Skip to main content
Pricing

The whole platform, free & open source

Turn requirements into reliable software with no paywall in the way. Apache License 2.0 — no paid tiers, no usage limits, no license keys. Run it on a Claude subscription or your own API key.

View on GitHub
What You Get

The full platform — nothing held back

Every pillar, every workflow, every tool. There's no upgrade tier to unlock — everything open source — apache 2.0.

20 AI workflows
MCP server with 47 registered tools
24 auto-triggering Claude Code skills
Spec-driven workflow with an approval gate (/spec)
Retrieval grounding — attune-rag is built in
Local-first project memory and lessons corpus
Verification: fact-check generated content before it ships
Works on a Claude subscription or an API key
Full source code access
Community support on GitHub
Commercial use rights (Apache 2.0)

Get started in seconds:

$pip install attune-ai
The Platform

Memory first, zero cost

Project memory and every capability around it — all real, shipped, and included in the free, open source release.

Project memory

Your agent stops starting from zero

Findings from each session are stashed and recalled in the next. A retrievable lessons corpus surfaces the right engineering lesson at the moment a prompt needs it.

Dynamic forms

Forms that improve how you and the AI talk

Attune improves human/AI communication by dynamically using interactive forms: instead of a fixed wall of prose, it renders the right form in response to your prompt whenever a structured turn communicates better than text. A multi-part question becomes one click; a recommendation arrives as weighable cards; a disagreement is shown side-by-side so you overrule it in one tap.

AI workflows

Specialist teams, not one prompt

20 workflows run teams of 2–6 Claude subagents to review code, surface vulnerabilities, generate tests, and plan refactors — with cost-tiered model routing.

Retrieval grounding

Answers anchored to your code

Keyword + semantic retrieval keeps generated content grounded in your actual source. Mean faithfulness ≥ 0.97, CI-gated — drift fails the build.

Verification

Catch hallucinations before they ship

Fact-check LLM output against source-of-truth: confirm imports import, CLI flags are real, links resolve, and counts match — before the change reaches main.

Our Philosophy

Why the platform is free

Reliability shouldn't be a premium tier

Specifying, grounding, remembering, and verifying are how teams turn requirements into software they can trust. Those aren't add-ons to charge for — they're the whole point. Apache 2.0 keeps the reliability loop open to everyone.

Built for teams

The best developer tools are built by communities, not locked behind seats. Memory is local-first with an optional Redis semantic tier, so a team can adopt the platform on its own terms. Your feedback and contributions are what make it better.

Ready to ship reliable software?

Free and open source forever. Install from PyPI, run /spec on your next feature, and let the platform keep the work grounded, remembered, and verified.