spooling
Open source · Built on Strands

One memory.Every session.Across every agentic assistant.

Spooling indexes every AI coding session across your tools into one searchable memory. Spooling Cloud makes that memory shared across your team. It's live now and free while we're in early access.

pipx install spooling && spooling login

app.spooling.ai/dashboard
Sessions
Messages
Tokens
Providers
Providers
Claude Code
92%
GitHub Copilot
22%
Cursor
14%
Gemini Code Assist
8%
Kiro
4%
Agents (2)
Manage →
GitHub Agent
gemma3:1b · 41 tools
Spooling Assistantdefault
gemma3:4b · 5 tools
Recent sessions
View all →
10 providers supported · Aider next
Zero telemetry. Your sessions stay yours.
GitHub stars
Two products, one CLI

The OSS engine. The Cloud SaaS. Same install path.

Every developer installs the same OSS spooling engine. spooling login is what connects it to a Spooling Cloud workspace.

OSS engine · runs on the laptop

Spooling

The open source CLI and local indexer. One pipx command, every session from every AI coding tool you use lands in your own pgvector index. Searchable by you, on your machine, MIT licensed. Free forever.

Install the OSS
Team SaaS · runs on our infra

Spooling Cloud

The hosted cloud the OSS engines push to. Many laptops feed one shared workspace, with cross-teammate search, per-person and per-project views, Google and GitHub sign-in, and an MCP endpoint your agents can call. Free while in early access.

Get started free
Architecture

Many laptops. One memory.

Each engineer's OSS spooling engine indexes their sessions locally. spooling push ships them to Spooling Cloud, where they pool into a shared team workspace your teammates and agents can search.

YOUR LAPTOPSSPOOLING CLOUDYOUR TEAMalice@laptopOSS spoolingClaude Code · Cursorben@laptopOSS spoolingCodex · Claude Codechen@laptopOSS spoolingCursor · Copilot · Kirospooling pushapi.spooling.aiFastAPI · Postgres + pgvectorMulti-tenant Postgresrow-level security per workspaceShared team workspacecross-developer searchapp.spooling.aisessions · search · teamsMCP endpointagents call as a toolREST APIpush · search · stats
left: OSS engine, MIT, your laptop, your data.
middle: Spooling Cloud, hosted and multi-tenant. Free in early access.
right: the web app, the MCP endpoint, and the REST API.
Features

Everything your AI sessions
should already do.

Spooling turns the opaque stream of AI coding sessions into a structured, searchable history you actually own.

Semantic search

Local embeddings mean you find sessions by meaning, not just keywords. No embedding API calls, and nothing leaves your machine unless you choose to push it.

Usage stats by tool

Per-session and per-project token counts, tool call histograms, and per-provider rollups, all aggregated automatically.

Git-aware

Sessions are linked to the branch and commit you were on. Trace what you were doing when without guessing.

Cross-tool mesh

Spooling sits between every AI coding assistant and weaves their sessions into one timeline. Switch tools without losing the thread.

Powered by Strands

Built on the Strands agent framework. Traces, spans, and metrics flow through the same observability model AWS ships for production agents.

CLI + GUI

Drive it from your terminal, or browse a local dashboard at localhost. Whichever you're already in.

How it works

Install. Sync. Search.
Share when you're ready.

01Install
pipx install spooling
# Python 3.11+. No Docker, no Postgres, no Node.
02Detect providers & sync
spooling init      # scan for available providers
spooling sync      # index every session for semantic search
03Search & explore
spooling search "that redis race condition"
spooling stats
spooling mcp       # MCP server for your agents
04Share with your team (optional)
spooling login     # approve in your browser
spooling push      # send sessions to your workspace
Cross-tool by design

One knowledge base
across every AI coding tool.

Each AI coding tool locks its sessions inside its own silo. Spooling reads them all, indexes them into one place, and gives you a single semantic memory across every provider you use.

Claude CodeAvailable
Codex CLIAvailable
CursorAvailable
GitHub CopilotAvailable
WindsurfAvailable
AntigravityAvailable
KiroAvailable
Gemini Code AssistAvailable
OpenCodeAvailable
Cortex CodeAvailable
AiderSoon

Cursor, GitHub Copilot, Windsurf, Kiro, Antigravity and Gemini Code Assist are read from their macOS locations today. The others read from your home directory. Linux and Windows coverage for the rest is in progress.

Compare

The glue your AI workflow
is missing.

Spooling lives in the same neighborhood as other AI memory tools, but none of them solve the thing that actually hurts: copy-pasting context every time you switch tools.

ToolPrimary strategyUnified knowledge baseBest for
Background sync across IDEs, CLIs, and web chatsAutomatedDevs moving between AI coding tools
Isolated project workspaces, chat inside its UIOnly internal chatsNon-devs organizing documents
Manual history hub, searchable archiveManual syncLooking up old conversations fast
Local model runnerSession logs onlyRunning free models on-device
Real-time memory graph over MCPLive state sharingLive context hand-off between apps
Cost tracking + API observabilityNo (traces, not memory)Ops teams monitoring LLM spend

Spooling solves AI amnesia by automatically feeding past decisions back into your current session, no matter which tool you opened it in.

Why us

Three things a frontier lab
cannot ship.

The AI labs and IDE incumbents will all build per-product usage dashboards. The defensible wedge for Spooling is the work they structurally won't do.

01

Cross-tool by design

Anthropic, OpenAI, GitHub, and Cursor each ship analytics for their own product. None of them will ever surface cross-vendor comparisons. That's competitive intel against them. An independent third party is the only place that aggregation can credibly live.

Labs won't aggregate across competitors.

02

One record across vendors

Each vendor will give you a usage log for their own product. None will hand you a single record of every AI-assisted session across all of them. Spooling Cloud keeps that record, with who pushed each session, the project it came from, and the model that answered.

The record only an independent tool can keep.

03

MCP-portable context

Your AI session history shouldn't be trapped inside whichever assistant you used last quarter. Spooling exposes everything as an MCP endpoint, so the next agent you open can call it as a tool. The data is yours, the assistants are interchangeable.

Bring your AI history with you.

Team visibility

You can't improve
what you can't see.

Most engineering teams can't say how AI-assisted work is actually happening, because each vendor only shows its own product. Spooling puts every tool in one view.

Visibility

Cross-vendor, including the tools you didn't approve

Anthropic Console shows Claude. GitHub Enterprise shows Copilot. Cursor's admin shows Cursor. None of them shows the union, and none of them shows the tool a teammate picked up last quarter. Spooling reads from disk, so it sees every tool that ever wrote a session file.

Attribution

Per-developer, per-project, per-model

In a team workspace every session is tagged with who pushed it, the project it came from, and the model that answered. Filter by teammate or by project, and see usage and cost rolled up by provider.

Independence

Not the vendor auditing itself

A coding tool's own dashboard is its own marketing surface. The numbers it shows you are the numbers it wants you to see. Spooling isn't aligned to any one provider and has no incentive to soften usage attribution.

What Spooling captures
  • Full prompt and response text, after best-effort secret redaction
  • Provider and model for each session, with token and cost counts
  • Working directory and git branch
  • Who pushed it: the account that owns the API key
Honest about what's not here yet
  • No SSO/SAML or SCIM yet (sign in with Google, GitHub or email)
  • No audit-log export or compliance reports yet
  • No SOC 2 or ISO 27001 certification yet
  • Tell us what you need and we'll prioritise it
Spooling Agent

An agentic mesh on top
of your unified memory.

Spooling isn't just a passive index. The Spooling Agent sits on top of your unified knowledge base and turns it into an active mesh you can query, reason over, and route work through.

Cross-provider recall

Ask in natural language. The agent retrieves relevant spans from every provider's history and feeds them to the model that's best suited to keep going.

Session handoff

Pick up where any tool left off. The agent reconstructs the working context and hands it cleanly to the next agent, so you never re-explain yourself.

Mesh routingRoadmap

Route prompts to the right provider based on cost, capability, or past success. Your unified memory becomes the traffic layer for every tool you use.

Spooling Cloud

Your team's AI memory,
unified in one workspace.

Spooling on your laptop is great. Spooling across your team is a different tool. The cloud workspace pools every dev's sessions into one shared mesh.

Shared team memory

Every teammate's sessions land in one shared workspace. Search across every prompt, every tool call, every fix.

Onboarding, solved

New hires inherit months of team context the moment they sign in. No knowledge transfer meetings.

Zero ops

We host the database, the search index, the sync layer, and the embedding service. You do not run Docker.

Cross-tool usage visibility

See which AI tools every team member actually uses, rolled up by project, repo, and teammate.

Isolated, exportable, deletable

Workspaces are isolated by row-level security in the database. Download everything you've stored, or delete your account and its data, from Settings.

Secrets redacted by default

The CLI replaces common API keys, tokens, PEM keys and sensitive env vars with [REDACTED] before syncing. It's pattern-based and best effort, so keep an eye on what you push.

Pricing

Free to start.
Built for teams.

Simple per-seat pricing. Everything is free today while we're in early access. Paid plans open soon, and we'll announce them before anything is charged.

Available now
Free
$0forever

For individuals and small teams getting started. The open source CLI is free with or without Cloud.

  • Your personal workspace
  • 1 team workspace, up to 3 members
  • Cross-tool semantic and keyword search
  • MCP endpoint for your agents
  • Sign in with Google, GitHub or email
  • Download or delete your data any time
Get started free
Coming soon
Team
$15per user / month

For engineering teams that want one shared memory across every AI coding tool.

  • Everything in Free
  • Unlimited team workspaces and members
  • Higher storage and session limits
  • Per-person and per-project usage views
  • Email support
  • 20% off billed annually
Get notified
Coming soon
Business
$30per user / month

For organizations that need single sign-on and an audit trail.

  • Everything in Team
  • Roadmap: SSO / SAML and SCIM Roadmap
  • Roadmap: audit-log export Roadmap
  • Roadmap: priority support Roadmap
  • 20% off billed annually
Get notified
Talk to us
Enterprise
Customannual

For security and procurement requirements beyond the plans above.

  • Everything in Business
  • Roadmap: self-hosting, data residency Roadmap
  • Roadmap: SLA and compliance reports Roadmap
  • Tell us what you need
Contact us

Prices are per user per month, in US dollars. Billing isn't open yet: Team and Business can't be purchased today, and nothing is charged. Plan limits aren't enforced during early access.

"On the roadmap" items are planned but not available yet. Tell us which ones matter to you and it shapes what we build first.

Live · Free in early access

Get started with Spooling Cloud.

From zero to searchable team memory in a few minutes.

01

Create your account

Sign up with Google, GitHub or email. It takes a minute and needs no card.

02

Install and sign in

The CLI opens your browser to approve the login.

pipx install spooling
spooling login
03

Push your sessions

Your recent sessions appear in the app, searchable by you and your team.

spooling push
Paid plans · Coming soon

Get notified when paid plans open.

Leave your email and tell us which plan you're interested in. We'll write once, when billing opens, and tell you about anything you asked for.

We only email about what you asked for. See our privacy policy.

FAQ

The things people ask first.

Is Spooling Cloud available today?

Yes. Create an account at app.spooling.ai, install the CLI with pipx install spooling, run spooling login, then spooling push. It's free while we're in early access. Paid plans (Team and Business) open soon, and we'll announce them ahead of time.

Does my code ever leave my machine?

Not with the OSS version: everything runs and stays locally. If you push to Spooling Cloud, the session text and metadata you push is stored on our servers and sent encrypted in transit. Sessions in your personal workspace are visible only to you; sessions in a team workspace are visible to its members. See the privacy policy for the details.

What about secrets? Are my API keys exposed in the cloud?

The CLI redacts common secret patterns before anything is uploaded: API keys (AWS, GitHub, OpenAI, Anthropic, Stripe and others), PEM private keys, and sensitive KEY=VALUE lines become [REDACTED]. That is pattern-based and best effort, so it can miss things, and passing --no-redact sends raw values. The server does not redact on its own yet.

Can I delete my data?

Yes. In Settings you can download everything you've stored as one JSON file, or delete your account and everything it owns. From the CLI you can delete individual sessions. Encrypted backups age out within 21 days.

How much will paid plans cost?

Planned pricing is $15 per user per month for Team and $30 per user per month for Business, with 20% off billed annually. Enterprise is custom. Billing isn't open yet, so nothing can be purchased and nothing is charged today. The Free plan stays free, and we'll announce paid plans before they take effect.

Do I need an API key to try it?

No. The OSS CLI runs fully offline with local sentence-transformers embeddings. You only need an API key if you want the chat agent to use Anthropic or OpenAI instead of a local Ollama model.

What's the difference between Spooling and Spooling Cloud?

Spooling is the open source engine you run on your laptop. Spooling Cloud is the hosted version where your team's sessions pool into a shared workspace.

Is there a time limit on the open source version?

No. Run it locally as long as you want. No account, no credit card, no usage cap.

Can I self-host Spooling Cloud in our own VPC?

Not today. Enterprise self-host is on the roadmap.

Which AI coding tools and operating systems are supported?

Claude Code, OpenAI Codex CLI, Cursor, GitHub Copilot, Windsurf, Kiro, Google Antigravity, Gemini Code Assist, OpenCode and Cortex Code. Cursor, Copilot, Windsurf, Kiro, Antigravity and Gemini are read from macOS locations today; the rest read from your home directory. Aider is next.

Do you have SSO, audit export or SOC 2?

Not yet. You can sign in with Google, GitHub or email today. SAML, SCIM and audit-log export are on the roadmap for the Business plan, and we don't have SOC 2 or ISO 27001 reports today. Tell us what you need and it helps us prioritise.

Start indexing
your AI memory.

Clone the OSS for yourself, or launch a team workspace in Spooling Cloud.