witcheer's Wingtips for Hermes Agent

Wingtips

1. #108 · hermes memory setup

   Oct 22, 2026 · Memory & context · CLI

   Hermes Agent keeps its own memory in MEMORY.md and USER.md. a memory provider runs alongside it and adds things like semantic search, knowledge graphs and automatic fact extraction.

   one command walks you through adding one:

   hermes memory setup

   pick a provider from the list, answer its setup questions and start a new session. your built-in memory stays on the whole time.

   great for a long project, a research habit or an agent you talk to every day!

   docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/memory-providers

   SourcesHermes docs: Memory Providers

2. #94 · attach a file to your message

   Oct 7, 2026 · Memory & context · CLI

   your Hermes Agent can take a whole file as part of your message, with no copy and paste.

   type @, pick file: from the menu, then add the file's name and your question:

   @file:meeting-notes.md turn this into a to-do list

   handy for meeting notes, or a config file you want checked!

   on X the line carries a space after the @ so it doesn't tag an account. type it with no space.

   only part of a file? add the line numbers after the name: @file:meeting-notes.md:3-5 sends lines 3 to 5.

   docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/context-references

   SourcesHermes docs: Context References

3. #89 · /branch, copy the conversation into a new session and try another direction, the original kept

   Oct 2, 2026 · Memory & context · CLI / Gateway

   it copies your conversation with your Hermes Agent into a new session, history included, and you carry on in the copy.

   want to try a different idea without losing where you are?

   type this in the chat:

   /branch

   useful before a big change of direction, or to compare two answers from the same starting point!

   name the branch if you like: /branch plan-b. without a name it takes the original title with a number.

   docs: https://hermes-agent.nousresearch.com/docs/reference/slash-commands

   SourcesHermes docs: Slash Commands

4. #88 · /context, see what fills your model's context window, by category, with the free space left

   Oct 1, 2026 · Memory & context · CLI / Desktop / Gateway

   your Hermes Agent's context window holds more than your messages: the system prompt, the tool definitions, your memory, any project rules and the conversation so far.

   how much room does each one take?

   type this in the chat:

   /context

   you get a breakdown of the window by what fills it, with the free space that is left.

   useful before a long session, or when you want to see how close a chat is to compressing!

   docs: https://hermes-agent.nousresearch.com/docs/reference/slash-commands

   SourcesHermes docs: Slash Commands

5. #65 · hermes sessions import

   Sep 7, 2026 · Memory & context · CLI / Desktop

   Hermes Wingtips #65: hermes sessions import

   if you have a conversation going in Claude Code or Codex CLI, you can carry it on in Hermes Agent.

   say you spent an hour with another coding agent on a feature, and now you want Hermes to take the next step with all of that context. instead of explaining it again from scratch, you bring the conversation over.

   hermes sessions import

   it lists the sessions it finds on your machine, newest first. pick one and it becomes a Hermes session you can resume like any other.

   what comes across is the conversation itself: your messages, the answers, and a short note wherever a tool ran. your other agent's files are only read, never changed.

   this is different from hermes import-agent, which moves your setup (instructions, skills). this one moves the chat.

   SourcesHermes docs: Sessions

6. #63 · compression.context_timeout_seconds

   Sep 5, 2026 · Memory & context · CLI / Desktop / Gateway

   Hermes Wingtips #63: compression.context_timeout_seconds

   when a chat gets long, Hermes summarises the older messages to free up room. a separate model writes that summary in the background while your conversation keeps going.

   but what if that summary model hangs? without a guard, your whole session would sit there waiting on it.

   this setting is that guard. if the summary model goes quiet for 120 seconds, Hermes stops waiting: it tries one backup model, and if that fails too it skips the summary, keeps all your messages and tells you.

   hermes config set compression.context_timeout_seconds <seconds>

   the guard only counts silence. a model that is slow but still writing gets all the time it needs. raise the number if your summary model runs on slower hardware, or set 0 to switch the guard off.

   SourcesHermes docs: Configuration

7. #52 · idle compaction

   Aug 23, 2026 · Memory & context · CLI / Desktop / Gateway

   Hermes Wingtips #52: idle compaction

   a long-lived thread carries its whole history back into context every time you come back to it, and you pay for that stale backlog on every turn.

   your Hermes Agent has a time-based trigger for exactly this:

   hermes config set compression.idle_compact_after_seconds 1800

   the size-based threshold waits for the context to grow big. this one fires on the time gap since your last message. set it in seconds, 1800 = 30 minutes.

   super useful if you keep one long Telegram or Discord thread with your agent, or park a session overnight and pick it up in the morning!

   SourcesHermes docs: Configuration

8. #49 · compaction thresholds

   Aug 19, 2026 · Memory & context · CLI / Desktop / Gateway

   Hermes Wingtips #49: compaction thresholds

   when your Hermes Agent stops mid-task to summarize, the number in that warning is not random. compaction fires at a fixed fraction of your main model's context window.

   the fraction is compression.threshold in config.yaml, and it is always read off the model you chat with, never the summarizers' window.

   on smaller context windows Hermes waits longer by default, so a compaction cannot fire with half the window still free.

   and if you switch between a huge-context model and a small one, compression.model_thresholds sets a different trigger per model, matched on the model name.

   SourcesHermes docs: Context Compression And Caching

9. #24 · gateway sessions do not auto-reset by default

   Jul 18, 2026 · Memory & context · Gateway

   Hermes Wingtips #24: gateway sessions do not auto-reset by default.

   the default is session_reset: mode: none, so a Telegram or Discord chat keeps its history across restarts until you say otherwise. if you want a clean slate on a schedule, opt in:

   (1) idle resets after idle_minutes of quiet (default 1440, so 24h)

   (2) daily resets once a day at at_hour (default 4, local time)

   (3) both resets on whichever comes first

   before any auto-reset it saves memories and skills first.

   SourcesHermes docs: Sessions

10. #19 · it remembered, it just can't see it yet

    Jul 13, 2026 · Memory & context · CLI / Desktop / Gateway

    Hermes Wingtips #19: it remembered, it just can't see it yet.

    we snapshot MEMORY.md and USER.md once at session start so the LLM prefix cache stays warm.

    a mid-session save hits disk immediately, and only lands in the system prompt on the next session.

    you need the new fact in play now?

    (1) start a fresh session (2) or hermes -c on the next turn

    tool responses already show the live write.

    SourcesHermes docs: Sessions

11. #15 · a compaction rewrites your history into a working brief

    Jul 7, 2026 · Memory & context · CLI / Desktop / Gateway

    Hermes Wingtips #15: a compaction rewrites your history into a working brief

    when a long session reaches the compaction point, Hermes doesn't drop the middle turns, it rewrites them into a structured brief with fixed slots:

    goal / constraints / progress / key decisions / relevant files / next steps / critical context.

    that brief carries the working state forward, and the raw turns stay in state.db where session_search can still reach them.

    so a compaction is your agent re-reading its own notes, not losing the thread.

    (1) work in the brief's shape: state goals and decisions in plain words, so they map straight into the slots that get kept

    (2) for anything that must never drop, put it in MEMORY.md, which reloads on every session no matter how many compactions happen

    SourcesHermes docs: Context Compression And Caching

12. #3 · your agent didn't forget, its memory is a frozen snapshot

    Jun 22, 2026 · Memory & context · CLI / Desktop / Gateway

    Hermes Wingtips #3: your agent didn't forget, its memory is a frozen snapshot.

    tell it something, it saves to MEMORY.md, the write hits disk right away. but the curated memory block in the system prompt loads once at session start and stays fixed for the whole session.

    this is on purpose, to keep the prefix cache warm.

    so mid-session it can act like it "forgot" what it just saved. it didn't: tool calls still read the live on-disk value, only the injected block is frozen. it refreshes next session.

    if you need it acting on a fresh memory right now, start a new session. the save already landed, it just shows up next time.

    SourcesHermes docs: Memory

13. #2 · the 🗜️ icon, what context compression keeps and what it drops

    Jun 19, 2026 · Memory & context · CLI / Gateway

    Hermes Wingtips #2

    the 🗜️ icon, what context compression keeps and what it drops

    this little emojy is the compression count: how many times Hermes auto-summarised the session to stay under the context limit, which kicks in around 50% full.

    when compression occurs, it keeps your first 3 turns and your last 20, and summarises everything in between. a detail from the middle of a long session can then drop out, and the agent repeats work it already did, even though the opening goal and the recent turns are intact.

    Copy code

    three levers when it bites, all in config.yaml, hot-reloading on a running gateway: 
    
    - protect_last_n keeps more recent turns uncompressed 
    
    - auxiliary.compression.model points the summariser at a cheap fast model so it does not burn main-model tokens
    
    - model.context_length raises the ceiling so it fires later.
    
    https://hermes-agent.nousresearch.com/docs/developer-guide/context-compression-and-caching
    

    SourcesHermes docs: Context Compression And Caching