Skip to main content
📖 The AI Tool Bible
getdebug preview image
getdebug logo

getdebug

Not yet source-checked

AI-powered codebase analyzer and auto-fixer that ships validated PRs

Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked Pricing captured How we rate

Freemium· Free tierCoding

In short

getdebug watches Git repos for bugs and vulnerabilities, generating validated fix PRs that pass your CI tests. It automates remediation for product teams without dedicated appsec staff.

Best for

Small-to-midsize product engineering teams that already run CI on GitHub-style repos and want validated fix PRs for bugs and vulnerabilities without hiring a dedicated appsec engineer.

Skip if

Solo tinkerers who just want an inline chat assistant, air-gapped enterprises that cannot connect a hosted service to their repo, or teams looking for a fully autonomous agent that also merges its own PRs.

getdebug is an AI code-review and auto-remediation service that continuously watches a Git repository for bugs, regressions, and security vulnerabilities, then generates a validated patch and opens a pull request for human review. Instead of stopping at a SARIF report the way most SAST tools do, getdebug produces a diff, runs the project's own build and test signals against that diff, and only proposes the change once it has evidence the fix compiles and does not obviously regress behavior. The engineer stays in the merge loop — nothing lands on main without approval.

The target user is a shipping product team that already has CI but does not have the bandwidth for a dedicated appsec or code-quality function. Typical workflows include continuous background scanning of one or more tracked repos, on-demand deep scans of a branch before a release, triage of committed secrets (Pro Plus adds git-history provenance to identify the first-seen commit), and cross-file refactor suggestions surfaced as reviewable PRs. Findings persist as stateful suppressions so the same false positive does not reappear every scan.

Pricing is per active seat with the first seat free, so solo developers and evaluators can use the paid tiers without paying, and pending invites are never billed. A free tier covers small teams that bring their own LLM API key; paid tiers include hosted inference. An adjacent public benchmark, codesecbench.org, is published by the same team and is used to calibrate the underlying detectors. getdebug is developer-facing infrastructure rather than a chatbot — the value shows up as merged PRs, not as prompts you have to write.

Editor's take

The interesting bet here is validation-before-PR: most 'AI security' tools stop at the SARIF report and let the developer figure out the fix, while getdebug commits to producing a diff and standing behind it with a build/test check. That shifts the review burden from triage to code review, which is where engineers actually add value. The per-seat pricing is fair for teams under ~15 devs; past that the caps start to bite.

— The AI Tool Bible editorial team

Pros

  • ✅ Delivers actual pull requests with proposed patches, not just a list of findings
  • ✅ Validates fixes against build and test signals before opening the PR, reducing noisy suggestions
  • ✅ Continuous repo watching plus on-demand deep scans in a single tool
  • ✅ First seat is always free, so solo devs and evaluators pay nothing on any tier
  • ✅ Free tier with BYO LLM key is genuinely usable for small teams (up to 5 members, 75 fix PRs/mo)
  • ✅ Stateful suppressions mean dismissed findings do not resurface each scan
  • ✅ Git-history provenance on Pro Plus pinpoints the first commit that leaked a secret
  • ✅ Publishes an adjacent security benchmark (codesecbench.org) that shows how detectors are calibrated

Cons

  • ⚠️ Per-seat pricing scales quickly for larger teams once you cross the seat caps on each tier
  • ⚠️ Underlying model family is not disclosed on the marketing site, which matters for teams with model-governance requirements
  • ⚠️ Free tier requires bringing your own LLM API key, so the true cost is not zero at that level
  • ⚠️ Hard monthly caps on fix PRs (75 / 150 / 350) can be a ceiling for large monorepos with many findings
  • ⚠️ Human-in-the-loop by design — teams looking for a fully autonomous fixer that also merges will need something else
  • ⚠️ Only integrates with Git-hosted repositories, so non-Git or heavily air-gapped codebases are out of scope

Pricing (captured )

TierMonthlyAnnualPer seatKey features
Free$0$0Yes
  • Up to 5 team members (with your own LLM key)
  • Up to 100 repositories
  • 75 validated fix PRs / month
  • On-demand security analysis
Pro—$39 / dev / moYes
  • Up to 15 team members
  • Unlimited deterministic fix PRs (secrets, deps, crypto, CORS…)
  • 150 AI-assisted code fixes / month (on us — no key needed)
  • Symbol-level dependency reachability (govulncheck)
Pro Plus—$79 / dev / moYes
  • Up to 30 team members
  • 350 AI-assisted code fixes / month
  • Deep insight — across every repo
  • Source→sink taint & sink analysis — interactive attack-path graph
Custom——Yes
  • 30+ team members
  • Unlimited AI-assisted fixes
  • Volume per-developer pricing
  • Zero-egress CLI scanning (--local-only / --local-llm) at scale
New usage-based———
  • Base + usage monthly base + per deep scan
  • Pick your LLM model per deep-scan stage — recon · hunt · validate
  • Bring your own provider keys — keyed stages run on your account at $0 markup
  • Unkeyed stages run on getdebug’s key, metered — pay only for what you use

Prices change; we show the grid as captured on Oct 29, 2026. Check current pricing on the vendor's site →

Facts

Free trial
Yes
Hacker News
1 story · top 2 points · last Jul 25, 2026 · checked Nov 12, 2026
Earliest Wayback capture
2026-07-25 (earliest archived capture of the site, not a launch date)

Where this tool sits

Use cases

Automated bug-fix pull requestsSecurity vulnerability remediationContinuous SAST replacementSecret-leak detection with git-history provenancePre-release deep code scansRegression triage on feature branchesAI-assisted code reviewCommitted-credential rotation workflows

Frequently asked

How much does getdebug cost?
Pricing is per active seat. The Free tier is $0. Pro is $39/dev/mo, Pro Plus is $79/dev/mo. Custom and pay-as-you-go options exist. The first seat is free, and pending invites are never billed.
Does getdebug merge code automatically?
No. getdebug generates a validated patch and opens a pull request for human review. The engineer stays in the merge loop, and nothing lands on main without explicit approval.
What integrations does getdebug support?
It works with GitHub-style repositories and runs the project's own build and test signals via CI. It is designed for teams already running CI on their repos.
Is getdebug suitable for solo developers?
Solo tinkerers wanting just an inline chat assistant should skip it. However, solo developers can use paid tiers for free because the first seat is free, and pending invites are not billed.
How does getdebug handle false positives?
Findings persist as stateful suppressions. This ensures the same false positive does not reappear in every subsequent scan, reducing noise for engineering teams.

Compare getdebug with similar tools

All alternatives →

Explore related

Reviews