Home / Compare / Sourcery AI code review and security scanning vs Takumi byGMO security AI agent

Sourcery AI code review and security scanning vs Takumi byGMO security AI agent

Quick answer

Sourcery AI code review and security scanning (PR review bot with merge-blocking security checks, auto-approval of low-risk PRs and nightly codebase scans) (Sourcery (Sourcery.AI Limited)) and Takumi byGMO security AI agent (AI-SAST/AI-DAST diagnosis, automatic fix pull requests and AI penetration testing) (GMO Flatt Security (GMO Flatt Security株式会社)) are both listed in the Code security category of Agent Index.

They share no framework tags in our dataset.

This is not a ranking.

Field	Sourcery AI code review and security scanning (PR review bot with merge-blocking security checks, auto-approval of low-risk PRs and nightly codebase scans)	Takumi byGMO security AI agent (AI-SAST/AI-DAST diagnosis, automatic fix pull requests and AI penetration testing)
Vendor	Sourcery (Sourcery.AI Limited)	GMO Flatt Security (GMO Flatt Security株式会社)
HQ	United Kingdom · Europe	Japan · Asia Pacific
Primary category	Code security	Code security
Also listed in	Code security, Security	Code security, Security
Summary	London AI code reviewer for GitHub and GitLab that reviews every pull request within minutes, flags security issues and suggests commit-ready fixes, fails the check on high-severity security findings so merging can be blocked, auto-approves low-risk PRs with no blocking findings, and scans whole repositories every night for vulnerable code, exposed secrets, misconfigured infrastructure and vulnerable dependencies.	Japanese security AI agent that continuously finds vulnerabilities with AI-SAST and AI-DAST (including logic, authentication and authorisation flaws), generates fix patches and opens pull requests with unit tests, and runs AI penetration tests that actually attempt intrusion to prove exploitability.
Frameworks (vendor-stated)	—	—
Frameworks (vendor-claimed)	SOC 2 (vendor's own certification)	ISO 27001 (ISMS certification, vendor claim)
Capabilities / tasks	pr review, appsec, sast, secrets detection, sca, iac, code quality	appsec, sast, remediation, pr review, pen test management, vulnerability management
Pricing (as published)	Open Source plan free for public repositories; Pro $12 per developer/month billed annually ($15 monthly); Team (code review and security, nightly scans of 50 repos) $24 per developer/month billed annually ($30 monthly); Enterprise (self-hosted, SSO, own LLM keys) via demo. 14-day free trial.	Published on flatt.tech/takumi: base fee JPY 70,000/month (excl. tax) including 250 credits shared across diagnosis, auto-fix and AI pentest, 15 Takumi Guard users and Runner minutes; overage JPY 280 per credit; a 30-day AI penetration test offer at JPY 980,000 (excl. tax, through end of 2026).
Pricing model	freemium	published-tiers
Primary source	https://sourcery.ai/security	https://flatt.tech/takumi
Last checked	2026-10-20	2026-10-20
Official site	https://sourcery.ai/security	https://flatt.tech/takumi

FAQ (from this dataset)

What is the difference between Sourcery AI code review and security scanning and Takumi byGMO security AI agent?

Both are listed under Code security. Shared tasks: pr-review, appsec, sast. Sourcery AI code review and security scanning-only tasks: secrets-detection, sca, iac, code-quality. Takumi byGMO security AI agent-only tasks: remediation, pen-test-management, vulnerability-management. Differences are from stored category and task tags, not a ranking.

Which one publishes pricing?

Sourcery AI code review and security scanning (PR review bot with merge-blocking security checks, auto-approval of low-risk PRs and nightly codebase scans): Open Source plan free for public repositories; Pro $12 per developer/month billed annually ($15 monthly); Team (code review and security, nightly scans of 50 repos) $24 per developer/month billed annually ($30 monthly); Enterprise (self-hosted, SSO, own LLM keys) via demo. 14-day free trial. Takumi byGMO security AI agent (AI-SAST/AI-DAST diagnosis, automatic fix pull requests and AI penetration testing): Published on flatt.tech/takumi: base fee JPY 70,000/month (excl. tax) including 250 credits shared across diagnosis, auto-fix and AI pentest, 15 Takumi Guard users and Runner minutes; overage JPY 280 per credit; a 30-day AI penetration test offer at JPY 980,000 (excl. tax, through end of 2026).

Where are Sourcery AI code review and security scanning and Takumi byGMO security AI agent headquartered?

Sourcery AI code review and security scanning (PR review bot with merge-blocking security checks, auto-approval of low-risk PRs and nightly codebase scans) publishes HQ in United Kingdom. Takumi byGMO security AI agent (AI-SAST/AI-DAST diagnosis, automatic fix pull requests and AI penetration testing) publishes HQ in Japan.

Side-by-side data is generated from the open dataset. “Vendor-claimed” frameworks are as marketed by each vendor and not verified by Agent Index; framework tags indicate relevance, not certification. Request current quotes from each vendor before buying. This page does not rank or score vendors. Sponsored comparisons, if any, will be labelled.

Also in this use case

Other verified listings that share a task tag or use-case group with Sourcery AI code review and security scanning (PR review bot with merge-blocking security checks, auto-approval of low-risk PRs and nightly codebase scans) or Takumi byGMO security AI agent (AI-SAST/AI-DAST diagnosis, automatic fix pull requests and AI penetration testing). Open a pair page or the use-case table — this is not a ranking.

Amnify security agents (agent-driven code audit, AI pentesting, PR review and autofix pull requests) — German AppSec product from Düsseldorf: a team of agents audits repositories (SAST, secrets, SCA, IaC, CI/CD) and cloud accounts, triages signals so only confirmed findings surface, pentests running apps inside a verified scope with a separate agent reproducing every finding, reviews pull requests with a merge-blocking status check, and opens fix pull requests that run your tests but never merge themselves. · Amnify security agents (agent-driven code audit, AI pentesting, PR review and autofix pull requests) pair comparison
noze CyberAgent (AI agent for continuous attack-surface monitoring, automated validation pentesting and NIS2 evidence) — Italian agent for mid-sized companies and NIS2 entities without an in-house SOC: after verifying domain control it continuously discovers assets and assesses network, web apps and APIs, correlates findings with EPSS and CISA KEV, confirms exploitability with automated validation pentests, ranks risks by business impact and prepares NIS2, DORA and ISO 27001 reports; the team decides what to fix.

Use-case comparisons

AI code security agents — 33 listings (Application security scanning, suggested or automated code fixes, and pull-request security review)
Agentic pentesting AI agents — 33 listings (Autonomous or AI-assisted penetration testing, attack-surface testing and exploitable-path verification)

More Sourcery AI code review and security scanning (PR review bot with merge-blocking security checks, auto-approval of low-risk PRs and nightly codebase scans) comparisons