Three products. One ground truth.
Local grounding for your agent, review for your PRs, root cause for your incidents. Each priced on its own, simply.
Niro Local
Ground truth for your agent, on your machine.
Graph traversal, not an LLM call. Nothing leaves your machine, by default, nothing ever does.
Up to 50k LOC, enforced automatically
Covers the vast majority of personal projects, side work, and learning.
- Up to 50k local LOC
- Call chains, blast radius, impact analysis
- No application, no self-declaration
Unlimited LOC, no further cap
For codebases past the free cap, personal or commercial.
- Unlimited local LOC
- Call chains, blast radius, impact analysis
- Everything in Free, no size cap
Data sharing, both off by default
When the graph can't resolve something, optionally send us that specific snippet so we can fix it. Asked in the moment it happens, not buried in a settings page.
A separate, explicit setting. Never bundled with the failure-snippet checkbox above, never turned on to unlock a cheaper tier.
Niro PR Review
Real-time review, grounded in structure.
Cross-service dependencies and blast radius, before merge. Codebase chat and graph visualisation included.
30 reviews/seat/month included, then $1/review
One shared graph, every PR checked against it before merge.
- 30 PR reviews/seat/month, overage $1/review
- Codebase chat, 1,000 messages/seat/month includedCalls a model, so it's metered like reviews, not left unlimited
- Interactive graph visualisation, includedNot a model call, no limit
- Resolved edges, like a compiler, not inferred from similarity
Unlimited reviews, SSO, SLA
For organisations that need unlimited volume and compliance.
- Unlimited PR reviews
- Unlimited codebase chat
- SSO, audit trail, dedicated support
Niro RCA
From incident to root cause, in minutes.
Automated graph traversal fires on alert. No payment decisions during an incident, we bill after resolution.
Billed after resolution, never mid-incident
Pay only for the incidents you actually run RCA on.
- Automated graph traversal, root cause identification
- Incident timeline, postmortem draft
- Configure alert sources (PagerDuty, OpsGenie, webhook) once
Unlimited, org-wide, in contract
For teams with frequent incidents, no per-incident billing.
- Unlimited incidents, no per-incident charge
- Org-wide scope, every indexed repo
- Dedicated support
Good to know
How this actually works
Each product stands alone
Local, PR Review, and RCA are priced and billed separately. Use one, two, or all three, there's no bundle requirement and no cross-product discount built in yet.
Why Local's free line is a LOC count
50k lines is something we can measure, not something you have to declare. It approximates personal-versus-commercial use without asking anyone to self-certify which one they are.
Two separate consent checkboxes, not one
Sending a failure snippet to help us fix a bug is a different, narrower ask than using your code for training. They're asked separately, so saying yes to one never implies the other.
Why PR Review has a cap
Unlimited flat-rate review pricing breaks down under real agentic PR volume. A included allowance plus a small overage keeps the price simple without an open-ended cost risk on either side.
RCA billing during an incident
We never hard-stop mid-investigation. RCA always completes regardless of billing status, we invoice after the incident is resolved, not before or during.
Enterprise across all three
Volume pricing, SSO, audit trail, and dedicated support are available per product or as one combined contract. Talk to us once, we'll scope whichever mix you need.