Shape 01 · Chats
Where a run starts.
The planner takes the prompt, scans, synthesizes and writes back into the same thread.
300 runs / month on Free
One prompt in. Research, design, code and deployment out. BookiStudios AI compounds context across every step — so nothing gets lost between the idea and the ship.
Every file, decision and deploy connected — nothing lost.
The same thread holds the scan, the writes, the pipeline and the deploy. Context is not re-explained between steps, because the graph remembers it.
Demo thread from the live landing page · illustrative command
✓ Scan 47 papers on mRNA delivery✓ Synthesize findings → research.md✓ Wire deploy pipeline→ Deploy preview → vercel.appChats, Design and Code are separate rooms in the same studio — and the same graph of files, decisions and deploys runs underneath all three.
The planner takes the prompt, scans, synthesizes and writes back into the same thread.
Shader-grade design: real art direction, not a template with the logo swapped.
Applications built from a single prompt, with the deploy pipeline wired for you.
A growing library of capabilities the studio can run end-to-end, compounding context as it goes.
Scan papers, synthesize findings, write source-backed reports.
Architect and ship applications from a single prompt.
Push to production with the pipeline wired for you.
Living, animated interfaces with real art direction.
Every file, decision and deploy connected — nothing lost.
Sites that keep working for you after the build.
Self-hosted is the same MIT-licensed harness, unlimited. Hosted plans pay for infrastructure and managed inference — not features.
| Capability | Self-hosted | Free | Pro | Team |
|---|---|---|---|---|
| Agent runs / month | Unlimited | 300 | 4,000 | 10,000 / user |
| Messages / day | Unlimited | 60 | Unlimited | Unlimited |
| Included tokens / month | Your keys | 2M | 25M | 60M pooled |
| Concurrent tasks | Hardware-bound | 1 | 4 | 8 |
| Sub-agents per run | Unlimited | 1 | 4 | 8 |
| Scheduled tasks | Unlimited | 5 | Unlimited | Unlimited |
| Workspace storage | Your disk | 1 GB | 50 GB | 200 GB pooled |
| Long-term memory | Local | 7-day | Persistent | Persistent + shared |
| Custom skills & MCP servers | Yes | 3 skills | Unlimited | Unlimited + shared |
| IM channels (Slack, Telegram…) | Yes | 1 channel | All channels | All channels |
| Deploy sites with a database | Self-managed | — | Yes | Yes |
Self-hosted and Enterprise: unlimited runs
“Similarity isn't relevance. Context is everything.”
Vector search retrieves fragments. BookiStudios runs on a graph of your entire project.
One thread, full memory — from the first prompt to the deployed site.
No van-metric theatre. Every figure below is a line item a paying customer actually receives, taken from the published plan table.
0
Agent runs included0M tokens
Managed inference included0sub-agents / run
And 8 concurrent tasks$0
Forever · MIT licensed“Originated from Open Source, give back to Open Source.”
BookiStudios AI is MIT-licensed and free forever when you self-host. The hosted plans add managed sandboxes, persistent memory, and scheduled agents — at roughly a third of what hosted-only agent products charge for the same capability tier.
LAUNCH20 20% off
OSS50 50% off first year
Annual billing saves 2 months · seats 1–50 on Team
Hosted plans include model inference on our managed keys. Bring your own keys on any plan and runs stop counting against your quota. Need more on a plan? Top up anytime — no contracts, no lock-in.
It compounds context across every step of a run — research, design, code and deployment live in one connected graph, so nothing is lost between the idea and the ship.
No. Hosted plans include managed inference. Self-hosted runs on your own keys.
Yes. Threads, memory and skills export as plain files and import into either.