Pricing

Simple. Honest. Founding-beta pricing.

Pricing locks in for the lifetime of your subscription. Annual options available on every tier — Context Credits scale with usage, no per-operation surprises.

Pro
$20$10/month
Founding: 50% off for life

For individual developers. Persistent project memory across every AI tool you use.

  • 1 user
  • 1 concurrent job
  • Monthly credit allowance
  • Full core product · Stream, Atlas, Capsules
  • MCP · Cursor · Claude Code · Cline
  • Extra credits available · top up anytime
  • Agent seats add-on · $10–$15 each
Most Popular
Elite
Graph depth: call + dataflow + type
$30$15/month
Founding: 50% off for life

Full graphs + Enhanced Context. The deepest recall ContextStream offers.

  • Everything in Pro
  • Call, dataflow, and type graph depth
  • Enhanced Context for deeper recall
  • Higher credit allowance
  • Priority indexing lane
  • Extra credits available · top up anytime
Team
$40$20/user/month
Founding: 50% off for life

Shared project wisdom. Scoped governance. Higher concurrency for teams that move.

  • Everything in Elite
  • 3-user minimum
  • Shared workspace · team Stream & Atlas
  • Team governance · roles & permissions
  • Scope and per-project access controls
  • Higher concurrency
  • Extra credits available · top up anytime
All plans use Context Credits, not per-operation pricing. We don't sell agent seats — we charge for concurrent jobs and the people who benefit. Need a custom enterprise rollout? Talk to us.
01 Pricing concepts

Two units, both predictable.

No "operations" counter, no surprise quotas. Two simple things scale: how many things run at once, and how much your project remembers.

Concurrent jobs

How many things run at once.

Indexing, capsule renders, agent recalls, scheduled refreshes. Pro gets 1, Elite adds a priority indexing lane, Team adds higher concurrency. Add agent seats for $10–$15/month each.

Context Credits

How much your project remembers.

A Credit covers retrieval, embedding, and graph traversal — not raw API calls. Monthly bucket included; top up anytime.

02 Plan comparison

What's in each plan.

plans · matrix
Knowledge Stream
Personal scope
Personal scope + Enhanced Context
All scopes + team audit
Knowledge Atlas
Single project
Single project + full graph depth
Multi-project + cross-workspace
Graph depth
Module + import
Call + dataflow + type
Call + dataflow + type
ContextCapsules
Personal handoffs
Personal handoffs
Team + client-safe handoffs
ContextStream Code
Included
Included
Included
MCP server
Included
Included
Included
Concurrent jobs
1
1 (priority lane)
Higher concurrency
Context Credits
Monthly allowance
Higher monthly allowance
Higher monthly allowance
Governance & audit
Roles · scopes · audit log
Seat model
1 user
1 user
3-user minimum
Pro
Elite
Team
03 Common questions

Pricing, in plain English.

What if my project gets really large?

All plans handle projects up to ~100k indexed files comfortably. Above that, Team adds higher concurrent jobs and a priority indexing lane. If you're indexing a monorepo with multiple millions of files, talk to us — we'll size you correctly.

What happens when I run out of Context Credits?

Nothing breaks. Your AI tools still query the Stream and Atlas — they just slow down for non-priority retrievals until your monthly allowance refreshes, or you top up.

What's the founding-beta discount?

Pro, Elite, and Team are 50% off list price for the lifetime of your subscription if you start during the founding-beta window. The discounted price locks in — it never goes up to the list price as long as the subscription stays active.

What's the difference between Pro and Elite?

Elite gets full call + dataflow + type graph depth and Enhanced Context for deeper recall, plus a higher credit allowance and a priority indexing lane. Pro is the full core product with module + import graph depth.

Is there a free trial?

Pro plans include a free starter period for new workspaces. We'd rather give you enough credits to feel the product than gate it behind a contact form.

Do you train models on my data?

No. We don't train models on any of your data — full stop. See the privacy page for the full statement.

Get reusable project context, in five minutes.

One decision, one lesson, one capsule. Watch your AI remember.

Talk to us