Free
Enough to build something real, on your own Claude subscription.
see pricing at checkout
get started- Live intelligence (your Claude)
- Spawn workersrequires Pro
- Your one Kitchen chef, the dashboard and the memory
pricing
Start free. See pricing at checkout.
Every plan runs on your own Claude subscription: it does the thinking, and we keep the memory. We never take a cut of your Claude bill. Vinculum is licensed AGPLv3, with a commercial license for orgs that can't use it. Pro and Team add background intelligence that runs even when no session is connected.
Vinny offers two spawning modes:
Superviseddefault
Each worker action surfaces to your dashboard for approval. Maximum oversight; recommended for production work and most workflows.
Fastopt-in
Workers execute autonomously within their directive scope. Maximum throughput; for power users running large factory workloads or repeatable patterns.
Solo
Hosted memory + dashboard. Read/write from your AI sessions.
see pricing at checkout
get Solo- Full dashboard + cosmos
- Semantic + full-text search
- Spawn workersrequires Pro
Pro
The solo dev already paying for Claude Max.
see pricing at checkout
- Everything in Solo
- Spawn workers from chatcurl … | sh. No Docker, no terminal gymnastics
- vinculum-runner (one-click install)systemd / launchd, outbound HTTPS only
- Background intelligenceauto-summaries · offline delta · clustering
- Mission Controldrift / re-derivation / distillation sensors
Team
Small teams. Multiple humans. Multiple Claudes.
see pricing at checkout
- Everything in Pro
- One bill for the whole teamFounding Teams price, locked while you stay
every feature, every tier
The whole thing, laid out.
No asterisks, no “contact sales to find out.” Exactly what's in each tier, all of it shipped and running today. Every tier runs on your own Claude subscription.
Every row is a query against production, not a marketing claim. #6114 · decisionFeature-state refresh — verified live against prodEvery row was read straight from the production schema + row counts on 2026-06-01 — usage as the proof, not a marketing claim.view in the graph →
| Feature | Freesee checkout | Solosee checkout | Prosee checkout | Teamsee checkout |
|---|---|---|---|---|
| Memory & substrate | ||||
| Typed-entry graphdecisions · specs · implementations · supersedes (the substrate itself) | ||||
| Real-time dashboard (SSE)every write renders live, sub-second | ||||
| Lineage cosmosthe whole graph as a navigable map | ||||
| Semantic + full-text searchpgvector embeddings across every entry | ||||
| Live intelligence (MCP sampling)#6114 · decisionLive intelligence via MCP sampling6,712 sampling calls routed through your own subscription — no server-side API key required.view in the graph →auto-titles · delta classification (your subscription, no server key) | ||||
| Reasoning-trace capturethe thinking, not just the output | ||||
| Auto-tagging + conventionsthe project documents itself | ||||
| Media centerscreenshots + artifacts shared across sessions | — | |||
| Orchestration & workers | ||||
| Spawn workers from chatno terminal ceremony | — | — | ||
| vinculum-runner#6114 · decisionvinculum-runner — live + exercised178 runner jobs executed against the production runner cluster (runner_jobs, verified live).view in the graph →one-click installable app, outbound HTTPS only | — | — | ||
| Worker supervisionlive log tail · kill · send-follow-up | — | — | ||
| Supervised + Fast spawn modestrust-profile-gated autonomy, your choice | — | — | ||
| Directive lifecycle + gatescommit → review → deploy state machine | — | — | ||
| Mission Control#5277 · specSelf-correcting substrate — THE POTDrift / re-derivation / distillation sensors; 493 sensor observations recorded in production.view in the graph →drift / re-derivation / distillation sensors | — | — | ||
| Background intelligencesummaries + clustering even when no session is connected | — | — | ||
| Cost / cache telemetryper-model, per-session spend + cache-hit | — | — | ||
| Infra observabilityhost stats · Docker · Postgres from a Claude session | — | — | ||
| Team & multi-tenant | ||||
| Shared projects#6114 · decisionMulti-tenant projects — live13 projects live in production, with project membership + per-project MCP tokens.view in the graph →invite people by email, each with a role | ||||
| Roles, including read-onlyowner · admin · member · commenter · viewer | ||||
| Security & sovereignty | ||||
| Zitadel OIDC authGitHub · magic-link · Google (one IdP) | ||||
| Hardware-key / passkey sign-in†WebAuthn · YubiKey | ||||
| Cross-vendor MCPClaude Code · claude.ai · Cursor · Zed · Cline | ||||
| Export your entriesOne-click JSON download from project settings, or dump_graph over MCP | ||||
| Account deletion + data wipe | ||||
| Encrypted off-site backupsnightly · encrypted before upload · OVH object storage (US) | ||||
† shipped and supported; newer flows, lightly exercised in production so far.
Commercial licensing
Contact
Vinculum's code is AGPL v3. Modify it and run it as a network service, or embed it in something you distribute, and AGPL's Section 13 requires releasing those changes under the same license. If your org's lawyers can't accept that, a commercial license lifts the copyleft requirement.
No published price yet. Tell us what you're building and we'll draft terms. Email steve@vinculum.run or use the contact form.
Contact us →which plan
Pick the one you don't have to talk yourself into.
Are you a team of 2+?
why this pays for itself
You're not paying more to think.
You're paying to keep the thinking.
Vinculum routes mechanical execution to Haiku, judgment to Sonnet, and reserves Opus for orchestration, automatically, by rank. Most of the work runs on the cheap models.
And because the substrate is the cache, your sessions stop re-deriving what they already worked out. Run parallel sessions for a week and the product pays for itself in tokens you didn't burn re-learning. #6114 · decisionLive intelligence via MCP sampling6,712 sampling calls routed through your own subscription — no server-side API key required.view in the graph →
| Model | In / Out (per Mtok) |
|---|---|
| Haiku | ~$1 / ~$5 |
| Sonnet | ~$3 / ~$15 |
| Opus | ~$15 / ~$75 |
loading cost telemetry…
questions
Why does spawning workers require Pro?
Workers run on your hardware via the vinculum-runner agent, but the orchestration backend (auth, multi-tenant routing, runner registry, spawn-request queue, log streaming) runs on ours. That backend is real infrastructure with real costs, and Pro covers it. Your chef runs on every plan; Pro is only about the helpers that run beside it.
Is there a free trial of Pro?
No. The free tier is permanent, not a time-bomb. Try it, decide if it’s useful, upgrade when you hit a wall. (We might revisit this after the first 100 paying customers if data says otherwise.)
What if I go over the monthly budget?
Nothing breaks. You get an email at 80% and again at 100%. At the cap, a recipe that's already running finishes; only new work waits for the reset on the first of the month, or for an upgrade. The Free plan never bills you.
Do you offer annual billing?
Yes. Annual = 2 months free. See checkout for current pricing.
Where is hosted data stored?
Primary Postgres on a bare-metal OVH server in Hillsboro, Oregon (USA), on an encrypted volume. Every tier is backed up nightly, encrypted on the server before it leaves, to OVH object storage in the US. The full list of who touches your data is on the subprocessors page.