| What it does | Catch your AI agents' mistakes, block the dangerous ones
| AI security reviewer for engineering teams
|
|---|
| 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 for up to 2 active contributors or open source projects. Starter $95/month for up to 5 contributors, Team $195/month for up to 15 contributors, Growth $395/month for up to 40 contributors. Annual subscriptions billed upfront at ten times the monthly price (2 months free).
|
|---|
| 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
| - Codebase context mapping across repositories and components
- Architecture review and security assumptions analysis
- Focused vulnerability hunting with specialised security lenses
- Finding validation and deduplication
- HTML reports with source locations and suggested fixes
- Review state dashboard with findings filtered by severity
- CLI and terminal dashboard interface
- Support for Claude, Codex and OpenCode AI models
- Unlimited repositories and Dokima runs per plan
- Local data processing without uploading findings
|
|---|
| 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
| - AI-powered security review that learns how your software works and keeps reviewing as code evolves
- Findings challenged before presentation to separate plausible issues from weak ones
- Choose your own AI models to suit your budget and privacy preferences
- Full product trial for 21 days with no payment card required
- Free forever for small teams up to 2 contributors and open source projects
|
|---|
| 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 | 1 |
|---|