Skip to content
ProductArena

Rank #3 of 6 in AI Code Review

cubic logo

cubic

YC X25 Built-in AI assistant

MRGE, Inc. · commercial

cubic.dev ↗Try it →
PA Score28/100AGENT-READY36/100BUILT-IN AI77/100API0/100
MCP✓CLI✓API~
npm 1.4k/wk
ArenasAI Coding Agents#10/13AI Code Review#3/6

Access

API docs ↗CLI docs ↗MCP docs ↗

Install

shellcurl -fsSL https://cubic.dev/install | bash

Vendor-official, but review any script before piping it to a shell.

npxnpx @cubic-dev-ai/cli install -g

Compare head-to-head

CodeRabbit logovs CodeRabbitGreptile logovs GreptileGraphite logovs GraphiteQodo logovs QodoCursor Bugbot logovs Cursor Bugbot

Alternatives to cubic →

Showcase

cubic homepage screenshot
homepage · captured Sep 2026 · view live ↗
cubic docs screenshot
docs · captured Sep 2026 · view live ↗

Try itExperimental

See what an agent can do with cubic before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$npx -y @cubic-dev-ai/cli --versionrecorded session — replayed, not live
recorded 2026-09-10 · exit 0 · captured verbatim by our probe harness, secrets redacted

Verified integrations

No integration evidence found in our corpus for this product yet — that means none was found, never that it doesn’t integrate.

By theme — the product's score on each story themeBy theme

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

40.3/100

Autofix agents — stories about autofix agents in this arenaAutofix agentsevidence →

Stories about autofix agents in this arena

77.8/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

28.0/100

Codebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understandingevidence →

How deeply the tool maps your repo — cross-file context, architecture awareness, history

52.9/100

Interaction — how you steer it — commands, replies, review conversations, configurability in the loopInteractionevidence →

How you steer it — commands, replies, review conversations, configurability in the loop

61.3/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

6.0/100

Pr integration — stories about pr integration in this arenaPr integrationevidence →

Stories about pr integration in this arena

70.2/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

30.7/100

Quality gates — stories about quality gates in this arenaQuality gatesevidence →

Stories about quality gates in this arena

23.3/100

Review accuracy — stories about review accuracy in this arenaReview accuracyevidence →

Stories about review accuracy in this arena

53.0/100

Surfaces — where it meets your workflow — IDE, CLI, web, PR comments, CI checksSurfacesevidence →

Where it meets your workflow — IDE, CLI, web, PR comments, CI checks

50.0/100

Workflow config — stories about workflow config in this arenaWorkflow configevidence →

Stories about workflow config in this arena

54.0/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 53/53 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full7/10X

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial6/10T

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10X

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10C

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10C

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial6/10T

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1n/auntestednone yet

I turn a review finding into an applied fix — a committed patch or an agent-generated follow-up — without leaving the PR C

Fixes

developerAutofix agents — stories about autofix agents in this arenaAutofix agents3full8/10C

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3full8/10C

The reviewer installs as a GitHub/GitLab app and posts reviews as native inline comments on my pull requests within minutes C

Platforms

developerPr integration — stories about pr integration in this arenaPr integration3full8/10X

I configure the reviewer with a versioned config file in my repo — path filters, per-path instructions, review profiles C

Config

engineering leadWorkflow config — stories about workflow config in this arenaWorkflow config3full7/10X

Review comments include committable suggested diffs I can apply with one click C

Suggestions

developerPr integration — stories about pr integration in this arenaPr integration3full7/10C

Review comments reflect the whole repository — call sites, related modules, existing conventions — not just the changed hunks C

Context

developerCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding3partial7/10C

The reviewer catches real bugs in my PR — logic errors, race conditions, broken edge cases — not just style nits C

Detection

developerReview accuracy — stories about review accuracy in this arenaReview accuracy3full7/10X

The reviewer keeps noise low — few false positives, deduplicated comments, severity labels — so my team doesn't tune it out C

Noise

engineering leadReview accuracy — stories about review accuracy in this arenaReview accuracy3partial6/10X

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial5/10X

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3none0/10

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3noneuntestednone yet

Every PR gets an auto-generated summary and change walkthrough so human reviewers orient fast C

Summaries

developerPr integration — stories about pr integration in this arenaPr integration2full9/10X

I reply to the reviewer in the PR thread to ask questions, get explanations, or issue commands — and it answers in context C

Chat

developerInteraction — how you steer it — commands, replies, review conversations, configurability in the loopInteraction2full8/10X

Review findings hand off cleanly to my coding agent — copyable fix prompts or direct integration with Claude Code, Cursor, or Codex C

Handoff

ai-native userAutofix agents — stories about autofix agents in this arenaAutofix agents2full8/10T

The reviewer builds a persistent memory of my team's conventions and past review decisions and applies it to future PRs C

Memory

ai-native userCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding2full8/10X

The reviewer holds the line on AI-generated PRs — it verifies agent-authored code at a volume no human team could review C

Ai authored

ai-native userAutofix agents — stories about autofix agents in this arenaAutofix agents2full8/10X

I define custom agentic pre-merge checks in plain language — 'docs updated', 'tests cover new paths' — that run on every PR C

Checks

ai-native userAutofix agents — stories about autofix agents in this arenaAutofix agents2full7/10X

I encode my team's own review guidelines — natural-language rules, AST patterns, or linked style guides — and the reviewer enforces them C

Rules

engineering leadWorkflow config — stories about workflow config in this arenaWorkflow config2partial7/10X

I get the same review inside my IDE before I push, catching issues while the code is still in my editor C

Ide

developerSurfaces — where it meets your workflow — IDE, CLI, web, PR comments, CI checksSurfaces2full7/10T

Push back on a bad review comment and the reviewer learns — it stops repeating the same rejected feedback C

Learning

developerReview accuracy — stories about review accuracy in this arenaReview accuracy2full7/10X

The reviewer understands changes that span multiple repositories or a large monorepo and reviews them coherently C

Context

engineering leadCodebase understanding — how deeply the tool maps your repo — cross-file context, architecture awareness, historyCodebase understanding2partial7/10C

Pushing new commits triggers an incremental re-review that tracks what was fixed instead of repeating old comments C

Updates

developerPr integration — stories about pr integration in this arenaPr integration2partial6/10C

Reviews flag security problems in the diff — injection risks, leaked secrets, insecure patterns — alongside functional bugs C

Security

security engineerReview accuracy — stories about review accuracy in this arenaReview accuracy2partial6/10X

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial5/10T

I run reviews from a CLI against local diffs or in CI scripts, with machine-readable output my tooling can consume C

Cli

developerSurfaces — where it meets your workflow — IDE, CLI, web, PR comments, CI checksSurfaces2partial5/10T

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial5/10C

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2partial3/10C

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2none0/10

The reviewer can gate merges — a required status check or blocking review that enforces resolution of critical findings C

Gates

engineering leadQuality gates — stories about quality gates in this arenaQuality gates2none0/10

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2n/auntestednone yet

I see dashboards of findings, acceptance rates, and review coverage across my org C

Analytics

engineering leadQuality gates — stories about quality gates in this arenaQuality gates1full7/10C

I roll out org-level review defaults across hundreds of repos and manage exceptions centrally C

Governance

engineering leadWorkflow config — stories about workflow config in this arenaWorkflow config1partial5/10C

I control when reviews run — skip drafts, trigger on demand, filter by branch or label — so the bot shows up only when wanted C

Control

developerInteraction — how you steer it — commands, replies, review conversations, configurability in the loopInteraction1partial4/10C

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1partial3/10C

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 29 stories with headroom

What would move cubic’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    nonemoves agent-readyimpact 45

    Cubic's MCP-related evidence is all about cubic exposing its own MCP server for other coding agents to consume (cubic-docs-8, cubic-probe-4) — the reverse of this story, which asks whether the AI-native user can plug external MCP servers into cubic so cubic can use their tools.

  2. Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave

    nonemoves PA Scoreimpact 30

    Cubic is a code review/analysis platform whose data (review findings, PR comments, analytics, wiki) lives in GitHub, Jira, Notion, etc.; there is no evidence of a data export feature for users to download their cubic-generated data in open formats.

  3. Openness — open source, data portability, and self-hosting storiesSelf-host the core product

    nonemoves PA Scoreimpact 30

    cubic is presented entirely as a hosted SaaS (GitHub app, cloud-based review engine, subscription/seats, analytics API); there is no evidence of a self-hosted/on-prem deployment option, Docker image, or open-source core anywhere in the docs.

  4. Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent

    nonemoves agent-readyimpact 30

    cubic documents role-based access control for human team members managing subscriptions/settings (cubic-docs-56) and offers an MCP server/Analytics API, but there is no evidence of any mechanism to issue scoped or least-privilege API credentials/tokens specifically for an agent's use.

  5. Agenticness — how well agents can access and operate the productBuild against official SDKs

    nonemoves agent-readyimpact 30

    Cubic documents an MCP server, CLI, and Analytics API, but the evidence pack shows no official client SDKs (e.g., Python/JS libraries) for building against cubic, and explicit probes for an OpenAPI/swagger spec returned 404s, indicating no formal SDK surface is published.

  6. Agenticness — how well agents can access and operate the productSubscribe to events via webhooks

    nonemoves agent-readyimpact 30

    No evidence of a webhook subscription mechanism; cubic offers an Analytics API, MCP server, and GitHub comment interactions but nothing about outbound event webhooks.

  7. Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples

    nonemoves API qualityimpact 30

    There is an Analytics API mentioned but no evidence of an interactive API reference or runnable examples; probes explicitly show no OpenAPI/swagger spec found (all candidate paths 404), indicating no interactive API documentation exists.

  8. Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)

    nonemoves API qualityimpact 30

    cubic has an Analytics API but there is no documented machine-readable OpenAPI spec or equivalent; a direct probe for openapi.json/swagger.json at standard paths returned 404 across all candidates.

Showing the top 8 of 29 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map12 surfaces · 38 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

AI review docs29 stories

Hacker News15 stories

Ide docs10 stories

Configure docs9 stories

Codebase scan docs7 stories

Analytics docs6 stories

Account docs4 stories

Changelog docs4 stories

Wiki docs3 stories

OpenAPI spec2 stories

llms.txt1 story

Code review platform docs1 story

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$npx -y @cubic-dev-ai/cli --versionreproduced
$ npx -y @cubic-dev-ai/cli --version
1.10.8
proves: Use an official CLIproves: I run reviews from a CLI against local diffs or in CI scripts, with machine-readable output my tooling can consumerecorded 2026-09-10
$curl -si -X POST https://www.cubic.dev/api/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>' | grep -iE '^HTTP|^www-authenticate'reproduced
$ curl -si -X POST https://www.cubic.dev/api/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>' | grep -iE '^HTTP|^www-authenticate'
HTTP/2 401

www-authenticate: Bearer resource_metadata="https://www.cubic.dev/.well-known/oauth-protected-resource/api/mcp", scope="openid email profile"
proves: Connect an agent via an official MCP serverrecorded 2026-09-10
$curl -s https://docs.cubic.dev/llms.txt | head -6reproduced
$ curl -s https://docs.cubic.dev/llms.txt | head -6
# cubic documentation

> cubic reviews code on GitHub and in local coding workflows. These docs cover review setup, coding agents, repository context, analytics, and account management. Older stacking and archived platform guides are listed separately below.

## How to use these docs
proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-10
$curl -sL https://docs.cubic.dev/ai-review/quickstart.md | head -12reproduced
$ curl -sL https://docs.cubic.dev/ai-review/quickstart.md | head -12
> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cubic.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Developer quickstart

> Get started with cubic AI code review in minutes.

## 1. Install the cubic GitHub App

<Steps>
  <Step title="Sign up">
proves: Point an agent at llms.txt or agent-oriented docsrecorded 2026-09-10

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

12 of 17 testable claims verified · 0 contradicted → integrity 71/100

18 distinct capability claims found in cubic’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

12

Verified

5

Unverified

0

Contradicted

21

Undersold

Verified (15)
Unverified (5)
Undersold (21)
Claims outside our story set (2)

Real capability claims found in cubic’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “Offers an 'Ultrareview' deep-review mode using more capable models for risky/complex changes”

    source ↗

  • “Generates an AI-indexed, searchable wiki of the codebase with architecture diagrams and source links”

    source ↗
Suggest a story for these →

Business model

free-tiersubscription-per-seatusage-basedenterprise-custom

Starter is free with 20 PR reviews/month; Team is $30/dev/mo and Pro $79/dev/mo (annual), metered by reviewed lines of code with a flex-capacity usage add-on; free for open-source teams; Enterprise is custom.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Score26 (Sep 10 '26)28 (Sep 16 '26)
Agent-ready38 (Sep 10 '26)36 (Sep 16 '26)

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)

Agent surface uptime MCP up · llms.txt up (tracking since Sep 11 '26)