112 results for “memory”
- How to keep Hermes Agent costs downGuide · Models, providers & costWhere Hermes spends tokens, how to measure it, and the documented settings and habits that keep your provider bill predictable.
- How to run Hermes Agent 24/7 on a VPS or home serverGuide · Running & deployingKeep Hermes Agent online around the clock: install the gateway as a service, enable linger or a system service, and lock it down before going public.
- How to run Hermes Agent in DockerGuide · Getting startedHermes Agent has an official Docker image for amd64 and arm64. Run the setup wizard, then start the gateway with your data on a mounted volume.
- How to set up Hermes Agent with Open WebUI and the API serverGuide · Messaging & the gatewayUse Open WebUI with the Hermes API server. Set a strong key, keep loopback private and understand Docker reachability and host tool access.
- How to write your first Hermes Agent skillGuide · Skills, plugins & MCPA step-by-step walkthrough of creating a SKILL.md, where to put it, how Hermes discovers and loads it, and how to keep agent-written skills under review.
- Where Hermes Agent runs: host vs work environmentGuide · Running & deployingDecide where the agent, its tools and its lasting files live before moving a workflow to a server.
- API server: use Hermes from any OpenAI-compatible clientTool & integration · Running & deployingExpose Hermes as an OpenAI-compatible HTTP endpoint so chat frontends and scripts can talk to your agent.
- Subagent delegation: split big jobs across parallel child agentsTool & integration · Automation & schedulingUse the delegate_task tool to hand pieces of work to isolated child agents that run in parallel and report back.
- Terminal backends: choose where the agent's commands runTool & integration · Running & deployingRun the agent's shell commands locally, in Docker, on a remote host over SSH, or in cloud sandboxes like Modal, Daytona and Vercel Sandbox.
- flash-attentionSkill · Skills directorySpeed up long-sequence transformer training and inference.
- openclaw-migrationSkill · Skills directoryImport an OpenClaw setup (memories, skills) into Hermes.
- unslothSkill · Skills directoryUnsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.