AI security · governance · cost — for AI agents

Govern every move your AI agents make.

CAGIS.ai is the enterprise control plane for AI coding agents. Every risky action is evaluated on the endpoint against your policy, secrets are tokenized before they leak, and every decision is audited — where AI intelligence meets governance, security, and cost control.

Agent action CAGIS gateallowaskdeny
See it in action

How CAGIS.ai works

Sixty seconds: the gate intercepts every agent action, routes what matters to a human, tokenizes secrets before they leak, and rolls the whole fleet into one console.

60 seconds · sound on for the full walkthrough (captions included)

The problem

Your teams gave AI agents a terminal. Who's watching?

Coding agents now run shell commands, read files, hit the network, and call tools — at machine speed, on every laptop. One prompt-injection or one careless command can exfiltrate a secret, wipe a disk, or phone home, and most orgs have no policy, no audit trail, and no idea how much it costs.

Secrets leak to models
Keys and PII flow into prompts and third-party APIs.
No approval, no audit
Destructive actions run with nobody in the loop.
Shadow AI everywhere
Agents, plugins, and MCP servers you can't see.
Runaway spend
Token cost with no attribution or budget.
What CAGIS stands for

Five disciplines, one control plane

C
Cost

Per-agent token & spend metering, budgets, and optimization.

A
Agent

Govern Claude Code, Codex, and hosted AI surfaces.

G
Governance

Native approval policy — allow, ask, or deny — fully audited.

I
Intelligence

Threat detection, DLP, and inventory without the friction.

S
Security

60-rule catalog, chains, shell-AST, secret tokenization.

Capabilities

Containment, not restriction

Enterprise guardrails that keep agents fast and useful — while making sure they can't read a secret, wipe a disk, or exfiltrate data without you knowing.

Behavioral threat detection

A 60-rule catalog across recon, execution, credential access, defense-evasion, C2, lateral movement, and supply-chain — enforced on-device, even offline.

Multi-step chain detection

Correlates a session's actions to catch attacks that span calls: read a secret → exfiltrate it, disable defenses → egress, steal creds → move laterally.

Shell-AST de-obfuscation

A linear POSIX tokenizer resolves quoting, ${IFS}, comments and metacharacter tricks, so evasions can't hide a dangerous action.

PII & secret DLP

Secrets are swapped for reversible vault tokens before the model, your logs, or the wire ever see them — only detector metadata leaves the machine.

Native approval policy

Allow, deny, or defer to the agent's own permission prompt. No custom dialogs. The gate fails closed — a crashed hook never means allow.

Cost & inventory

Per-agent spend, budgets, adoption analytics, and a fleet-wide inventory of the AI assets on every endpoint.

Outcomes, not seats

Priced on the risk you remove

CAGIS surfaces the value it delivers — leaks prevented, incidents caught, spend saved — and prices on the protection you get, not the number of people who log in.

100%
Actions governed
every tool call, on-device
0
Secrets to the model
tokenized before they leak
60+
Threat rules
+ multi-step chains
1
Command to deploy
Node-free, offline-capable
One control plane

Everywhere your agents run

From the terminal to hosted surfaces — governed by one policy, one audit trail, one console.

Claude Code Codex Hosted surfaces Zero-dep binary
# one command — installs the gate, wires Claude Code + Codex,
# then asks for your server URL + agent token, and verifies.
curl -fsSL https://cagisai.aiatscale.dev/install.sh | sh

Where the URL + token go: the installer prompts for your CAGIS server URL (e.g. https://cagisai.aiatscale.dev/api) and your agent token (Dashboard → My Agent). To skip the prompts (paste / MDM), pass them: …/install.sh | sh -s -- --url https://…/api --token cagis_…. Then restart Claude Code — risky actions are now governed.

Prefer the Claude Code plugin? /plugin marketplace add dinesh2648/CAGIS-ai/plugin install cagis@cagiscagis install.

endpoint governed — Node-free, offline-capable

Bring your AI agents under control.

See CAGIS.ai govern a live agent — threat detection, DLP, and approval policy — in a 20-minute walkthrough.