| What it does | Catch your AI agents' mistakes, block the dangerous ones
| Security checks for AI-built apps before launch
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | Not given
| GB
|
|---|
| Pricing model | Not given
| Freemium
|
|---|
| Pricing | Free: $0/month with 5,000 conversations/month, Langfuse or LangSmith integration, problems and Slack alerts, rules that block costly actions, no credit card required. Starter: $49/month for 25,000 conversations/month plus email support. Growth: $149/month for 100,000 conversations/month plus priorit
| Free: All checks, terminal and JSON output, exit codes for CI. Pro: £99/year or £12/month, includes HTML reports, scan history, comparison features, priority support, 2 machines. Agency: £349/year, includes white-label reports, scan multiple projects in one report, 10 machines.
|
|---|
| Key features | - Monitor AI agent conversations without code by connecting Langfuse or LangSmith
- Judge conversations on six criteria: accuracy, goal alignment, decision quality, completeness, helpfulness, and factuality
- Create code-based rules that block risky actions before they run
- Group failures into problems with suggested rules and failure counts
- Send Slack alerts for serious mistakes and reply checks immediately
- Add to agents with one line of Python code for OpenAI Agents SDK, LangChain and LangGraph
- Mask sensitive data like email addresses, phone numbers and card numbers before sending to Kalytera
- Rules continue running offline if Kalytera goes down
- Correct judge verdicts by marking conversations as passed or failed
| - Detects leaked secrets including API keys, passwords, and LLM keys in browser code
- Checks database and storage security including row-level security policies and open Firestore rules
- Identifies API route and payment vulnerabilities including missing auth checks and unverified webhooks
- Detects AI and agent security issues including system prompt injection and unsafe model output rendering
- Scans dependencies for known vulnerabilities using OSV database
- Runs entirely locally with code never leaving your machine
- Works offline and integrates with CI pipelines using environment variables
- Provides fix suggestions and AI-ready prompts for each finding
- Supports multiple frameworks including Next.js, React, Vue, Svelte and platforms like Supabase, Firebase, Stripe
- Generates shareable HTML reports and tracks scan history with Pro plan
|
|---|
| What makes it different | - Rules are code-based, not AI, so they cannot be overridden or argued with
- No code setup using Langfuse or LangSmith connections for immediate visibility
- Rules continue protecting agents even when Kalytera is offline
- Catches exact mistakes from real AI agent incidents like database deletes, account takeovers and crypto theft
- Customer data stays on your servers; Kalytera only reads conversations, never writes or stores sensitive data
| - Designed specifically for security gaps that AI coding tools create
- Code never leaves your machine, with zero uploads required
- Low false alarms through context-aware checking of actual code behavior
- Free tier includes all core checks with no limitations
- Source-available license with code readable on GitHub
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 1 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 0 |
|---|
| Citation Flow (Majestic) | 14 | 0 |
|---|
| Referring domains (Majestic) | 28 | 0 |
|---|
Seaworthy