Graph-Native Agent Studio0%
Graph-Native Agent Studio — V2.0

The Studio Agents Run On.

One prompt in. Research, design, code and deployment out. BSAI compounds context across every step — so nothing gets lost between the idea and the ship.

Get Started
Scroll to enter
01 Studio

One prompt in. Research, design, code and deployment out.

02 Benchmarks

A capacity table, seen from here.

03 Skills

Research, build, deploy — full-stack.

04 Pricing

Run the harness yourself, or let us run it.

StudioV2.0

Every surface is a different shape.

Chats, Design and Code are separate rooms in the same studio — and the same graph of files, decisions and deploys runs underneath all three.

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.

Watch It Work
4,000Agent runs included
25MManaged inference included
8Sub-agents / run
$0Forever · MIT licensed
BenchmarksIncluded

A capacity table, seen from here.

Self-hosted is the same MIT-licensed harness, unlimited. Hosted plans pay for infrastructure and managed inference — not features.

AGENT RUNS / MONTHIncluded
300Free
4,000Pro
10,000Team / user

Self-hosted and Enterprise: unlimited runs

BUILT ON A REASONING CORE01 — 03
01 · Graph-native memory

“Similarity isn't relevance. Context is everything.”

02 · Compound intelligence

Vector search retrieves fragments. BSAI runs on a graph of your entire project.

03 · Continuous runs

One thread, full memory — from the first prompt to the deployed site.

THREAD — 001.RUNBSAI · Planner
$ bsai run "Research mRNA delivery, build a landing page, deploy to Vercel"
01✓ Scan 47 papers on mRNA delivery
02✓ Synthesize findings → research.md
03✓ Wire deploy pipeline
04→ Deploy preview → vercel.app
Agent skillsFull-stack

Research, build, deploy — full-stack.

A growing library of capabilities the studio can run end-to-end, compounding context as it goes.

01

Deep Research

Scan papers, synthesize findings, write source-backed reports.

4 min
02

Full-Stack Builds

Architect and ship applications from a single prompt.

5 min
03

One-Prompt Deploys

Push to production with the pipeline wired for you.

6 min
04

Shader-Grade Design

Living, animated interfaces with real art direction.

5 min
05

Graph Context

Every file, decision and deploy connected — nothing lost.

6 min
Simple pricing — no surprises

The Studio Agents Run On.

BSAI 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.

Annual billing saves two months — switch above.
Free
$0 / month
Hosted, no card
  • 300 agent runs / month
  • 60 messages / day
  • 2M tokens / month
  • 1 concurrent task
  • 5 scheduled tasks · 2 projects
  • 1 GB workspace storage
Start free
Most popular
Pro
$19 / month
For daily driving an agent
  • 4,000 agent runs / month
  • Unlimited messages
  • 25M tokens / month
  • 4 concurrent tasks · 4 sub-agents
  • Unlimited scheduled tasks · 50 projects
  • 50 GB storage · long-term memory
  • Deploy sites and dashboards from a run
Subscribe
Team
$49 / user / mo
Shared skills and runs
  • 10,000 agent runs / user / month
  • 60M tokens / month, pooled
  • 8 concurrent tasks · 8 sub-agents
  • Shared skill library and agents
  • Roles, seats and usage dashboard
  • 200 GB pooled storage
Start a team

Self-hosted is unlimited and free forever — no card, no quota. Hosted plans include model inference on our managed keys; bring your own keys and runs stop counting against your quota. All five plans →

Start Building