Back to vendors
c

cubic

Also known as: cubic, cubic.dev, cubic-dev-ai, mrge

Visit site
Entry priceFree plan. Team at $30 per developer per month billed annually, or $40 monthly.Full pricing detail

AI code review agent that reviews every pull request with whole-repository and cross-repo context, learns from reviewer corrections, runs scheduled codebase scans that file tickets and open fix PRs, and can auto-approve clean PRs under a policy you test in shadow mode first.

cubic is an AI code review platform built for the moment when AI generated code made review the bottleneck. When a pull request opens, cubic reviews the changes automatically in a secure isolated container with context into the whole codebase, not just the diff, and comments inline on the lines that matter.

Its reviewer navigates a repository the way a developer would, and its analysis covers the whole repository, so it catches issues that span multiple files. Reviews across repositories go further, letting cubic read selected companion repositories when a change to a frontend affects a backend API or a shared schema.

A Y Combinator backed startup, listed there under its earlier name mrge, cubic is used by teams at n8n, Cal.com, PostHog, Granola, Resend, Daytona and the Linux Foundation.

Beyond flagging bugs, cubic learns each team's conventions. Reacting to a suggestion or correcting it is remembered, which reduces false positives over time. Teams turn on prebuilt review agents from cubic's agents library of 63 agents, or define custom agents in natural language or code patterns to enforce internal API usage, architectural decisions or deprecated functions. cubic reads current documentation for the libraries in the stack, so suggestions reflect present APIs rather than patterns from a model's training data. It generates pull request descriptions and offers fixes: click Fix with cubic or tag the agent in a comment and background agents generate and apply them, with heavier work handed to a coding agent such as Claude Code or Cursor.

Ultrareview escalates risky migrations and security sensitive changes to the most capable review models on request. On higher tiers, scheduled codebase scans run many agents in parallel across whole repositories for bugs and security issues. They triage findings, notify owners over Slack and email, create tickets in Jira, Linear, Asana or Notion, and open fix pull requests. Since October 2026 the scan agents can check their findings against production errors and logs from PostHog, Sentry or Datadog when one of those is connected, so a suspected bug is confirmed by what users actually hit.

Auto approval lets cubic approve clean pull requests under a policy the repository owner defines. It ships with a shadow mode that shows which pull requests cubic would have approved before live mode is switched on, so a team validates the policy before granting the agent any authority. cubic runs outside GitHub as well as inside it. A CLI installed by shell script reviews uncommitted changes, branches or specific commits before a pull request exists, and cubic connects to Cursor, Claude Code, VS Code, Codex and Gemini CLI to run local reviews and answer codebase questions without leaving the editor.

In the CLI a developer can connect a ChatGPT or Claude Code subscription and switch providers and models for local reviews, while hosted pull request reviews run on models cubic chooses from OpenAI and Anthropic. An AI wiki indexes the repository into searchable documentation with architecture diagrams on demand. It refreshes monthly on Team, on a daily, weekly or monthly schedule the customer picks on Pro and Max, and by hand for public repositories on the free plan.

cubic exposes its own work to other systems through two MCP servers, one for codebase scan findings and one for the AI wiki, plus an Analytics API. It tracks model attribution per commit, so it can report which coding agent wrote a change and whether bugs were found in it.

cubic states SOC 2 Type 1 compliance and reviews code without storing it or using it to train models. The Enterprise tier adds SSO and SAML through GitHub OAuth, GitHub Enterprise support, exportable compliance audits, bring your own API keys and custom MSA and DPA terms. A trust center at trust.cubic.dev lists its subprocessors; no attestation report is published openly, so the certification rests on cubic's own statement.

Pricing is per developer. The free Starter plan includes 20 pull request reviews a month, automatic descriptions, project connectors and unlimited AI wikis. Team is $30 a month billed annually or $40 monthly, adding 40,000 reviewed lines per developer, the CLI, Ultrareview and simple analytics. Pro is $79 annually or $99 monthly, adding 80,000 reviewed lines, codebase scans on three repositories, automatically created fix pull requests, Confluence, the MCP servers and the Analytics API. Max, added in October 2026, is $160 annually or $200 monthly with 160,000 reviewed lines. Extra reviewed lines cost $20 per 10,000, and Enterprise is custom. cubic is free for public repositories.

From our AI code reviewers video

AI Code Review Tools: Which Ones Run the Code They Review?

Our video on the 7 AI code reviewers in the index names what each one does best. For cubic, that is proving the policy before granting the authority.

The player starts at cubic's part, 2:59 in. Recorded in October 2026; the profile here is live and updates as research is verified.

Vendor details

Canonical URL

https://www.cubic.dev

Category

Coding agent

Subcategory

AI code review agent

Funding status

Independent. Y Combinator backed, listed under the YC company name mrge, which still appears in the pricing page's backing link and enterprise contact metadata. Customers named on first-party pages include n8n, Cal.com, PostHog, Granola, Resend, Daytona, Legora, Better Auth, Cartography and the Linux Foundation. Specific funding figures are not disclosed on first-party pages.

Company status

independent

Use cases & customers

Primary use cases

automated pull request reviewbug and vulnerability detectioncoding standard enforcementbackground codebase scanning

Target customers

software engineering teams on GitHubopen source maintainersplatform and infrastructure teams

Deployment options

SaaS (GitHub app, two-click install)Local CLI for pre-flight reviewsIDE and coding-agent hosts (Cursor, Claude Code, VS Code, Codex, Gemini CLI)Desktop app

Integrations

Two-way GitHub integration installs as an app in two clicks and drives inline comments, fix branches and auto-approval, with GitHub Enterprise support at the Enterprise tier. Project connectors cover Jira, Linear, Asana and Notion from the free plan, with Confluence added on Pro, so a change referencing a ticket is reviewed with that context. PostHog, Sentry and Datadog connect as production evidence sources since October 2026, letting scan agents confirm findings against real errors and logs. Slack and email notifications ship on Pro as outputs. cubic also runs inside Cursor, Claude Code, VS Code, Codex and Gemini CLI, ships a local CLI installed by shell script that can run on a developer's own ChatGPT or Claude Code subscription, and exposes two MCP servers (Codebase scan MCP and AI wiki MCP) plus an Analytics API so other agents and systems can consume its findings. The agent acts by commenting inline, committing one-click fixes, opening fix pull requests and creating tickets.

In practice

Your team is drowning in pull requests and rubber stamping them. cubic reviews each PR against your whole codebase, flags real bugs on the exact lines, and enforces the rules you wrote in plain English.

You maintain a busy open source project alone. cubic is free for public repos, learns your conventions, and reviews contributor PRs so you spend less time on routine feedback.

You worry about latent bugs already merged. On higher tiers cubic runs nightly scans where many agents comb the repo for bugs and vulnerabilities, then file tickets and open fix pull requests.

Agentic Index coverage score

10.5 / 14 capabilities · 75%

Integrations & Tool Calling Full

A two way GitHub app drives inline comments, fix branches and approvals, project connectors cover Jira, Linear, Asana and Notion with Confluence on Pro, Slack and email notifications ship on Pro, PostHog (5 Oct), Sentry (8 Oct) and Datadog (11 Oct 2026) connect as production evidence so scan agents can confirm findings against real errors and logs, and cubic runs inside coding agent hosts through its MCP server and CLI.

Sourcecubic.dev/pricing-plans and docs.cubic.dev/changelogread 2026-10-28

Workflow Orchestration Full

Codebase scans are documented as thousands of parallel agents working through a staged process that maps the codebase, runs parallel checks, investigates, deduplicates and scores findings, and Ultrareview is a documented multi pass analysis. The scan docs still label scans beta and available by request, while the pricing page lists them on Pro. Reviews run a fixed sequence of review, inline comments, fix branches and optional approval, and heavier implementation can be handed to an outside coding agent.

Sourcedocs.cubic.dev/codebase-scan/codebase-scans and cubic.dev/pricing-plansread 2026-10-25

Knowledge Grounding & RAG Full

The AI wiki automatically indexes the codebase into searchable documentation with source links and architecture diagrams, regenerated monthly on Team and on a daily, weekly or monthly schedule on Pro and Max as code changes. It can be queried in plain English, over MCP or as synced markdown, alongside whole repository and cross repository context during reviews.

Sourcedocs.cubic.dev/wiki/ai-wiki 2026-09-29 and cubic.dev/pricing-plansread 2026-10-25

Human Oversight & Guardrails Partial

Auto approval runs under a per repository policy the customer sets (low risk only, custom or always), and cubic approves only when its review finds no issues. No person approves anything before cubic acts, so the policy constrains the agent and is not an approval step. Shadow mode, which previews approvals before they go live, is covered under testing.

Sourcedocs.cubic.dev/ai-review/auto-approvalread 2026-09-29

Security, Identity & Governance Full

Compliance is SOC 2 Type 1, with TLS 1.2 or higher in transit, AES-256 at rest, subprocessor agreements that prohibit training on customer code, and a trust center at trust.cubic.dev listing subprocessors. Enterprise adds SSO and SAML through GitHub OAuth, GitHub Enterprise support, exportable compliance audits and custom MSA and DPA terms.

Sourcedocs.cubic.dev/account/privacy-security and cubic.dev/pricing-plansread 2026-10-28

Observability & Auditability Partial

The Analytics API returns per pull request metrics (issues flagged and fixed, AI authored lines, engagement times), the Analytics AI review tab rebuilt on 6 Oct 2026 shows what happens to each issue cubic raises, Pro tracks AI coding usage, and Enterprise exports compliance audits. These report outcomes, and there is no stated per run record of the review agent's steps or tool calls.

Sourcedocs.cubic.dev/analytics/api, docs.cubic.dev/changelog and cubic.dev/pricing-plansread 2026-10-28

Memory & State Persistence Full

cubic extracts learnings from PR comments, reactions and senior reviewers' past reviews, scoped to the team and never shared across organizations or repositories. Learnings are browsable, editable and deletable under Memory and Learning, and a weekly cleanup merges duplicates and archives outdated guidance.

Sourcedocs.cubic.dev/ai-review/memory-and-learningread 2026-09-29

Deployment & Data Residency Not documented

cubic is hosted SaaS installed as a GitHub app, and code is never stored or used for training. There is no stated self hosting, customer cloud or region choice.

Sourcecubic.dev/pricing-plans, cubic.dev/enterprise and docs privacy-securityread 2026-09-29

Prebuilt Agents, Templates & Packs Full

Teams turn on prebuilt review agents from cubic's agents library, which lists 63 agents, and adopt community and suggested agents with one click. Since 9 October the library runs on all repositories by default. Teams also write their own custom agents in natural language, five on Team and ten on Pro.

Sourcecubic.dev/agents and docs.cubic.dev/ai-review/custom-agentsread 2026-10-25

Triggers & Channel Coverage Full

Reviews run automatically when a pull request opens and again on new commits, codebase scans run nightly on Pro, and the AI wiki regenerates on a weekly or monthly schedule, so work reaches the agent without a person starting it. @cubic mentions, Fix with cubic and the CLI add requested runs.

Sourcecubic.dev/pricing-plans and docs.cubic.dev/wiki/ai-wikiread 2026-09-29

Model Flexibility & Routing Partial

Hosted pull request reviews run on models cubic chooses from OpenAI and Anthropic, so more than one provider is disclosed but the customer does not pick for the reviewer that acts on pull requests. Enterprise offers bring your own API keys without a model or provider selection. The cubic CLI alone lets a developer connect a ChatGPT or Claude Code subscription and switch providers and models for local reviews (changelog 19 Apr 2026), a picker that does not reach the hosted reviewer.

Sourcedocs.cubic.dev/account/privacy-security, cubic.dev/pricing-plans and docs.cubic.dev/changelogread 2026-10-28

APIs, SDKs & MCP Extensibility Full

cubic's own MCP server at cubic.dev/api/mcp, signed in with OAuth or an API key, offers 20 tools plus three environment tools, including get_pr_issues, trigger_pr_review, update_pr_issue_status, list_wikis, list_scans and get_scan. Several of them start reviews or change finding status, so outside agents can act through cubic, not only read from it. On Pro, an Analytics API adds a bearer token endpoint, and since 2 October organization API keys and a Members API are available.

Sourcedocs.cubic.dev/ide/mcp-server and changelog 2026-10-25, analytics/apiread 2026-09-29

Testing, Debugging & Optimization Full

Shadow mode keeps cubic in comment only mode on real pull requests while adding a summary of whether it would have approved each one, so a team tests the agent's approval behavior under its chosen policy before granting it live authority. Bug detection, the product itself, tests the customer's code and not the agent.

Sourcedocs.cubic.dev/ai-review/auto-approvalread 2026-09-29

Browser & Computer Use Not documented

cubic works through the GitHub API, an isolated review container, a CLI and MCP, with no stated browser control or operation of software through a graphical interface.

Sourcedocs.cubic.dev and cubic.dev/pricing-plansread 2026-09-29

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Product updates

·Agent capabilityPartially Verified

Codebase scan agents in cubic can now check whether production data confirms the bugs and vulnerabilities they find, starting with PostHog, which is switched on per repository under Production evidence. Sentry followed on October 8 and Datadog on October 11, with confirmed findings showing how often the issue occurred and linking to the matching events or logs.

Bears on: Integrations

View source
·Human approval / guardrailsVerified

cubic added a repository policy that allows automatic pull request approval while findings at selected priorities remain unresolved. Choosing a priority also allows lower priorities, and cubic publishes new findings before submitting a separate approval. Other approval rules and GitHub branch protections still apply.

Bears on: Human approval / guardrails

View source
·Agent capabilityPartially Verified

cubic now supports cross-repo reviews, allowing users to link up to five related repositories for coordinated updates. The agent checks related code across repository boundaries, displays findings inline with citations to affected files, and tracks fixes across companion pull requests.

Bears on: Agent capability

View source
View all 3 cubic updates →Tracked since Sep 2026 · Verified from public vendor sources

Pricing

Free plan. Team at $30 per developer per month billed annually, or $40 monthly.

Subscription tiers priced per developer per month, each with a monthly allowance of reviewed lines (the added and deleted diff lines cubic reads). The free tier is capped by monthly review count, and Enterprise is custom.

Free tierTrial available

Included quota

Pricing is per developer, with reviewed line allowances. The free Starter plan includes 20 PR reviews a month, automatic PR descriptions, custom context, Jira, Linear, Asana and Notion connectors and unlimited AI wikis. Team, at $30 per developer per month billed annually or $40 monthly, includes 40,000 reviewed lines per developer, up to 5 custom agents, the cubic CLI, Ultrareview, monthly wiki updates, 5 private repo wikis and simple analytics. Pro, at $79 annually or $99 monthly, includes 80,000 reviewed lines per developer, faster PR and CLI reviews, up to 10 custom agents, Fix with coding agents, Confluence, codebase scans on 3 repositories on a schedule the team chooses, automatically created fix PRs, Slack and email notifications, Codebase scan MCP, AI wiki MCP, 20 private repo wikis, AI coding usage tracking and an Analytics API. Max, added on 2 October 2026, is $160 annually or $200 monthly with 160,000 reviewed lines per developer. On Pro and Max, any developer with 15 or more PRs in 30 days needs a seat. Enterprise is custom, with additional custom agents and scans, SSO and SAML with GitHub OAuth, GitHub Enterprise support, exportable compliance audits, bring your own API keys, and custom MSA, DPA and payment terms. Public repositories are free and unlimited.

What is public

All tier prices are published exactly, per developer, with annual and monthly rates side by side: Free $0, Team $30 annual or $40 monthly, Pro $79 annual or $99 monthly, Max $160 annual or $200 monthly, and Enterprise custom. Reviewed line allowances (40k Team, 80k Pro, 160k Max), custom agent caps, scan coverage, the flex capacity rate and the feature list of each tier are all published, as is the definition of a reviewed line. Only Enterprise pricing is quoted.

Billing mechanics

Tiers are priced per developer per month, with monthly reviewed line allowances. The free tier is capped by review count, and public repositories are free and unlimited.

Cost watchouts

High PR volume or large diffs can exceed the reviewed line allowances. Pro costs more than twice the Team seat price. The free tier caps at 20 reviews a month.

Variable cost rationale

cubic bills per developer, and each tier carries a monthly allowance of reviewed lines, 40,000 per developer on Team, 80,000 on Pro and 160,000 on Max, while the free tier caps reviews at 20 a month. The bill grows with team size, and high PR volume or large diffs push a team to flex capacity at $20 per 10,000 extra lines or to a higher tier. The main step up is Pro, at $79 to $99 per developer, for codebase scans and auto fix. The tiers bound the bill. Each developer's allowance resets every billing period.

Additional watchouts

The free tier's cap of 20 reviews a month runs out quickly for active teams. Pro, at $79 to $99 per developer, is a large step for small teams. cubic is centered on GitHub. Code is reviewed in a secure container and never stored or used for training, and cubic states SOC 2 Type 1.

Overage / add-ons

Usage is metered by reviewed lines (the added and deleted diff lines cubic reads) against the monthly allowance, and the free tier is capped by its monthly count of PR reviews. Flex capacity adds reviewed lines beyond the allowance at $20 per 10,000, or a team moves to a higher tier.

Sales call required

No, self serve available

Free / trial

Free Starter plan with 20 PR reviews a month, free and unlimited for public repositories, and a 7 day trial on paid plans

Lowest paid plan

Team at $30 per developer per month, billed yearly

Commercial notes

cubic is positioned on review depth, with repo wide context, custom rules and background scans. The free tier is usable for real work, especially open source, and Pro's scheduled codebase scans are its main draw. Value is highest where review quality is inconsistent or senior reviewers are a bottleneck.

Key ambiguities

Reviewed lines are the metered unit. They are the added and deleted lines in a diff that cubic actually reads, excluding generated files, vendored code, binaries, ignored and skipped files and failed or canceled reviews, with incremental reviews counting only new changes and manual reruns counting again. Usage resets with the billing period. Pro carries codebase scans on 3 repositories and a 7 day trial.

Cancellation / refund

Cancellation and refund terms are not published. Enterprise runs on a custom MSA and DPA.

Support SLA / resale

Standard support on Starter and Team, and premium support with a shared Slack channel on Pro and above. No reseller or white label program is published.

Missing data

Enterprise pricing is not published.

Agentic Index verified 2026-10-28

Alternatives to cubic

The closest documented capability profiles to cubic among coding agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

  • Qodo12.0 / 14Adds documented Deployment & Data Residency
  • Graphite8.5 / 14A lighter documented profile than cubiccubic vs Graphite →
  • Potpie AI11.0 / 14Adds documented Deployment & Data Residency
  • Sonar11.0 / 14Adds documented Deployment & Data Residency
  • Embedder11.5 / 14Adds documented Deployment & Data Residency
  • Mistral Vibe12.5 / 14Adds documented Deployment & Data Residency and Browser & Computer Use

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.