Skip to content
Lateos logo

Lateos

Detects malicious and typosquatted npm packages by behavior, and offers a pay-per-query API serving executable SOAR security playbooks to AI agents.

At a glanceswept 2026-10-12

424 installs/mo

Emerging

For
developers and security teams building LLM systems or PostgreSQL infrastructure who need tested security tooling
Price
Price not read
Activity
Actively maintainedrelease 2 days ago
Company
Domain since 2026domain registered
Runs as
API
What people do with it
  • validate LLM defenses against recorded attack-pattern test datasets
  • scan npm dependencies for malicious packages and typosquatting
  • review PostgreSQL schema migrations before applying them
The companyeach fact with its source · read 2026-10-12
  • Domain since2026domain registered
How a program reaches itfound, not claimed · read 2026-10-12
  • MCP serverai.lateos/soar-record-gatewayverified in the MCP registry
  • Stateanswers, requires sign-inchecked 2026-10-12
  • Address to connectsoar-api.nevada-f99.workers.dev/mcp

MCP server details →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Securityby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

All Security tools →

Questions this page answers
  • What is Lateos?

    Detects malicious and typosquatted npm packages by behavior, and offers a pay-per-query API serving executable SOAR security playbooks to AI agents. It is listed in the Atlas under Security.

  • Who is Lateos for?

    developers and security teams building LLM systems or PostgreSQL infrastructure who need tested security tooling

  • Do people use Lateos?

    Emerging: 424 installs/mo (npm).

  • Is Lateos still maintained?

    Actively maintained: release 2 days ago.

  • What are alternatives to Lateos?

    In Security, by use: HiddenLayer, Superagent Cloud, Strix, AI Security Guard, DocVerify, Hacktron AI.

Not quite it? Describe the job

beta

Five tools from the Atlas that fit it, each judged against what you wrote.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.