Your agent remembers everything.
Most AI tools reset the moment you close the tab. Every new conversation starts from zero — you re-explain your stack, your preferences, your context. It compounds into wasted hours.
Hermes agents are different. They live on a persistent server. When you come back tomorrow, next week, or six months from now, the agent knows your name, your projects, your decisions, and what it was working on.
What "persistent" actually means here
Context windows — the amount of text a language model can process at once — are not persistence. A 200,000-token context window still resets to zero when you start a new session. The model does not remember the previous conversation unless you manually paste it back in.
Persistent memory is a separate system that runs alongside the model. Between sessions, a memory layer stores what the agent has learned about you, your projects, and its own task history. At the start of a new session, relevant memories are retrieved and loaded into context. The agent does not start from scratch — it picks up where it left off.
This is how Hermes Agent is designed to work, and it is the main reason people use it over a general-purpose chatbot.
Three memory types Hermes uses
The user model is a structured record of who you are: your technical preferences, your communication style, the projects you are running, your time zone, how you like results reported. This loads at the start of every session and shapes how the agent responds without you having to re-explain.
Skill Documents are procedural memory — records of how the agent solved a particular class of problem. When Hermes successfully scrapes a tricky website, processes a specific data format, or debugs a pattern of error, it can synthesize that experience into a reusable document. The next similar task takes less time and requires less guidance because the agent already knows a working approach.
Event memory is a timestamped log: tasks undertaken, decisions made, results achieved, failures encountered and how they were handled. This is what lets the agent tell you what it did last Tuesday, or explain why it made a particular call three weeks ago.
Why this requires a server that stays on
Memory stored in a local application disappears if you reinstall, switch machines, or the application crashes. For memory to be genuinely useful over months of agent use, it needs to live somewhere persistent — a server with its own storage, separate from your local environment.
This is why running an agent locally on your laptop is fundamentally limited for memory-intensive use. You get the capability during the session, but you lose the compounding effect that makes the agent genuinely useful over time.
Hermes OS hosts the memory layer on dedicated cloud infrastructure. Daily encrypted backups run automatically. If you switch to a new computer, your agent's full memory is exactly where you left it. Nothing is tied to a local process.
Memory isolation across agent profiles
If you run multiple agent profiles — a research agent, a coding agent, a customer support agent — each profile has a completely separate memory store. They do not share context and cannot contaminate each other's working memory.
On the Power plan, agents can make deliberate cross-agent references: an operations agent can pass a structured summary to a research agent, which can reference it in its task log. But this is explicit and auditable, not accidental bleed-through.
Memory review and correction
The Hermes OS dashboard includes a memory viewer. You can search the full memory store, inspect individual memories, and edit or delete anything that is wrong or outdated. If the agent learned an incorrect assumption — a wrong belief about how a system works, a mistaken preference — you can correct it directly rather than waiting for it to get overwritten through repeated correction in conversation.
You can also export your complete memory store as a structured file at any time. If you ever want to move to a self-hosted setup or a different hosting provider, you are not locked in by accumulated state.
- Full conversation and task history retained across sessions
- User model lives in USER.md — goals, preferences, communication style, project context
- General knowledge lives in MEMORY.md — curated facts the agent reads at session start
- Skill Documents: agentskills.io open format, procedural memory that compounds over time
- Event log: timestamped record of every task and decision
- Optional Honcho integration: cross-session AI-native user modeling across tools
- Checkpoint and rollback support — /rollback command reverts file changes
- Memory isolated per agent profile — multiple agents, no cross-contamination
- Automatic daily encrypted backups
- Memory reviewer and editor in the dashboard
- Full export available — not locked in
How long does persistent memory last on Hermes OS?
Your agent's memory persists for the life of your subscription. There is no expiry. Daily backups ensure you are always covered against data loss.
Can I reset or wipe an agent's memory?
Yes. You can reset the full memory store or delete individual memories from the dashboard. Selective removal is supported — you do not have to wipe everything to correct one wrong memory.
Does memory work across different agent profiles?
Each profile has isolated memory by default. Cross-agent references are supported on the Power plan via an explicit coordination mechanism — not automatic sharing.
What format is the memory export?
Memory exports as a structured JSON file compatible with self-hosted Hermes installations. The format is documented in the Hermes Agent specification.
Is the memory encrypted?
Yes. Memory is encrypted at rest and in transit. Backups use the same encryption.
Can the agent's memory get too large and slow things down?
Typical agent memory after months of active use is in the hundreds of megabytes — small enough that retrieval latency is not a concern. The memory retrieval system uses vector similarity search, which scales well past hundreds of thousands of stored items.