Your personal context layer

Your knowledge,
connected.

Private by design and local-first: drop in anything, and stoa builds an ever-evolving wiki + knowledge graph you own.

Local-first — you own your data & your models Works with the tools you already use

You drop in anything

meeting-notes.pdf

“add what I just read”

Re: pricing (email)

How it works

You bring the raw material.
stoa does the thinking work.

Ingest

Any unstructured file

Understand

Smallest claims + entities

Reconcile

One name for one thing

Living graph

Stays coherent for you

Share & reach

Team, agents, anywhere

Every step runs automatically — no tagging, no folders, no configuring.

Why stoa is different

The graph finds what search can't

However you work — solo or as a team — stoa turns your pile of context into answers you can trust.

Months of meeting notes, specs, and threads about a launch.

On your own

You scroll Slack and three docs, half-remember who owns what, and rebuild the picture from scratch every time someone asks.

A notes app or AI assistant

DocsSlackDrive

search docs & threads…

spec.doc

sync notes

thread

not linked

no source cited

A good assistant has your docs and threads and will pull the ones that mention the launch. But it retrieves by similarity — it doesn't hold the relationships between the pieces: the decision, who made it, and how the facts have evolved since.

With stoa

“What's blocking the Q3 launch?”

Three blockers: pricing sign-off, the Acme billing-platform integration, and reseller approval — the critical path runs through that integration.¹² stoa followed decision → owner → what changed, and retired the earlier go-live date instead of returning both.

How stoa got there

Connected the facts · cited 3 of your sources

Why it's called stoa

The discipline behind the name.

ΣτοάGREEKstoá

The painted porch where Stoic philosophers — the founders of propositional logic — met to think out loud, taking big ideas apart into small, clear claims and making sure it all held together.

stoa does exactly that with your knowledge — the same discipline, run for you.

Stoic philosophers in conversation on an ancient colonnaded stoa at golden hour

Pricing

Free forever. Managed when you want it.

stoa is free and complete. The managed edition removes the hassle — it never withholds capability.

Self-host

Free

Open source · run it yourself

$0forever

The full engine, free — nothing held back.

The full engine — nothing held back

Private by default — you own your data

Bring your own model key, or run fully local

Unlimited brains & documents

Self-hosted MCP — connect any agent

Cited chat + maintained wiki + graph

Managed

We host it — hassle removed

First access & special pricing for people who join the waitlist.

No spam — opt out anytime.

Everything in Free, hosted for you — plus:

Zero-ops hosting — of self-hosting

Always-on, remote MCP server — reach your brains from any agent or tool, fully hosted, behind auth

1-click sharing — invite collaborators you trust to access and jointly build out a brain, complete with a full audit trail

An online portal to reach your instance from anywhere, securely, from any device

Private by design

Your data — never retained, never shared.

Always on — , , continuous backup

Per-tenant encryption —

Maximum privacy & managed inferenceOptional add-on

By default, you bring your own model key.

Rather not think about model providers? Let us run your for you — pay-per-use, with full cost guardrails — so no one, not even the model provider, can see your data. It's a no-human-access architecture: the infrastructure itself enforces the privacy, built on confidential computing.

Teams & enterprise? Shared brains, SSO, and support for your org.

Open source

Running in a few minutes — and it's all yours.

Install Docker, point stoa at one model key (or a local model, free), and bring the whole stack up with one command. No account required to start — and nothing comes to us: your files, your keys, your machine.

Install Docker — The only hard prerequisite.

Point it at one model provider — Set two env vars — the provider and your key. That's all stoa needs from you.

docker compose up — Brings up the app, Postgres, and migrations — one command.

Open localhost:8000 — Create a brain, drop a doc, ask a question.

Self-host from $0 fully local. We publish guidance and one-command quickstarts for two reference deployments — a light box for one person, and a production setup for teams.

Star the repo

~/stoa

# 1 · point stoa at your model provider
export STOA_LLM_PROVIDER=openai
export STOA_OPENAI_API_KEY=sk-...
 
# 2 · bring up the whole stack
docker compose up
 
# 3 · open the app
open http://localhost:8000

stoa.wiki/brains/greek-philosophy Wiki

Pages

Concept24 claims

Propositional logic

The logic your computer runs on — invented 2,000 years early. Propositional logic treats whole statements as single true/false values joined by operators like "if… then", "and", "or".

Why it matters today

This is exactly how a computer thinks: every if/else a program runs is propositional logic in action. It became Boolean algebra and the switching circuits inside every chip.

Who founded it

The Stoics — systematized by (3rd c. BCE), over two millennia before the transistor. (Aristotle founded the other branch, term logic.)

Built on — "if… then", "and", "or"
Codified as the five — the first rules of inference

Frequently asked

A personal context layer for everything you learn. Drop in your files — and stoa compiles them into a maintained knowledge graph and a cited wiki you can talk to, always showing its work. Instead of re-reading your files on every question, it builds the picture once and keeps it current as you add more.

Each of these nails part of the job — a chatbot reasons, a notes app organizes, an AI-memory tool remembers. None of them turn your own documents into one maintained, entity-resolved, fully-cited knowledge base you can reach from anywhere and actually own. stoa is built to do all of it — and the best part is it's not meant to replace the tools you already use. It's the knowledge layer underneath them: reach the same brain from your chatbot, your editor, or your terminal.

	Chatbot	Notes app	AI memory	stoa
Turns any document into a retrievable corpus	connects to sources; stores nothing itself	stores, doesn't extract	no denoising or cleaning
Maintained knowledge graph		graph visualization, not a graph model	conversation-recall memory, no cited wiki over it
Retrieval beyond semantic search (keyword + graph walk)	possible, but closed — no visibility into how		some fuse signals; varies by tool
Every answer cited to your source	cites files, but facts aren't grounded — can hallucinate		some cite; depth varies
Programmatic access — MCP + CLI	calls out to sources	limited, at times behind a paywall	some gate MCP behind a paywall; often no CLI	MCP + CLI
Shareable — invited people query and grow one brain, together in sync		real-time editing	per-user partitions, not shared co-writing
Open source — inspect it, self-host it, own it		a few are; most aren't	typically closed & hosted

full partial none

Yes — the full engine is free and open source, self-hosted on your own machine with your own model key, and nothing comes to us. The managed edition is for people who'd rather not run it themselves: hosted, zero-ops, private by design — you'd pay for the convenience, never for capability.

Your knowledge,connected.

You bring the raw material.stoa does the thinking work.