What Tablif read on Parry's site
Parry describes itself as: “Parry Catch bugs in AI-written code before you push”
- Price model: One-time · Monthly · free tier
- Free tier: Free forever
- Stage: Beta
What it costs
One-time purchase and monthly subscription. A free tier, free forever. Has an enterprise plan. Prices quoted: $19/month, $5/mo.
- One-time: yes
- Monthly: yes
- Free plan: free forever
- Price: $19/month · $5/mo
- Enterprise plan: yes
“$29 one-time lifetime license”
“Open Source MIT $0”
“MIT open source. Runs locally”
Who it sells to
Sells to developers. Built for solo users. Available in 4 languages.
- Sells to: developers
- Company size: solo / indie
- Languages: 4 languages
“For Solo Devs”
“JavaScript”
How it runs
A command-line tool. Runs locally and works offline. No API. Open source. AI is a side feature. You can bring your own API key.
- Kind: cli
- Runs where: on the device, offline
- API: no
- Open source: yes
- AI role: a side feature
- Bring your own key: yes
“MIT Open Source CLI · Python, JavaScript, TypeScript & Rust · Local-first”
“Parry runs locally in < 1ms to catch silent signer downgrades, hallucinated package imports (slopsquatting), and prompt-to-transaction wallet drains.”
What it works with
Integrates with Claude and Cursor.
- Integrates with: Claude · Cursor
“Register Parry as a local MCP stdio tool in Claude Code”
“Includes .cursorrules, CLAUDE.md, GEMINI.md, and AGENTS.md.”
What it offers as proof
In beta. Claims “25”. Try it without signing up.
- Stage: beta
- Number claimed: 25
- Trial asks for: nothing
“…v0.1.0-alpha”
“No account or license key required”
Sources
Tablif read these pages, last on 12 Nov 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- Bugweg: AI code review that spots bugs your team keeps repeating
- DejaLoop: A live brake for AI coding agents stuck in loops
- Code Buster: Static analysis for AI-assisted codebases
- FeedBug: Report bugs visually, get a Linear ticket with screenshot and diagnostics. AI traces bugs to source code via MCP. One script tag, set up in
- Slipmark: Make AI agents prove what they checked before anything ships
- Durabl: The self-correcting codebase for AI-assisted development
- ShipSpec: Practice catching what AI gets wrong
- bugrewind: The best #1