Get This Tool
Nable
Pricing
- Model
- Free
Summary
Your cloud bill keeps climbing even as per-unit prices drop, and by the time the dashboard surfaces the anomaly you have already paid for three weeks of idle compute — nable puts that interrogation inside the editor where the code causing the spend lives.
nable runs locally via uvx and connects Claude or Cursor to your AWS, Azure, GCP, and AI token spend, so you can ask cost questions in plain language without leaving the editor. It detects billing anomalies, flags idle resources, recommends rightsizing, and — the differentiating move — opens the PR to apply the fix rather than handing you a PDF of suggestions. All data stays on your machine; the vendor states no telemetry is sent to an external hosted service. The tool provision model means it surfaces data and generates actions, but you review and merge — nothing ships without you approving the PR.
Bottom line: nable earns its place on a team running multi-cloud infrastructure from Cursor or Claude who wants cost fixes that arrive as mergeable code — but teams needing a persistent anomaly-monitoring dashboard with alerting outside the editor will find it stops short of that workflow.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- PR generation for rightsizing recommendations, so the gap between 'flagged waste' and 'merged fix' closes inside the same workflow — without it, recommendations rot in a dashboard nobody revisits.
- Normalized cross-provider cost view across AWS, Azure, GCP, and AI APIs in one query, so you stop context-switching between four separate billing consoles to understand where a spike originated.
- Fully local execution with no vendor data custody, so finance and security teams who block SaaS cost tools that require billing API credentials sent to a third-party host have no objection to clear.
- Editor-native integration with Claude and Cursor, so cost interrogation happens at the moment of writing infrastructure code rather than as a separate post-deploy audit cycle.
Cons
Sign in to edit- nable answers questions on demand — it does not run a persistent background monitor. Teams that need anomaly alerts during off-hours or scheduled cost reports delivered to Slack will hit this ceiling immediately and need a separate monitoring layer such as AWS Cost Anomaly Detection or a dedicated FinOps platform running alongside it.
- The tool integrates with Claude and Cursor specifically; teams standardized on VS Code without Cursor, JetBrains IDEs, or other editors are not in scope. Those teams route cost workflows through a browser-based tool or CLI, and nable offers no path to close that gap.
- PR generation relies on the tool constructing infrastructure code changes correctly from cost data — for environments with complex Terraform module hierarchies or non-standard naming conventions, the generated PR requires careful review before merge, adding a manual verification step that reduces the time-to-fix advantage on large or irregular infrastructure setups.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- macOS, Linux, Windows (via uvx/Docker)
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-16T18:23:48.685Z
Best For
Who it's for
- Developers using Claude or Cursor
- Teams wanting local cost intelligence
- FinOps workflows that produce code changes
- Multi-cloud environments needing PR-based fixes
What it does well
- Query real-time AWS/Azure/GCP/AI spend in editor
- Detect billing anomalies and idle resources
- Generate and open PRs for rightsizing changes
- Normalize costs across providers in one view
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Nable
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Nable free?
- Yes — Nable is fully free to use. There is no paid tier.
- Is Nable open source?
- Yes. Nable is open source.
- Can I self-host Nable?
- Yes. Nable supports self-hosting on your own infrastructure.
- When was Nable released?
- Nable was first released in 2026.
- What platforms does Nable support?
- Nable is available on: macOS, Linux, Windows (via uvx/Docker).
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Cloud cost tools generate reports. nable generates pull requests. Installed with a single uvx command and wired into Claude or Cursor as a local tool, it lets you query your AWS, Azure, GCP, and AI API spend in natural language from inside the editor — then takes the next step by opening a PR for the rightsizing change it recommends. The core loop is: ask a cost question, get a normalized answer across providers, receive a recommendation, and land a code change — without switching to a browser, a FinOps portal, or a separate CLI.
The differentiating feature is the PR generation. Most cost intelligence tools stop at the recommendation. nable bridges the last mile between ‘you should downsize this instance’ and an actual branch in your repository with the change applied. For developer-led FinOps workflows where the person reviewing spend is also the person writing infrastructure code, that gap closure matters.
Where it fits well: teams that already work inside Claude or Cursor, run multi-cloud environments where normalizing spend across providers is a daily friction point, and want cost changes treated as code rather than tickets. Where it breaks: the tool is a local data-provision layer, not a monitoring service. It answers questions when you ask them — it does not watch for anomalies overnight and send an alert at 3 a.m. Teams that need continuous cost monitoring with scheduled alerting will need a separate system alongside it.
Apache 2.0 licensed and self-hostable, with no hosted paid tier found in the vendor’s documentation. The docs confirm the install path is uvx nable, and the GitHub repository is the canonical source for configuration and integration details.