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.
Verifiable history · correction · deletion · export — on every plan
Get startedMore room to chat, connect and build a shared history. Includes 6,000 monthly compute credits. Early price locked for life.
Everything in Free + more monthly compute, voice and optional prepaid credit top-ups. Usage receipts, not message limits. No automatic top-ups.
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 AlivePay for actual compute, not message count. 1,000 credits = $1 usage allowance. Verified model cost × 2 determines usage; input, output and cached tokens follow the provider receipt. Included credits reset on the first of each UTC month and do not roll over. Purchased credits never expire, are spent second, and remain usable after cancellation. Extra credits: 5,000 for $5 plus applicable tax, subscribers only. No automatic top-ups, overdraft or retroactive charges. History, correction, deletion and export stay accessible when credits run out. Background memory maintenance does not consume chat credits. Plugin hosts pay for their own model inference separately.
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.
Hosted chat uses managed models; no API key is needed. We charge verified provider USD cost × 2 × 1,000 credits, not a fixed amount per message. Short answers, cached context and different models cost different amounts. A tool-assisted answer can include several model rounds. Missing or unverified usage is not charged. See your token counts and credit receipts in Plan & billing.
No automatic top-ups or balance overdraft. A credit pack is a one-time checkout that you explicitly approve. Free accounts cannot buy credits; subscribers can buy 5,000 credits for $5 plus applicable tax. Subscription cancellation does not delete history or purchased credits.
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, contact@getthroughline.ai.