What people actually say about Deepsource
26 mentions across 3 sources · 58% positive · researched Oct 15, 2026
Hacker News, YouTube, Product Hunt
What users praise
- • PR-native inline comments and merge gates make fixing issues feel mandatory, not optional
- • Autofix patches ship alongside findings, turning review into a queue-clearing exercise
- • 5,000+ deterministic rules back the AI agent, giving it grounding beyond raw LLM output
What frustrates them
- • All published accuracy benchmarks are vendor-run and haven't been independently reproduced
- • AI Review priced per 10K processed LOC can balloon on large, high-churn monorepos
- • Early Product Hunt feedback flagged missing Ruby, JavaScript, and GitLab support
This is a summary. The full report adds every quote we found, a per-source breakdown, recurring themes, hidden costs and the learning curve — run a free scan below, or see the full Deepsource review.
What comes up again and again about Deepsource
Recurring themes across everything we collected, with where each one showed up.
Vendor-published benchmarks are treated with heavy skepticism
criticised · seen on Hacker News
PR-first workflow with merge gates and inline comments is the standout feature
praised · seen on Product Hunt, Hacker News
Autofix and pre-generated patches reduce the manual review burden
praised · seen on Product Hunt, Hacker News
AI code review may not catch problems AI code generation creates
criticised · seen on YouTube, Hacker News
Language and VCS coverage gaps (Ruby, JavaScript, GitLab) lower adoption
mixed · seen on Product Hunt
Comparison against SonarQube, Codacy, CodeFactor, and CodeRabbit is a recurring ask
mixed · seen on Product Hunt, YouTube
AI agent integration (MCP, code-generation feedback loop) is the forward-looking bet
praised · seen on Hacker News
How hard is Deepsource to learn?
Users describe it as intermediate · typically A few hours to get going
Where people get stuck
- • Configuring rule sets and thresholds for existing codebases takes tuning
- • Interpreting the PR Report Card's five categories requires familiarity
- • MCP Server setup for agent workflows needs some integration knowledge
- • Monorepo per-sub-repository config is more involved than single-repo setup
Who Deepsource actually suits
Works well for
- • Engineering teams running PR-heavy workflows on GitHub or GitLab
- • Security-conscious orgs needing OWASP/SANS-mapped compliance reports
- • Monorepos that need per-sub-repository dependency scanning
- • Teams feeding review output back into AI coding agents via MCP
- • Platforms that want merge gates combined with Autofix patches
Not the right fit for
- • Solo developers who don't want per-LOC AI Review metering
- • Teams on languages without a native DeepSource static analyzer
- • Buyers who require independently verified security benchmarks
- • Short-horizon projects wary of post-acquisition roadmap shifts
What people are discussing right now
Discussion volume is medium and trending stable
- AI code review benchmark skepticism
- Autofix Bot and MCP agent integration
- Narada open-source secrets detection model
- Harness acquisition and roadmap implications
- Comparison vs SonarQube, Semgrep, CodeRabbit, Greptile
What people really think about Deepsource
A real-time sweep of the open web — social media, forums, review sites, video reviews and live community discussions — distilled into one honest verdict with the actual mentions behind it.
What's inside your Deepsource report
Everything you need to decide — distilled from real, current user opinion.
Live mentions
The actual posts, reviews & complaints about Deepsource — with links and dates.
Honest verdict
A straight answer on whether it lives up to the hype — and who it’s really for.
Praise & gripes
What users genuinely love and the frustrations that keep coming up.
Real quotes
Representative voices from real users, not marketing copy.
Recurring themes
The patterns across hundreds of opinions, surfaced at a glance.
Red flags
Hidden costs and dealbreakers people only discover after signing up.
How it works
Sign up free
Create an account in seconds — get 5 free scans, no card.
We sweep the web
Live social media, forums, reviews & video opinions — in ~30–60s.
Get your report
An honest, downloadable verdict with the real mentions behind it.
Ready to see the real verdict on Deepsource?
Your scan is ready in under a minute · $1.
Top alternatives to Deepsource
Researching options? Explore the closest alternatives.
CodiumAI
Agentic AI code review with a governance layer that enforces your team's coding rules on every pull request
Greptile
AI code review agent that checks every pull request against a graph index of your whole codebase
Qodo
Qodo runs agentic AI code review and governance on every pull request, grounded in your codebase, PR history, and tickets.
SonarQube
Static analysis and AI code verification that scans every pull request and blocks the merge when Quality Gates fail.
GitHub Copilot
GitHub Copilot is an AI coding agent that completes code, reviews pull requests, and runs agent tasks from issue to merge.
CodeRabbit
AI code review that validates, prioritizes, and secures every pull request your team ships.
Check sentiment on these too
Run a live scan on the alternatives before you decide.
Deepsource — questions buyers ask
What do people complain about most with Deepsource?
The complaints that recur most often are all published accuracy benchmarks are vendor-run and haven't been independently reproduced, AI Review priced per 10K processed LOC can balloon on large, high-churn monorepos and early Product Hunt feedback flagged missing Ruby, JavaScript, and GitLab support. Drawn from 26 mentions across 3 sources.
What do users like about Deepsource?
Users consistently praise PR-native inline comments and merge gates make fixing issues feel mandatory, not optional, autofix patches ship alongside findings, turning review into a queue-clearing exercise and 5,000+ deterministic rules back the AI agent, giving it grounding beyond raw LLM output.
Is Deepsource hard to learn?
Users describe it as intermediate; most people are up and running in a few hours; the usual sticking points are configuring rule sets and thresholds for existing codebases takes tuning and interpreting the PR Report Card's five categories requires familiarity.
Who should not use Deepsource?
Based on what users report, it is a poor fit for solo developers who don't want per-LOC AI Review metering, teams on languages without a native DeepSource static analyzer and buyers who require independently verified security benchmarks.
What are people saying about Deepsource right now?
Discussion volume is medium and trending stable. Current topics: AI code review benchmark skepticism, autofix Bot and MCP agent integration and narada open-source secrets detection model.
How current is this report?
Each scan runs live the moment you click — it reflects what people are saying now, and every report lists the dated mentions behind it.
Can I download it?
Yes — download the full report as a polished, shareable PDF.