How it worksArchitectureUse casesPricingDocsSign in

Pricing

Start free. Scale when you're ready.

Open source SDK forever. Cloud sync, team collaboration, and enterprise controls when you need them.

Free

$0/forever

The open source SDK. Local-only brain. BYO key.

  • pip install gradata
  • Local brain (SQLite + JSONL)
  • Correction capture + graduation
  • Works with any model
  • AGPL-3.0
Install the SDK
Most popular

Cloud

$20/month

Hosted brain, sync across machines, metrics dashboard.

  • Everything in Free
  • Hosted brain + sync
  • Metrics dashboard
  • Rule marketplace access
  • Email support
Start free trial

Team

$99/seat/month

Shared brains, role-based access, audit logs for up to 10 seats.

  • Everything in Cloud
  • Shared team brains
  • Role-based access control
  • Audit logs
  • Priority support
Start team trial

Enterprise

Custom

SSO/SAML, on-prem option, SLAs, and dedicated success.

  • Everything in Team
  • SSO / SAML
  • On-prem / VPC deployment
  • SLA + dedicated CSM
  • Security review + DPA
Contact sales

Prices in USD. Taxes may apply. Cancel anytime.

FAQ

Common questions

Most users see corrections drop within 10–15 sessions. The brain converges as it accumulates repeated signals.

Rules need multiple repeated signals before they stick. One bad correction stays weak and dies if unreinforced. You can also undo any rule instantly with brain.rollback().

Yes. Gradata works with any LLM: OpenAI, Anthropic, LangChain, CrewAI, local models. It sits between you and the model at the system prompt layer.

No. Gradata runs entirely on your machine by default. Zero network calls. Your corrections never leave your computer. Open source (AGPL-3.0).

Custom Instructions are static files you write and maintain manually. Gradata captures corrections dynamically and graduates them into rules that compound over time.

About 250 tokens at session start (your 10 most relevant rules). Additional rules swap in based on context. Roughly $1/month in added token cost.

Your rules are yours. Export as JSON or YAML anytime with brain.export(). No lock-in.

Yes. brain.share() and brain.absorb() let team members share graduated rules. Cloud Dashboard with team analytics coming soon.

The SDK is free and open source (AGPL-3.0). A cloud dashboard with team features, meta-rules, and weekly digests is coming soon.

Fine-tuning requires datasets, GPU time, and retraining. Gradata learns from individual corrections in real-time. Think scalpel vs cannon.