中文
~/home / Show HN
Show HN

Paranoia – Get a cold, adversarial review of your code

Paranoia – Get a cold, adversarial review of your code is a skill AI agent for Automatically uncover potential defects and design issues in code without relying on human reviewers. Pricing: not stated on the product page. As of 2026-10-27, KanonAgent records 4 upvotes. First indexed by KanonAgent on 2026-08-04.
Paranoia uses an AI-driven, adversarial review process to simulate harsh code critiques and expose hidden bugs and design flaws in your code.
Paranoia – Get a cold, adversarial review of your code — official preview image
4 upvotes
Tracked by Kanon since Aug 4, 2026
no signal yet
status
20/100
momentum · conf 0.74
66d
tracked since 2026-08-22
7
evidence records

No signal event on file yet — status is unknown, not "quiet".

📈 Timelinewhat changed, and when
🔎 Known / Unknown 9 of 23 fields unknown
Machine-callable— unknown —
Open source1 inferred 1 quote(s)
Self-hostable1 inferred 1 quote(s)
Bring your own key1 inferred —
Autonomy level2 inferred 1 quote(s)
Pricing modelsubscription inferred 2 quote(s)
Integrationsmcp,claudecode,codex inferred 1 quote(s)

“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.

🤖 Agent teardown · skill
Job to be doneAutomatically uncover potential defects and design issues in code without relying on human reviewers.
AutonomyL2 · tool-calling(evidence: "codex exec (read-only)…")
Who it is forDevelopers
Prerequisitesopen source · self-hostable · bring your own API key
Integrationsmcp · claudecode · codex
Real costsubscription
Why it matters

It stands out by simulating high-pressure, critical code reviews to strengthen code resilience, offering a unique approach to quality assurance.

Evidence quotesverbatim, from the product’s own materials

“public GitHub repository (README fetched)”— structural
“running locally, on its own subscription, with full read access to your repository.”— readme
“codex exec (read-only)”— readme
“signed in on a subscription”— readme
“paranoia-local is the MCP server between them”— readme
“running locally, on its own subscription”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Paranoia – Get a cold, adversarial review of your code badge
Building Paranoia? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
Share on X
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.

FAQ

What is Paranoia?

Paranoia uses an AI-driven, adversarial review process to simulate harsh code critiques and expose hidden bugs and design flaws in your code.

What does Paranoia do?

Automatically uncover potential defects and design issues in code without relying on human reviewers.

Why does Paranoia matter?

It stands out by simulating high-pressure, critical code reviews to strengthen code resilience, offering a unique approach to quality assurance.

Is Paranoia open source?

Yes — Paranoia is open source.

Can I self-host Paranoia?

Yes — Paranoia can be self-hosted.

What does Paranoia integrate with?

mcp,claudecode,codex

How popular is Paranoia?

As tracked by KanonAgent: 4 upvotes (first indexed 2026-08-04).

What are the best Paranoia alternatives?

Similar AI agents tracked by KanonAgent: Stealth Venture, taste-skill, open-design, deer-flow, ruflo, career-ops.

Paranoia – Get a cold, adversarial review of your code alternatives — similar AI agents

Stealth Venturetaste-skillopen-designdeer-flowruflocareer-ops

Where this fits — browse the same shelf

AI Agent Skills & PluginsAI agents that work with MCP (Model Context Protocol)AI agents that work with Claude CodeAI agents that work with OpenAI CodexSelf-hosted & open-source AI agents