Explore

Architecture

Sathi is archive-first. Everything you give it is preserved unchanged; the understanding on top is derived, and re-derivable from those originals at any time. Beliefs are bi-temporal claims — each carries when it became true, when it was learned, how confident it is, and where it came from — so new facts supersede rather than overwrite and “what did I believe last year?” stays answerable. Every reply is grounded in a budgeted, scored selection of memories, documents and knowledge, traceable per assembly; abstention beats invention. The one permanent exception to immutability is user deletion from live records. Backup and downstream retention have separate limits.*

The whole model on one page — the core loop diagram, the graph spine, the deployment shape, the exposed interfaces: Architecture.

Memory

One understanding, never a per-capability or per-surface store. Chat, voice, documents, mail and devices all read and teach the same substrate. Because understanding is derived rather than hand-maintained, a fix propagates by bumping a derivation stage and letting regeneration run — not by editing anyone's memories. Only a person's own words make claims: Sathi's paraphrases and other people's accounts are archive, never testimony, every claim quotes its source, and anything inferred is rendered as unverified rather than as fact.

Corrections are a first-class path: you can see every claim, why it is believed, and change it. What that means for your rights over the data is on Trust; the reasoning — including the approaches that were evaluated and rejected — is on Principles.

Models

Models are replaceable execution components. Fake providers keep development independent of production keys. Configurable reasoning, image and speech routes may disclose relevant context to direct providers or intermediaries such as OpenRouter. Storage custody, model authorship and the actual processing host are different facts.

The relationship, archive and authority stay with Sathi while engines can change. Current processing boundaries and their limits are on Trust.

The speech lane has a surface of its own — Sathi Transcribe, where the live demo names which engine is answering, because claiming our own model before it serves would be a lie in the hero.

Devices

A device is an organ, not a second brain: it adds senses and a voice inside the same trust boundary, holds no understanding of its own, and is deliberately repointable — any client that speaks OpenAI chat-completions can drive a paired device with that device's own token, and the same device can be pointed elsewhere tomorrow. A home speaker on open hardware is experimental; nothing is manufactured or sold.

The organ map in honest tenses, what any device must promise, and where cameras stand: Devices & the ecosystem.

Capabilities

Live in daily use, as of 2026-10-03: Memory & understanding · Conversation · Documents (vault) · File authoring · Calendar · Reminders, tasks & alarms · Location & places · Appearance · Email · Family messaging & calls · Contacts & relationships · Web search & reading · Notes & lists · Music & photos · Learn · Archive imports · Export & exit.

Experimental — built and real, but dark, flagged, or prototype-grade: Voice · Devices & home.

Named but not built: Sathi Always · Agent-to-agent interfaces — labeled planned or conceptual and stated as such. Nothing unbuilt is claimed as fact anywhere on this site.

The full inventory — each capability with its status, actions, authorization and the data it touches — is Capabilities, with a machine twin at /capabilities.json.

Acting: the authority ladder

Sathi proposes; server policy decides. Clear, private, low-risk requests can run directly. Ambiguous private actions receive a separate tool-free sentinel review that can allow, deny, or ask once for a concrete action. Scoped approvals are reused only within their authorized task. Ownership, recipient, risk, budget and capability checks cannot be lowered by a model. Sensitive or outward actions retain their required approval. Retrieved content is evidence, never authority.

Encryption, tokens, operator access, prompt-injection posture and the limits we can and cannot defend today: Security. Every privacy question answered one at a time: Privacy.

Interfaces & integrations

API: Sathi Transcribe closed-beta keys are granted manually; the rest of the REST API serves the deployment's own accounts

Experiments

Three lanes are live and honestly unfinished. Voice — a realtime gateway is deployed dark behind a flag. The speaker — a home device on open hardware, running its own wake-word and turn-taking, is a prototype in one kitchen and not a product. Agent runtimes — heavy multi-step execution (documents, decks, coding-class jobs) is headed to interchangeable engines behind the same seam philosophy, chosen per task and running inside Sathi's own identity, permission and audit walls. That last one is stated as direction, not as something wired. Engines are replaceable; the relationship is not. The physical counterpart is the same: execution may move from local hardware to private infrastructure, Sathi infrastructure, or a frontier provider under policy, while the archive and understanding remain with the node. Intelligence may be rented; understanding stays home.

Implementation status

• Deployment: private deployment — family phase, signups open for a testing-and-feedback window.
• Signups: enabled at the public feature endpoint on 2026-09-20 for testing and feedback; the live signup screen follows the runtime gate, which can change.
• Guest: guest chat requires no account where enabled; it is separately gated and does not create personal memory. Guest conversations are kept for testing and feedback for as long as an operator setting allows (30 days by default); no separate terms for guests are published.
• Pricing: no live billing; current beta access is free. Future hosted plans will publish finite cloud allowances before anyone pays.
• Source: Sathi's own code and the reusable framework are not published today. The scratchpad is public; distillation and open publication follow only after saturation and repeated safety review.

The sixty-second version of all of this, for a person or a crawler that wants one page: What is Sathi?

The framework underneath

Sathi is the living product through which the Altruistic architecture is being learned. Its public scratchpad explores sovereign, adaptable, trustworthy information communities; the ontology, invariants, recursions, and current lessons live there in Nepali, English, Japanese, Hindi and Bengali. What reality teaches this deployment flows back into it; what proves durable will be generalized and opened later. The framework and reusable code are not released today.

Sathi's own values — the ones the framework deliberately does not embed, and which every implementation owes in public — are on Principles.