agentry/assistant
A personal assistant that keeps its conversation with you across sessions, on your computer.
Built into Agentry. The application runs this package itself; it is published here so you can read how it works. Its README says what Agentry gives it beyond its manifest.
Declared capabilities
Capabilities are the author's declaration and the basis for policy and scanning. The registry cannot enforce them at run time. Your runtime should.
Persistent agent
What this release declares as a persistent agent. You agree to all of it when you install, and again when an update declares more. The runner on your computer gives it nothing else.
It may use
- clock — the time on each turn, its own tasks and the heartbeat that fires them
- memory — a memory on its own volume that it keeps, compacts and recalls from
- skills — the skills it ships and the ones you add
- secrets — stored secrets you keep for it in your keychainFASTMAIL_TOKEN, BRAVE_API_KEY
- selfConfigure — changing its own name and persona
- calendars — reading the calendar feeds you add
- meetings — taking notes in the meetings you arm
- mail — your mail, at the providers you sign in togoogle, microsoft, fastmail
- imageServers — servers the runner runs from its own images, once you sign ingoogle-workspace, microsoft-365
- web — searching the web and reading pages
- helper — finding, installing, running and scheduling QuickAgents, each install and new version with your agreement
- desktop — a capability this page has no description for yet
Persona
It declares no persona.
Subagents
It declares none, so it is given no tools to start another QuickAgent.
MCP servers & tools
agentry run serves exactly the tools this contract declares, through a per-run MCP gateway. An undeclared capability is a tool that does not exist at run time.
Tools the runner grants
| Manifest declaration | Tool(s) granted |
|---|---|
| (always) | write_report — reports → the run's output folder |
| (always) | list_inputs, read_input, search_inputs — operator-provided input files, read-only |
MCP servers involved
- QuickAgent Tools — the runner's companion server, served through a per-run Docker MCP Gateway; its tool surface is exactly the table above.
In an embedded install
Installed into an existing coding agent (agentry install), the same contract maps to the host's built-in tools — enforcement there is the host's. Allowed tools: none declared (host defaults apply).
Install as a persistent agent
A persistent agent keeps its conversation between sessions and runs on your own computer. Agentry never runs it hosted. One dialog asks you to agree to what it declares, and installing it again updates it.
Install in Agentry Desktop
In Agentry Desktop, open Browse, find agentry/assistant and choose Install as a persistent agent.
Agentry Desktop 0.7.1 or later. Get Agentry Desktop if you do not have it.
Install with the CLI
agentry agent install agentry/assistantNeeds CLI v0.7.2 or later. Persistent agents covers updating and removing one.
- memory/
- skills/
- agent.yaml850 B
- INSTRUCTION.md12.6 kB
- LICENSE1.1 kB
- README.md16.9 kB
README.md
The Assistant
The Assistant is a personal assistant that keeps its conversation with you across sessions. It runs on your computer as a persistent agent: you start it, talk to it, stop it, and when you start it again the conversation continues.
This is the package that runs
The Assistant is built into the Agentry CLI and the desktop app, and it runs
from there: agentry agent start assistant, then agentry agent chat assistant, in the CLI. This release has the same bytes. The registry built
its archive from the package the CLI carries, and the archive's digest is the
one the CLI reports. Run agentry builtins to print it and compare it with
the digest on this page.
Installing this release does not give you a second Assistant: the CLI refuses to install a built-in's release as a persistent agent, and runs the Assistant it carries. It never runs this release as an ordinary QuickAgent, since the release declares only the persistent mode.
What the application gives it
The manifest declares no network access, no file access, no commands and no
run secret. Under capabilities.persistent it declares the time with its
tasks (clock), a memory (memory), skills (skills), the stored secrets
it asks for (secrets: FASTMAIL_TOKEN and BRAVE_API_KEY; you may store
others), its own name and personality (selfConfigure), Agentry's helper
tools (helper), the meeting tools (meetings), calendar feeds
(calendars), mail at Google, Microsoft and Fastmail (mail), and the
Google Workspace and Microsoft 365 servers the CLI runs from its pinned
images (imageServers). When the application
runs the Assistant, it gives it what follows, and agentry agent show assistant lists what it has:
- Its conversation is kept on a volume of the agent's own, which the
runner keeps between starts and removes only when you reset the agent
(
agentry agent reset assistant). - Its own files are on a second volume, its data folder, kept the same way.
- Its memory is on a third volume, kept the same way: pages it writes in
memory/for itself to read, on what you tell it and what you share with it, one fact per line with its source (a file in your share and the date it read it, or what you said and when), an index and a log. It reads its memory at the start of each topic and adds to it when a topic ends. When its conversation has grown large (two hours with nothing from you and 100,000 tokens or more, or three quarters of the model's context window in use), it saves the conversation to its memory and goes on in a fresh conversation that opens with a short handoff it wrote;agentry agent compact assistantdoes it at once. Once a day, after two hours with nothing from you, it tidies its memory if it changed (duplicates merged, long pages split, the index kept short), as one of the same upkeep turns. Agentry reminds it to read its memory at the first message of each new conversation and when you come back after half an hour. Its Agentry toolrecallsearches the conversations it had before, compacted ones included, as the transcript on your computer keeps them (your messages, its answers and its tasks' turns, never tool results); it changes nothing. It is told never to change your share's files to keep it. When the memory is made, the notes in its data folder'snotes/are copied into it, and stay where they are.agentry agent memory export assistant <folder>copies the memory into a new folder, readable by you alone; a reset removes it. - Eighteen skills of its own, on unless you switch them off:
memory-ingest,memory-query,memory-consolidateandmemory-compact, which say how it adds to its memory, answers from it, tidies it and saves a whole conversation before it is compacted;meeting-notes, which says how it summarises a meeting Agentry Desktop recorded and transcribed (a call, its far side's voices told apart or not, or a meeting held in the room; it never names a voice unless the transcript does), each point with its time in the transcript, saves the summary beside it, files the meeting in its memory, and arms the recordings you ask it for;google-workspace-setup, which walks you through connecting your Google account;google-workspace,google-inbox-triageandgoogle-meeting-prep, adapted from gog's own skills (MIT, their licence beside them), which say how it uses your Google account safely;microsoft-365-setup, which walks you through connecting your Microsoft account with an Entra app of your own;microsoft-365,microsoft-inbox-triageandmicrosoft-meeting-prep, which say how it uses your Microsoft account safely;fastmail-setupandfastmail-inbox-triage, for your Fastmail account;calendar-feeds-setupandcalendar-feeds, which walk you through giving it a calendar by its iCal address and say how it reads one; andquickagent-use, which says how it works out what a QuickAgent needs from what it shows (its questions, files, keys and guide) and runs it for you; andquickagent-edit, which says how it changes, forks, makes and looks after the QuickAgents you publish. - A share folder of yours,
~/agentry/assistantshareunless you choose another, is mounted read and write while it runs: you see what it writes there as it writes it. A file you add is checked for malware with ClamAV before it reads it, and one ClamAV finds is not read; a file the check cannot read (no signatures on your computer, or past its size limits) is read unchecked, and the segment's receipts say so. You can switch the share off. - The web tools,
web_searchandweb_read, off until you switch them on (in Agentry Desktop, the Web search and pages card in its Configuration; in a terminal,agentry agent grant assistant web on), which asks you to agree first. AI Review reads every search result and page with your own TypeSafe key before the Assistant sees it, and withholds one it flags; the start says so when no key is set. Their container also holds your share, the Assistant's own files and memory, its knowledge packs and the events of the calendar feeds you add. What it reads there could be sent in an address it opens, which is why the tools are off until you choose them. Without AI Review (agentry agent grant assistant unreviewed on) runs them with no TypeSafe key, and nothing reads a page before the Assistant does: a page can then tell it to act with your share, its memory, your mail and calendar and the QuickAgents it looks after. It is off until you switch it on and agree, and refused while your organization's managed settings lock how AI Review is done. - MCP servers it comes with, each an entry of its roster that you switch
on and off: Wikipedia (
@cyanheads/wikipedia-mcp-server, English Wikipedia alone), on until you switch it off, and web search with Brave (@brave/brave-search-mcp-server), off until you store your own Brave Search API key for it (agentry agent secret set assistant BRAVE_API_KEY). Each reaches only its provider's host. It also suggests two servers you can add as your own, for your own use under their providers' terms: weather from Open-Meteo, whose free service is for non-commercial use, and maps from OpenStreetMap, whose public servers ask for light use (agentry agent configure assistant --add-suggested weatherormaps). - Google Workspace through gog's MCP server, run from the image Agentry
pins, off until you switch it on and sign it in with your own Google Cloud
OAuth client (in Agentry Desktop, the Google card's Set up in its
Configuration's Mail and calendar; in a terminal,
agentry agent configure assistant --google-client <file>, then--google-sign-in <email>); thegoogle-workspace-setupskill walks you through it. It reads Gmail, Drive, Docs, Sheets and your Calendar's events, read only unless you also switch on its changes, and sends mail only with sending switched on too. It keeps its sign-in on a volume of its own, under a password kept in your system keychain, and reaches Google's hosts alone. - Microsoft 365 and Outlook.com through Softeria's MCP server, run from
the image Agentry pins, off until you switch it on and sign it in with your
own Entra app (in Agentry Desktop, the Microsoft card's Set up in its
Configuration's Mail and calendar; in a terminal,
agentry agent configure assistant --microsoft-client <id>, then--microsoft-sign-in <email>), by a device code. A work or school account usually needs its administrator to approve the app first, and themicrosoft-365-setupskill writes that request with you. It reads your mail, calendar, contacts and OneDrive, read only unless you also switch on its changes, and sends mail only with sending switched on too. It keeps its sign-in on a volume of its own, sealed under a key kept in your system keychain, and reaches Microsoft's sign-in and Graph hosts alone. - Fastmail through Fastmail's own MCP server, run at Fastmail and
reached at
api.fastmail.comalone, off until you give it your own Fastmail API token of the MCP type (in Agentry Desktop, the Fastmail card's Set up in its Configuration's Mail and calendar; in a terminal,agentry agent configure assistant --fastmail-token), which is kept in your system keychain once Fastmail accepts it: it can read, change or send in your account whatever your token allows, so make the token Read only unless you want changes. - Mail providers: Google, Microsoft and Fastmail are each enabled or disabled
(
agentry agent configure assistant --mail-provider <key>); only an enabled one's server is on its roster, and setting one up enables it. - Calendar feeds: any calendar you give it by its iCal (ICS) address,
under a name you choose (in Agentry Desktop 0.6.176 or later, Add a
calendar feed in its Configuration's Mail and calendar; in a terminal,
agentry agent configure assistant --calendar-feed <name>, the address read without echo); thecalendar-feeds-setupskill walks you through it. It takes Google Calendar's secret address, the ICS link Outlook gives a published calendar, an iCloud public calendar or another service's. An address that answers only a signed-in browser, such as a Google Workspace calendar's public address while its secret one is turned off, is given with--calendar-sign-in: a browser window opens at it, you sign in, and the cookies that window sends to the calendar's site (your sign-in to that site, not a key to one calendar) are kept in your keychain beside the address, sent to that site alone. Each feed is an entry of its roster, on once you agree. Its toolscalendar_events,calendar_free_timeandcalendar_feedsread them read only, in your time zone, fetching each from its own host alone and at most every five minutes; it never changes your calendar, and proposes an event as an.icsfile in your share folder for you to open. The address is kept in your system keychain and given to its tools server alone: the agent is never shown it. - What you add: knowledge packs from your computer and MCP servers, each an entry of its roster that you switch on and off. Adding one, or turning on one you have not agreed to on this computer, asks you first.
- A name and a personality, when you give them, reach it at its next
message. On its first conversation it asks you for both, and saves your
answer through its Agentry tool
self_configure, which changes its name and personality and nothing else. - Agentry Helper's tools, in Agentry Desktop: the same Agentry tools
Agentry Helper has, so the Assistant can do anything the Helper can.
registry_searchandquickagent_showfind a QuickAgent and say what it may reach and how to run it (its questions, the files it takes, the keys it needs and its publisher's guide),quickagent_installinstalls one,quickagent_runruns an installed one with answers to its questions, files from its share folder and a task, andrun_resultreads the outcome; itsquickagent-useskill says how it works out what to give a QuickAgent from what you asked;installed_listlists what is installed,schedule_add,schedule_list,schedule_pauseandschedule_removekeep scheduled runs,settings_openopens a section of Settings for you, anddocs_readreads a page of Agentry's documentation. The desktop asks you first, in a dialog that names the Assistant, before an install, a QuickAgent's first run for it, a run that fetches from an address you have not agreed to for that QuickAgent, a schedule and a schedule's removal, and a No does nothing. None of these tools changes a setting, starts or stops an agent, signs in, publishes or touches a key. Run from the CLI, these tools answer that only Agentry Desktop answers them. - Your QuickAgents, in Agentry Desktop, which Agentry Helper does not
have.
quickagent_minelists the QuickAgents you publish, in your own namespace and in each organization you publish for, private ones included.quickagent_versionssays where each version stands.quickagent_fetchcopies a version intoshare/quickagents/<namespace>/<name>/for the Assistant to read and change.quickagent_revisehas the Drafter revise that folder, in Agentry for credits or on this computer with your own key.quickagent_submitsubmits a folder as a new version, or as a new QuickAgent, which is always private.quickagent_forkforks a public QuickAgent into your namespace so it can be changed.quickagent_managemakes one private, retires it or restores one that was private when it was retired, or yanks or withdraws a version. The desktop asks you first, in a dialog that names the Assistant, before every fork, revision, submission and owner action, every time: no earlier answer and no setting skips it. A submission's dialog shows the files and the capabilities that changed, and says when the QuickAgent is public that everyone who installs or updates it receives the version. Every version then goes through Agentry's checks like any other. The Assistant cannot delete a QuickAgent or make one public, nor restore one that was public when you retired it; you do that in Agentry's Publisher section. These tools reach your QuickAgents with your Agentry sign-in, which the Assistant never sees, and none changes what the Assistant itself may do. Run from the CLI, they answer that only Agentry Desktop answers them. - Meeting recordings, in Agentry Desktop with its Meeting notes on: when
its roster's meetings entry is on (off until you switch it on, and only
with its heartbeat on), its Agentry tools
meeting_arm,meeting_listandmeeting_cancelarm Agentry Desktop to record a call during a meeting on your calendar that you asked it to record. A window opens 5 minutes before the meeting and closes 15 minutes after it, records only a call the desktop detects inside it, and is refused when it would open more than an hour ahead, so the Assistant arms each meeting from a task in the hour before it. Each armed window shows in Agentry, where you can cancel it. Off, or run from the CLI, these tools record nothing. - The time: each message it is sent starts with the time now and your time zone.
- Tasks and a heartbeat. When you ask it to do something at a time, it
registers a task through its Agentry tools (
task_add,task_list,task_update,task_remove): a name, a cron time and an instruction to itself. While it runs and its roster's heartbeat entry is on (off until you switch it on), its heartbeat fires each task as a message of its own at its time, which uses your model plan. A task due while it was stopped does not run: it is told at its next message. At most 25 tasks, none more often than every 15 minutes and 96 fires a day in all.agentry agent tasks assistantlists them, and pauses, resumes or removes one. A task gives it nothing it does not already have. A chat folds a task's turn into one line; what the task is for (a reminder, something you asked to be told) the Assistant sends withtell_person, which the chat shows as a message from it. - Each start is a segment, with its own receipts and result envelope in the agent's folder under the runner home, and the conversation's record continues across segments.
- It runs without the session caps an interactive QuickAgent has: no idle timeout, no time limit and no turn limit. You stop it.
- It runs on the harness and model your runner policy names, in a container, with the same sandbox every run has: no route out but the model's.
Using Agentry: https://docs.secureagentry.net/