Paladin

Deterministic policy enforcement for AI agents. Early access, v0.1.

Identity tells you who an agent is. Paladin is the other half: what it may do, right now, decided before it acts.

Request early access

Run it now

Paladin installs as one command and enforces from the first request. It runs on your machine. Nothing leaves your network.

pip install paladin-ai
paladin up
paladin install-hooks --agent claude

After the third command every Claude Code tool call is checked against your policy before it runs. Codex CLI and Cursor integrate through their own hook mechanisms. Anything else runs behind the proxy.

• Read the docs
• See the benchmarks

The gap

Agents authenticate fine, then act unsupervised. Approval happens at deploy time; behavior happens at runtime. The missing control is a plain yes or no at the moment of action, decided the same way every time.

What Paladin is

• A control plane for agent actions.
• Deterministic policy, not model judgment. The same input gives the same decision.
• Self-hosted. It runs inside your own infrastructure.
• No data egress. Your data stays with you.

What Paladin is not

• Not an LLM. It does not guess.
• Not a dashboard that tells you what went wrong after the fact.

Where it sits

Paladin enforces inside your walls. CortexaNet governs between organizations. Robusto hardens the models underneath both.

Paladin is in early access. It installs today and enforces from the first request. We are working with a small number of teams on real runtime policy problems.

Request early access

Cortexa Labs, Inc.