---
title: "Hermes Agent memory: where it lives and how to clear it"
description: "Hermes Agent memory from pinned source: MEMORY.md and USER.md limits, the frozen snapshot, session search, external providers, and how to view or clear it."
url: https://personalagentbench.com/hermes-agent/memory/
last_updated: 2026-10-20
---

# Hermes Agent memory: where it lives and how to clear it

Hermes Agent memory is two small Markdown files per profile, `MEMORY.md` for the agent's notes and `USER.md` for what it knows about you, kept in `~/.hermes/memories/` and capped at 2,200 and 1,375 characters. Both are read once when a session starts and pasted into the system prompt. Everything else it can recall comes from a separate store: every conversation sits in a local SQLite database, `state.db`, which the agent searches with a full-text `session_search` tool. [Memory files and limits](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L13-L20); [Session search](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L217-L224).

This page goes further than the memory section of our [Hermes Agent review](https://personalagentbench.com/hermes-agent/). It's a source reading of the same pinned revision, `0b89435e7e4f7fab88a34eb69f13bf339eb2fd00`: we read the documentation and the Python that implements it, and we didn't run Hermes. Where the docs and the code disagree, we say so.

- The files are plain text. Entries are separated by a line holding only `§`, so you can open, edit or empty them yourself.
- A fact saved mid-session doesn't reach the prompt until the next session, or until context compression or `/undo` rebuilds the prompt, neither of which the user guide mentions.
- A background review runs every 10 user turns by default. It can add entries, but it can't delete or rewrite them on its own; those changes wait for your approval.
- Session search returns stored messages, not model summaries, and deleting the Markdown files leaves `state.db` untouched.

## What Hermes Agent memory stores, and where

There are three places Hermes keeps things about you, and they behave differently. The table is the short version; the sections below give the evidence.

| Store | Where it lives | What goes in | How you clear it |
| --- | --- | --- | --- |
| `MEMORY.md` | `<hermes home>/memories/` | Agent's notes: environment, conventions, tool quirks | Edit the file, or ask for a `remove` |
| `USER.md` | Same folder | Your name, role, preferences, style | Same as above |
| `state.db` | `<hermes home>/state.db` | Every session's full message history, indexed with FTS5 | `hermes sessions delete` or `prune` |
| External provider | Depends on the plugin: a cloud service, a local server or a local SQLite file | Synced turns plus mirrored memory writes | Through the provider |

The home folder is `~/.hermes` on macOS and Linux, and `%LOCALAPPDATA%\hermes` on Windows unless `HERMES_HOME` says otherwise. The memories folder is computed from it on every call, which is why profiles get separate memory: `hermes -p work` reads `~/.hermes/profiles/work/memories/`, not the default folder. [Home resolution](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/hermes_constants.py#L51-L58); [Memory directory](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool.py#L38-L40); [Profiles](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L82-L82).

The database path follows the same home, and its messages table keeps role, content, tool calls and reasoning fields for each message. [state.db path](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/hermes_state.py#L176-L178); [Messages table](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/hermes_state_common.py#L449-L475).

## How the Hermes Agent memory tool writes entries

Hermes only remembers something when the model calls its `memory` tool. A reply saying "I'll remember that" is just text, and the official troubleshooting page says small or weak tool-calling models often produce the sentence without the call. [Write check](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L71-L78).

The tool has three actions, `add`, `replace` and `remove`, and two targets, `memory` and `user`. There's no read action, because the contents are already in the prompt. `replace` and `remove` find an entry by a short unique substring, and `replace` overwrites the whole entry rather than splicing text inside it. [Tool actions](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L90-L113); [Schema enum](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool.py#L372-L383).

The source adds a few things worth knowing:

- An `add` is stripped, scanned for prompt-injection and exfiltration patterns, skipped with a "no duplicate added" message if an identical entry exists, and refused if the joined file would pass the limit. [Add path](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L334-L346).
- Every write takes a lock, re-reads the file from disk, then saves through a temporary file and a rename, so a reader never sees half a file. [Locked write](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L303-L332); [Atomic save](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L581-L589).
- When memory is full, the tool asks for one batch that frees space and adds the new entry, checking the limit only on the final result. On the fourth consecutive failure in the same turn it tells the model to stop and answer you instead; a successful write resets the count. [Batch guidance](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool.py#L346-L365); [Retry cap](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L146-L185); [Reset on success](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L535-L537).

Nothing is auto-compacted. Hermes never drops an entry to make room; the model has to choose what to cut. [No auto-compaction](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L26-L34).

## When Hermes Agent memory reaches the prompt

At load, Hermes reads both files, removes exact duplicates and renders a block with a header, a usage line giving the percentage and characters used, and the entries. That rendered text is the frozen snapshot. Writes during the session go to disk straight away, but the prompt keeps the old snapshot so the model provider's prefix cache stays valid. [Snapshot at load](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L187-L218); [Frozen block](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L524-L550).

The user guide says that snapshot "never changes mid-session". The code has two exceptions. After context compression, `invalidate_system_prompt` clears the cached prompt and calls `load_from_disk()` again, so a long chat that compresses picks up the session's own saves before it ends. `/undo` calls the same function, in the CLI and in the TUI, so rewinding a turn also reloads memory. The developer guide on prompt assembly mentions a compression-triggered rebuild; the user guide mentions neither. Our [Hermes Agent architecture page](https://personalagentbench.com/hermes-agent/architecture/) covers how the rest of the prompt is assembled. [User guide claim](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L57-L57); [Reload after compression](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/system_prompt.py#L808-L826); [Developer guide](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/developer-guide/prompt-assembly.md#L284-L286); [CLI undo](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/hermes_cli/cli_session_mixin.py#L699-L712), [which calls it](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/hermes_cli/cli_session_mixin.py#L809-L809); [TUI undo](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tui_gateway/methods_tools.py#L958-L965); [Function binding](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/run_agent.py#L1212-L1212).

Two load-time details matter if you edit the files by hand. An entry matching a threat pattern is replaced in the prompt with a `[BLOCKED: …]` note, while the raw text stays in the file so you can see and remove it. And a file over its limit isn't truncated: it all loads, a warning is logged, and every later `add` fails until you trim it. [Load sanitising and over-limit warning](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L194-L217).

On Telegram or Discord a chat is one continuous session, even across restarts, so new facts can stay out of the prompt for weeks. The docs suggest `/new` at natural boundaries. [Session boundaries](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L59-L65).

## Hermes Agent memory you didn't ask it to save

Hermes saves without being asked. The guide says the agent stores preferences, corrections and environment facts proactively, and a background review runs after turns to catch what the main conversation missed. [Proactive saving](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L139-L148); [Background review](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L346-L353).

In the source, the memory nudge interval defaults to 10, and a counter of user turns fires the review when it reaches that number, provided the memory tool is available. [Default interval](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/agent_init.py#L1321-L1333); [Turn counter](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/turn_context.py#L752-L761).

The review is limited in what it can do alone. An unattended review may `add`, but any `replace` or `remove`, single or inside a batch, is staged for you to approve with `/memory pending` instead of being applied. If staging fails, the change is denied. That means a background pass can grow your profile but can't quietly rewrite or erase an entry you wrote. [Background delete gate](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool.py#L171-L211).

If you want every save checked, set `memory.write_approval: true`. The interactive CLI then prompts inline, and writes from messaging platforms, scripts and the review are staged. To stop the review entirely, set `auxiliary.background_review.enabled: false`. [Write approval](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L311-L336); [Disabling reviews](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L409-L421).

## Hermes Agent session search, the other memory

The two Markdown files hold roughly 1,300 tokens between them. Anything bigger lives in `state.db`. Messages are indexed in an SQLite FTS5 table on content, tool name and tool calls, kept in sync by triggers. [FTS5 table](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/hermes_state_common.py#L785-L799); [Memory vs search](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L232-L243).

The `session_search` tool infers its mode from the arguments: a query searches, a session id plus a message id scrolls around that message, a session id alone reads the session, and no arguments browses. Its header says there are no model calls; every shape returns stored messages. [Tool modes](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/session_search_tool.py#L1-L8).

Two ranking choices shape what the agent can find. Sessions from integrations, subagents and kanban workers are hidden from search. Cron sessions stay searchable but rank below your own conversations, because their repeated vocabulary was crowding them out. [Hidden and demoted sources](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/session_search_tool.py#L21-L32).

Compression doesn't delete any of this. It starts a continuation session, numbered `#2`, `#3` and so on, and the sessions guide says plainly that compression "is not a privacy delete". [Lineage on compression](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/sessions.md#L298-L306); [Not a privacy delete](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/sessions.md#L60-L68).

## External Hermes Agent memory providers

A provider plugin adds memory beyond the two files. Only one can be active at a time, chosen with `memory.provider`, and the built-in files keep working beside it. At this revision the repository ships RetainDB and ByteRover; Honcho, Hindsight, Mem0, OpenViking, Supermemory and Holographic come from the plugin catalog. [Provider overview](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L9-L28); [One provider at a time](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/memory_provider.py#L1-L5).

Turning one on changes where your data goes. The docs list what the provider receives: injected context, prefetch before each turn, synced turns after each response, session-end extraction, and a mirror of every built-in memory write. Hermes runs a secret scrub over that traffic first, and the docs warn it misses credentials with no recognisable shape. In the source, the mirror only fires from the live `memory` tool, and only for a write that actually landed; a staged write is skipped. We found no mirror call on the `/memory approve` path either, so a write you approve later appears not to reach the provider. [Committed-write check](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/memory_manager.py#L871-L884); [Only caller](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/inline_tool_executors.py#L151-L154); [Approve path](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/hermes_cli/write_approval_commands.py#L122-L136). [What providers receive](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L30-L43).

To choose one, run `hermes memory setup` for the picker, `hermes memory status` to see what's active, and `hermes memory off` to go back to the built-in files only. Where the data ends up differs by provider. Holographic is a local SQLite file, and ByteRover is local by default with optional cloud sync. Hindsight can run in the cloud, as local embedded PostgreSQL, or against your own local server. Honcho, Mem0 and Supermemory offer a cloud service or self-hosting, and RetainDB is cloud only. [Setup commands](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L11-L17); [Holographic](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L558-L564); [ByteRover](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L632-L638); [Hindsight](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L497-L497); [Honcho](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L59-L59); [Mem0](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L400-L400); [Supermemory](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L673-L673); [RetainDB](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L615-L615).

The source interface backs the mirror claim. `on_memory_write` receives each add, replace or remove with the target, the content and, for a replace or remove, the full previous entry. A separate `on_pre_compress` hook hands the provider the messages about to be compressed. [Mirror hook](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/memory_provider.py#L194-L201); [Pre-compress hook](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/agent/memory_provider.py#L176-L178).

Hand edits never go through the tool, so a fact you delete from `USER.md` by hand is never sent to the provider as a removal, and it may still exist there. Removing it is the provider's job, and we didn't test any provider's deletion.

## Check Hermes Agent memory on your own install

These commands and paths come from the pinned docs. Run them against your own setup; we haven't.

- `cat ~/.hermes/memories/MEMORY.md` and `cat ~/.hermes/memories/USER.md` show what will load next session. For a named profile, look in `~/.hermes/profiles/<name>/memories/`, and use `hermes profile list` if you're unsure which profile you're on. [File checks](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L71-L86).
- `/memory pending` lists staged writes, including review changes tagged `[auto]`; `/memory approve` and `/memory reject` take an id or `all`. [Staged writes](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L325-L332).
- `hermes journey list` prints memory node ids, and `hermes journey delete <node>` removes a memory chunk. [Journey commands](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L255-L263).
- `hermes memory status` shows whether an external provider is active, and `hermes memory off` disables it. [Provider commands](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory-providers.md#L11-L17).
- `hermes sessions list` browses history, and `hermes sessions delete <id>` removes one session. Close the chat first: a session still open will be recreated on its next save. [Session deletion](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/sessions.md#L463-L475).

Hand edits are safe if you keep the format. The store splits entries on a newline, `§`, newline. It refuses to write, and saves a `.bak` copy, when a single entry is longer than the whole file's limit, which is what free text without separators looks like. It also refuses to write over a file it can't read, such as one with invalid UTF-8, rather than saving over it from an empty view. [Separator](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L25-L25); [Drift guard](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L591-L606); [Unreadable file](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L553-L568), [refused before writing](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool_store.py#L314-L318).

To switch memory off, set both `memory.memory_enabled` and `memory.user_profile_enabled` to `false`; the tool and its prompt guidance disappear. Listing `memory` under `agent.disabled_toolsets` also hides external provider tools. In the source, both flags default to true. [Disabling memory](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L265-L291); [Flag defaults](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool.py#L297-L309).

## Where the Hermes Agent memory docs and source disagree

Most of the documentation matches the code. Three places don't, and one is only half true.

1. **Frozen snapshot.** The user guide says it never changes mid-session; compression and `/undo` both reload it, as shown above.
2. **Folder path.** The prompt-assembly guide names `~/.hermes/MEMORY.md` and `~/.hermes/USER.md`. The code and the user guide use the `memories/` subfolder. [Developer guide path](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/developer-guide/prompt-assembly.md#L311-L312).
3. **Completed work.** The user guide lists "Completed work" as something to save to `memory`. The tool description the model actually sees says to skip "completed-work logs" and use `session_search` for them, and to put task lessons in a skill. Expect the model to follow the tool description. [Guide example](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L147-L147); [Tool description](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/tools/memory_tool.py#L358-L370).
4. **Providers "never replacing" built-in memory.** True by default, but the same page explains how to turn the built-in stores off and run a provider instead. [Additive claim](https://github.com/NousResearch/hermes-agent/blob/0b89435e7e4f7fab88a34eb69f13bf339eb2fd00/website/docs/user-guide/features/memory.md#L526-L530).

## Hermes Agent memory compared with OpenClaw

Both projects keep memory as Markdown you can open. OpenClaw promotes records into a workspace `MEMORY.md` and keeps a SQLite-backed index beside it, and deleting the file isn't verified to clear that index. Hermes is similar in shape: the Markdown files are what the prompt sees, and `state.db` is the searchable history that outlives them. Our [OpenClaw security review](https://personalagentbench.com/openclaw-security/) covers its stores, and the [Hermes Agent vs OpenClaw comparison](https://personalagentbench.com/hermes-vs-openclaw/) puts the two side by side.

Hermes caps prompt memory at a few thousand characters and pushes everything else into search or skills. That makes it cheap to inspect: two short files and a database.

## FAQ

**Where is Hermes Agent memory stored?** In `~/.hermes/memories/MEMORY.md` and `USER.md` for the default profile, or `~/.hermes/profiles/<name>/memories/` for a named one. Conversation history is in `~/.hermes/state.db`.

**How big can Hermes Agent memory get?** 2,200 characters for `MEMORY.md` and 1,375 for `USER.md` by default, set by `memory_char_limit` and `user_char_limit`. Session history in `state.db` has no such cap.

**Why doesn't Hermes remember what I told it a minute ago?** Either the tool was never called, so check the file, or the save happened after the session's snapshot was taken. Start a new session with `/new`.

**Can I edit MEMORY.md by hand?** Yes. Keep each entry separated by a line containing only `§`, and stay under the limit, or later saves will fail until you trim it.

**How do I delete everything Hermes remembers?** Empty or remove both memory files, delete sessions with `hermes sessions delete` or `prune`, and clear any external provider through its own tools. We haven't verified that this removes every copy, such as backups.

**Does Hermes send my memory anywhere?** The built-in files stay local, but they reach your model provider inside the system prompt. An external memory provider also receives synced turns and mirrored memory writes.

---

Published by Personal Agent Bench (https://personalagentbench.com), run by the Zentor team. Zentor builds agent software of its own, so its products are not on the scorecard and will not be added.