Developers
Everything PRAE publishes, in one place.
PRAE installs beside the agent: the gate is an npm package, the Claude Code hook decides on
the machine, and the Command Center runs on your machine. For a fleet, PRAE hosts a control
plane (AWS, EU): it enrolls each machine, ships one signed policy per group and receives each
endpoint's health and decision metadata, never prompts, commands or file contents. Admins
drive it with prae org, each request signed with their
own key; there is no shared API key. prae-ai.com serves one public, read-only API over what
the trust center publishes.
Install
npm install -g prae-cli # the prae command
npm install prae-gate # the gate, loaded by the agent harness as a plugin
prae check ./org.prae.json # validate a policy pack
prae explain ./org.prae.json write path=/etc/hosts
prae console ./ledger.jsonl --out ./console --serve # the console, and its record API on localhost The CLI
prae check— a policy pack against the schema;prae testruns it against security invariants.prae explain— why a call is allowed, held or refused, rule by rule.prae verify— a decision ledger's hash chain and signatures, offline;prae reportrenders it.prae console— the console as static pages from a ledger, and with--serveits record API on localhost.prae mcp— an MCP server over stdio: gated filesystem access for any MCP client. Every file read is judged, and sealed when--ledgeris given; listings are confined to the root.prae init claude-code— installs a Claude Code PreToolUse hook (prae hook claude-code) that judges each tool call before it runs, in shadow mode first.prae org— the fleet control plane, as an admin: policy versions and their approval, promotion and rollback per group, deployment profiles, registration codes,install-scriptfor Linux, macOS and Windows, the fleet view and integrity events.prae enroll,prae sync,prae agentd— an endpoint's side: enroll with a registration code, apply the signed policy, and run the agent that keeps it current and reports health and evidence.
The API
prae console --serve exposes a JSON API on
localhost: the record, the ledger and its verification. The Command Center server adds
same-origin mutations — signed with the operator key — for answering a held call and
steering a fleet; it ships with the Command Center today, not in prae-cli. Both are
described in /openapi.json,
with an operationId, a description and typed
schemas on every operation, and JSON error bodies throughout.
The public read API
https://prae-ai.com/api/v1
— no key, read-only, JSON. /api/v1/trust/status
says whether PRAE's control layer passed its latest validation run, and when;
/api/v1/trust/scenarios lists each attack, the
control expected to stop it and what was observed;
/api/v1/trust/provenance is the connector image's
build record. It reads the same published record as the
trust center; it controls
nothing.
Each client may make 60 requests a minute. Every response says where it stands in the
IETF RateLimit and
RateLimit-Policy headers; past the budget the answer
is a 429 with Retry-After. The budget is kept per
edge location, so treat it as a pace to keep, not a quota to plan against.
Versioning and deprecation
The public API is versioned in its path: /api/v1
changes only by adding fields and routes, and a breaking change would ship as
/api/v2 beside it. Every response names its
version in X-PRAE-API-Version. A route on its way
out carries Deprecation (RFC 9745) and
Sunset (RFC 8594) headers for at least 90 days
before it stops answering, and the OpenAPI document marks it deprecated in the same
release. The self-hosted API follows prae-cli's semver and carries the package version in
the same header.
Policy packs
A pack is a JSON document: rules over tools, paths, commands, data and approvals, each with an effect (allow, require approval, refuse) and a reason the operator reads. Packs can expire, can be signed, and layer: a built-in baseline, your organisation's rules, and a fleet steer an operator applies at runtime. The packs view shows a real one; the playground judges calls against one in your browser.
Resources
- prae-gate on npm — The gate: a plugin that judges every tool call against a policy pack and seals the decision.
- prae-cli on npm — The prae command: validate, explain, verify, serve.
- /api/v1 — The public read API: validation status, scenarios and provenance, no key.
- /openapi.json — OpenAPI 3.1 for the public read API and the self-hosted Command Center API.
- /llms.txt — The site for agents: what PRAE is, when to use it, how to call it.
- Trust center — Latest validation run, coverage matrix, limitations, provenance and SBOM references.
- Security policy — Where to report a vulnerability.