Today every person who opens the chat gets their own small computer (a container) running a full coding agent. The new design gives every conversation a tiny always-ready home instead, and borrows the best ideas from OpenClaude's agent loop without copying its code.
OpenClaude is excellent at one thing: running one agent for one person on one machine. Three habits make it single user.
To move from Claude to another model it overwrites the process's environment variables. Two people in one process would overwrite each other's keys.
Session id, working folder and running cost live in one global state object. A second person would share them.
Settings, keys, memory and team mailboxes are files on the machine. Its server and daemon modes are empty stubs.
Our chat today has the same shape for a different reason: it runs the Claude Agent SDK, the Claude Code harness, which expects a machine. So each person holds a container (half a CPU, 4 GB memory) that stays awake 30 minutes after their last message. We cap it at 60.
Each conversation is a Durable Object: a tiny named home on Cloudflare's network with its own small database. The transcript, the open approval cards and the turn in progress live there. Any Cloudflare machine can wake it in milliseconds, so there is nothing per person to boot.
Where OpenClaude rewrites its environment, the router decides provider, model and key for each call and passes them along with that call. Thousands of people with different models share the same code safely. Keys come from the encrypted store per request.
OpenClaude's best idea: a loop that always ends with a typed reason (done, needs a tool, too long, retry) and gets its model call injected. We write that loop clean room inside the object. Every tool call is guaranteed a result, so an aborted turn never corrupts the chat.
Between messages the object hibernates. A hibernating object costs nothing, unlike a container that bills memory for 30 idle minutes. When the tab closes mid-turn, the object finishes the turn anyway and replays it on return.
Borrow the patternfrom OpenClaude, written clean room Keepfrom Tantra chat today Build newin the PRD Drop
Model tokens are over 95 percent of the cost in both designs. The platform cost falls from cents to fractions of a cent, and the model cost falls because the script engine parses answers with a cheap call and only writing goes to Opus.
| Today | Merged | |
|---|---|---|
| Compute for that hour | 1,000 containers awake: about $42 | 1,000 objects running turns: about $5.80 |
| After everyone stops | Containers bill memory 30 more minutes: about $20 | Objects hibernate: $0 |
| Start-up wait | Seconds per cold container, "starting up" past the cap | Milliseconds; past the model rate limit people queue with a position shown |
| Ceiling | Our cap of 60, then cost | The AI provider's rate limit (checked first, FC-00) |
| Input | Value | Source |
|---|---|---|
| Everyday message today | $0.15 average on Opus 5.5 (3 to 4 model calls) | Measured on 20 typical questions, CHAT_COST_PER_MESSAGE.md, 16 Nov |
| Funnel build today | about 40 messages at $0.25 (change turns carry the full funnel tool list) | 19 Nov live test: 17 answers, about 40 approval rounds |
| Funnel build merged | 40 answers parsed on Sonnet at about $0.017, 15 writing turns on Opus at about $0.20 | PRD: script engine, phase-scoped tools under 8k tokens |
| Everyday message merged | Opus about $0.08, Sonnet about $0.04 (cached 1 hour prefix) | Opus 5.5 $4 / $20, cache read $0.20; Sonnet 5.5 $2 / $10, cache read $0.10 per million tokens |
| Container | standard-1: 1/2 vCPU, 4 GiB, about $0.042 an awake hour; 50 awake minutes per visit, 8 messages a visit | Cloudflare Containers pricing: memory $0.0000025 per GiB-s, CPU $0.00002 per active vCPU-s |
| Durable Object | 128 MB while a turn runs, about 20 s a turn; $0 hibernating | Cloudflare Durable Objects pricing: $12.50 per million GB-s, hibernation not billed |
| Own provider | Model cost moves to the customer's own key; Tantra pays only platform | Owner decision, 19 Nov |
Estimates, not invoices. Phase 4 of the PRD replaces them with measured cost per completed funnel from the load test.