tools, sessions, approvals, and extensible model adapters.
Comparisons featuring Hermes Agent
Use a reviewed comparison when the choice is between two adjacent tools.
Execution evidence
Known working recipes using Hermes Agent
Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.
No verified recipe is linked to this record yet.
Compatibility estimates remain available in the planner. A recipe appears here only after its exact stack and verification protocol are documented.