PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchiTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
1Presence is a software-based AI assistant and automation platform built around persistent context: instead of treating every conversation as a fresh start, it is designed to retain information about a user and make that information available across chats and connected tasks. Founder Jon Kafton describes its memory as a structured graph plus an editable, Obsidian-compatible markdown vault, with connectors, specialist agents, scheduled routines, dashboards, and workflows layered on top. Those are the founder’s and app listing’s descriptions—not independent findings about reliability, privacy, or security.
What 1Presence is designed to do
Kafton says he had repeatedly built context-carrying AI backends for earlier projects and wanted a reusable system rather than rebuilding them. He presents 1Presence as the hosted version: an assistant intended to learn a person’s context, preferences, ongoing projects, and things they want to track, then carry that context from one conversation to another. The Google Play listing similarly describes an assistant that retains context and connects to digital tools. These descriptions explain the product’s intended behavior; the reviewed sources do not measure how accurately it remembers or performs.
That makes 1Presence broader in scope than a chat interface alone. Its stated design combines memory with connected services and task execution. Whether those capabilities suit a particular workflow depends on the connectors, permissions, and features available in the user’s account.
What it remembers, and how users can inspect it
The founder describes two complementary memory layers:
#1 Best Overall
- A structured memory graph records facts and relationships, such as how people, projects, preferences, and plans are connected.
- A markdown vault stores notes, files, and documents as plain markdown, organized and interlinked in an Obsidian-compatible format.
Kafton says users can browse and edit the vault, inspect the memory graph, see which facts were used in an answer, and correct or remove inaccurate information. The stated aim is to make persistent context visible and manageable rather than a hidden profile. As Kafton puts it, “You should never have to wonder what your AI knows about you.” That is the founder’s design position, not an independently tested guarantee about every answer or stored fact.
The founder also says memory is represented in a compact notation intended to reduce prompt-token use. No comparative benchmark is provided, so this should be understood as an implementation choice rather than evidence of a quantified cost or speed improvement.
How it extends beyond chat
Connectors and drafted actions
The Google Play listing names Gmail or Outlook, calendars, Drive or OneDrive, Notion, Slack, GitHub, and CRMs as examples of connected services. It says the assistant can draft replies and that it will not send or post anything without the user’s approval. These are developer-provided descriptions, and the available connectors and behavior may change as the app evolves.
Specialist agents and workflows
Kafton describes named agents with their own skills and connector permissions, multi-stage workflows that can hand work between specialist agents, and human approval gates. The product account also mentions structured datasets and refillable document templates. Together, these features are presented as a way to move from asking questions to coordinating repeatable work. The sources do not provide independent reliability testing or examples sufficient to establish how well a given workflow performs.
Routines, dashboards, and meetings
The founder lists recurring routines, live dashboards, and meeting recording, with transcripts and summaries filed to the vault. The Play listing also highlights voice interaction, meeting notes, integrations, and cross-device use. These are feature descriptions, not a guarantee that every routine or integration is available in every region or account.
What happens when an agent runs on a schedule
For organization use, the founder describes separate personal and company spaces, an organization-level shared vault and memory, team-scoped access, purpose-built shared agents, and seat billing into a common credit pool. The stated permission model resolves an agent’s access from the member who invokes it, rather than from the person who created the agent.
A scheduled run has no human invoker. According to the founder’s account, it therefore runs within the scopes bound to that schedule and is recorded as the scheduler. That distinction matters when designing recurring jobs: the creator’s permissions should not be assumed to define the run’s access, and a schedule should be configured with only the scopes it needs. The source does not independently verify enforcement of these controls.
How the founder describes its infrastructure
Kafton says each user receives a dedicated pod on Google Kubernetes Engine (GKE), isolated and internal-only, with GCP Workload Identity and a service account scoped to that user’s data. In this account, state is stored in Google Cloud Storage (GCS) and Firestore, while the pods are stateless, start when the first message arrives, and scale to zero after ten minutes idle.
These are architectural claims from the founder’s article. The reviewed sources do not include an independent security audit, configuration review, threat assessment, or evidence that would establish security outcomes. Organizations evaluating sensitive data should request assurance appropriate to their requirements rather than treating an infrastructure description as proof of protection.
Privacy, portability, and evidence limits
The Google Play listing says user data is not sold or used to train models, markdown notes can be exported, accounts and data can be deleted in-app, and data is encrypted in transit. It also provides developer-declared data-safety details. Those statements are from the app listing; they should not be read as an independent verification, a complete account of data handling, or a broader promise about privacy than the listing makes.
The founder’s emphasis on an editable vault and the listing’s export claim make portability and correction central points to examine before relying on the service. Check the current app disclosures and terms for the exact data covered, export and deletion behavior, connected-service access, and retention details relevant to your use. The reviewed sources do not establish measured memory accuracy, comparative model quality, user adoption, or independent security testing.
Free tools Windows power users keep installed
One-click scans. No signup required.
Pricing and availability described in the sources
A surfaced copy of the founder article lists the following personal plans and says lasting memory, the vault, connectors, and unlimited agents are included across all three. The article says tiers differ in credit headroom and thinking depth.
| Plan | Monthly price reported | Included token credit reported |
|---|---|---|
| Starter | $8 per month | $5 |
| Pro | $25 per month | $16 |
| Max | $60 per month | $42 |
These figures and terms are reported in a 2026 copy of the founder article, not verified against a live checkout. That article says usage stops by default when credit is exhausted, optional auto top-up has a monthly cap, purchased credit does not expire, and refunds can be requested. Confirm current prices, included credit, and billing terms before subscribing.
The founder article says 1Presence launched on August 27, 2026, and could be tried without a card. The Google Play listing reports an update on September 7, 2026. The sources establish a Google Play listing, but do not establish availability in every country or on every platform.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Who may find the design relevant
Based on its described features, 1Presence may be worth examining if you want an assistant that can carry context across sessions, let you inspect and edit stored notes, connect to work services, or coordinate repeatable tasks. For a team, the relevant questions include how shared and personal spaces are separated, how access is scoped for agents and schedules, and whether the available independent assurance meets the organization’s requirements.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minuteIt is not possible to conclude from these sources that 1Presence remembers more accurately, performs better, or is more secure than another assistant. A careful evaluation should focus on memory visibility and export, the connectors and permission controls your workflow needs, approval behavior, scheduled-job scopes, current usage terms, and independent security evidence.
Quick Recap
Sources
- Jon Kafton’s founder article, republished on DEV Community. The page says it was originally published on 1presence.com on August 27, 2026; DEV shows September 25, 2026.
- 1Presence on Google Play, including developer-provided feature and data-safety descriptions; listing update reported September 7, 2026.
- Pricing details in a surfaced copy of the founder article; prices and terms are time-sensitive and were not verified at checkout.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
