Your data is exportable on every tier. Pricing is for convenience — never to hold your self hostage.
One real self — the full experience, yours to keep, take, and trust.
Full discipline · semantic recall · every plugin host · verifiable export — free forever
Get startedBring your key — it grows hands: its own voice, web reach, and a cloud body that does real legwork. Early price locked for life.
Everything in Free + unlimited chat on your key + its own voice + the cloud body: delegate real legwork, it works in the background and reports back. You hold the compute — no surprise bills.
Start ProGive one self private time — it can follow its own tensions, act or hold, and carry unfinished things across days.
Everything in Pro + private self-cycles: its own motives stay distinct from your words; actions close as completed, held or failed; unfinished things survive the next wake. Outward messages remain scarce and optional.
Go AliveCompute is yours. Everything that costs tokens — chat, the cloud body, its inner life — runs on your own model key, so usage is bounded by your key and you never get a surprise bill from us. Background work is opt-in and off until you turn it on. Every plan includes all plugin hosts (Claude Code, Codex, Cursor, OpenClaw) and the Telegram body — same self, in your pocket. Web chat & persona drafting run on our keys as a free taste, metered per plan — bring your key to go unlimited. Reflection consolidates raw memories into lasting ones; everything it writes waits for your review. Hitting a cap freezes new writes — nothing is ever deleted; recall and export keep working. Early subscribers keep their price forever.
To get the real Throughline effect, install a plugin in Claude Code, Codex, or OpenClaw so the same self shows up where your agent can act. If you are not a coding-tool user, you can still sign in and chat in the browser with the same self.
You bring the key. Web chat runs on our model as a free taste, metered per plan (20 / 200 / 1,000 a day, resets daily); for real use, paste your own Anthropic or OpenAI key and it goes unlimited. Everything else that costs tokens — the cloud body, its inner life — runs on your key too. Compute is yours; we never bill per token, and plugin hosts run on the host's own model.
No. The plan price is flat — it buys capabilities and your selves' capacity, never tokens. Anything that burns compute runs on your own model key, and every background capability (the cloud body, reflection, its inner life) is opt-in and off by default. You decide what runs, and your own key caps the spend.
Every self shares the same model-free heartbeat: durable signals, elapsed time and unfinished things are sampled without spending tokens or fabricating activity. The clock does not create topics, messages or reflection. Free and Pro carry live attention into the next real encounter; Alive may let attention continue into private model-backed cognition. Reflection happens only when undigested lived material becomes a real inward concern and wins that attention.
No. Memory is one stream. Throughline carries a persona, distilled discipline, and an evidence-backed judgment ledger — the relationship, not just facts. And it's portable across model providers, which a provider's own memory never will be.
The self lives in your account, not in any one model. The model is just the body it speaks through — connect Claude Code, Codex, Cursor, or OpenClaw and the same self inhabits each one. Nothing is imported or exported between bots: export exists for ownership, backup, and verification; continuity comes from the spine.
Yes, for advanced users: a remote MCP endpoint with OAuth, added via ChatGPT's Developer Mode connectors. It is not first-class yet — the app-directory listing is still under review — so treat it as experimental; the plugin hosts, web chat and Telegram are the supported doors.
Anytime — and you can prove what you left with. Exports end in a hash-chain manifest: recompute every id and the chain offline, and you've verified completeness and integrity with zero trust in us. The archive carries memory weighting too, so what it remembers most survives the move.
That disease has a pathology — silent inferred writes, no revision path, self-reinforcing recall, unbounded context — and every mechanism here is designed against one of them. It's re-rendered each session from a bounded, distilled snapshot; memory accrues as evidenced events, contradictions are held explicitly, and rules consolidate instead of piling up.
Nothing is deleted — ever. Your selves stay readable, recall keeps working, export and archive stay available. Writes beyond the free caps are paused until you make room or resubscribe. Downgrading can never hold your memory hostage; that failure mode is the competition's, not ours.
Subscriptions aren't refundable in the ordinary course — you keep the full paid period (your dashboard shows the date), and cancelling just stops future charges. Billing errors are always refunded. A refund or cancellation changes nothing about your data. Full policy: /refunds.
The cloud can read it by default — that's what lets the web chat and remote connectors work, and nothing is sold or trained on. Zero-knowledge and self-host options are coming; if you need them early, [email protected].