not read yet
Use
- For
- teams running AI agents that call provider APIs and need to keep provider keys out of agent environments
- Runs as
- Self-hosted
- Used for
- check agent identity, scope and budget before provider calls
- suspend one agent without rotating shared provider keys
- return signed receipts for allowed provider calls
- Publishes llms.txt, a file written for AI assistantsvertias.eu ↗
- Launched on Product Hunt on Oct 23, 2026Product Hunt ↗
- HeadquartersSofia, BGper their site
Figure and bar: visits/mo, estimate · year: online since
- #1
ArcjetMCP · sign-in
Checks each action an AI agent takes against prompt injection, PII, bot and policy rules before the call runs, and logs the decision.
738ActiveFrom $25/mo - #2
DocVerify
Detects forged and manipulated documents through forensic analysis before AI agents process them.
542ActiveFrom $10/mo - #3
APort
Enforces authorization policies for AI agents before they execute shell commands, access files, call tools, or modify repositories.
395ActiveFrom $499/mo2024 - #4
HedgeMCP · sign-in
Places hard-to-insure commercial risks with specialty carriers, tracking each submission in one shared file for brokers.
145Active2026 - #5
deepidv
Verifies identities and detects deepfakes through document, liveness, and biometric checks via API.
42ActiveFrom $19/mo - #6
Kaidn
Checks signups, logins and payouts for fraud through one API call, returning a verdict and a plain-language reason.
18ActiveFrom $39/mo
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use Peras for?
Sign in to leave a noteWhat is Peras?
Checks each agent's identity, scope and budget before it uses a provider API key held server side. It is listed in the Atlas under Security.
Who is Peras for?
teams running AI agents that call provider APIs and need to keep provider keys out of agent environments
Do people use Peras?
Emerging.
What are alternatives to Peras?
In Security, by use: Arcjet, DocVerify, APort, Hedge, deepidv, Kaidn.
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.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.