Hermes Agent · Nous Research
Nous Research's MIT-licensed 'self-improving' server-resident agent (Feb 2026, ~211k stars): model-agnostic with persistent cross-session memory, autonomous skill creation compatible with the agentskills.io standard, DSPy/GEPA evolutionary self-optimization, and execution backends from local/Docker to Modal and Daytona.
Identity
| Homepage | https://hermes-agent.org/ |
|---|---|
| Repository | https://github.com/NousResearch/hermes-agent |
| License | open-source |
| Domain | general |
| Form factor | cli · chat-integration |
Model support
| Model-agnostic | ✓ yes |
|---|---|
| Native models | Hermes 4 (default via Nous Portal) |
| Local models | ✓ yes |
| Pricing | byok |
Extensibility
| MCP client | ✓ yes |
|---|---|
| Agent Skills support | ✓ yes |
| Plugins / hooks | ✓ yes |
Execution & safety
| Sandboxing | optional |
|---|---|
| Autonomy spectrum | supervised → semi-autonomous → autonomous-local |
| Subagents | ✓ yes |
| Parallel sessions | ✓ yes |
| Context management | persistent-memory · compaction |
Integration & evidence
| Headless / API | ✓ yes |
|---|---|
| GitHub integration | ? unknown |
| Sources |
✓ profile last verified 2026-07-08 · benchmark figures are vendor-reported unless a source states otherwise