Related Products
|
||||||
About
Harden AIF is an agent endpoint security platform for AI coding agents. It evaluates supported agent tool calls before execution using the developer’s intent, session context, organisational policy, and the effect of the proposed action.
Harden helps protect against destructive commands, unauthorized access, unintended data transfers, secret exposure, privilege misuse, and other unsafe agent actions. Legitimate actions can proceed normally, sensitive data in supported flows can be safely redacted, and actions that fall outside the developer’s intent or authority are blocked before execution.
Harden works across popular coding agents and agentic development tools including Claude Code, Codex, Cursor, Antigravity CLI, Kiro, Hermes, and OpenClaw, providing a consistent security layer across the agent ecosystem.
|
About
Mountain Theory, the AI security company: every action an autonomous AI takes is checked before it runs, ALLOW, HOLD or BLOCK.
Mountain Theory controls what your AI agents can do. Every action is checked before it runs, then allowed, held for a person to approve, or blocked. When an agent tries to work around a block, the workaround is stopped too. When an agent drifts off the task it was given, that is caught. New bad behavior is stopped the day it appears, with no new rule needed.
It keeps personal data from leaving your environment and blocks instructions hidden in emails and documents. Rules are written in plain English, with no code. Every decision is logged for your auditor. It works with any AI you already use, in your environment or the cloud.
We publish our recorded tests, misses included.
|
|||||
Platforms Supported
Windows
Not Supported
Mac
Supported
Linux
Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Audience
Software engineering teams, security teams, DevSecOps teams, platform engineering teams, AI engineering teams, CISOs, security leaders, and enterprises deploying AI coding agents.
|
Audience
Enterprise security, risk and IT teams running autonomous AI agents
|
|||||
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Not Supported
|
|||||
API
Offers API
Not Supported
|
API
Offers API
Supported
|
|||||
Screenshots and VideosNo images available
|
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Supported
Free Trial
Not Supported
|
PricingPaid plans use flat annual pricing. A 30-day proof of concept is available.
Free Version
Not Supported
Free Trial
Not Supported
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
Training
Documentation
Not Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Company InformationHarden
Founded: 2025
United States
harden.run/
|
Company InformationMountain Theory
Founded: 2024
United States
mountaintheory.ai
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
Antigravity CLI
Supported
Claude Code
Supported
Cursor
Supported
Google Antigravity
Supported
Hermes Agent
Supported
Kiro
Supported
OpenAI Codex
Supported
OpenClaw
Supported
|
Integrations
Antigravity CLI
Not Supported
Claude Code
Not Supported
Cursor
Not Supported
Google Antigravity
Not Supported
Hermes Agent
Not Supported
Kiro
Not Supported
OpenAI Codex
Not Supported
OpenClaw
Not Supported
|
|||||
|
|
|