RuleOak Core v2.0.1

Govern every AI tool call before it acts

RuleOak wraps agent actions with policy checks, evidence records, approval gates, and audit reports — without forcing developers to redesign their app.

Local-first AGPL Core Protocol v1 No cloud required
RuleOak tool call governance demo
Allowedsearch_docs
Approvalsend_external_message
Blockeddelete_workspace_file
npm install
npm run integrate:10min
npm run approval:inbox:build
npm run report:html

The shortest path: declare a tool, evaluate policy before execution, record evidence, pause for approval when required, then export an audit report.

Developer value

Add governance at the tool boundary

Keep your agent framework, your tools, and your local workflow. RuleOak sits at the action boundary where safety and accountability matter.

Policy outside prompts

Define allow, deny, and approval-required actions outside the model prompt.

Approval before risk

Pause external messages, writes, and high-risk tool calls before execution.

Evidence by default

Attach decision context so recommendations and actions are reviewable.

Audit reports

Generate local reports for tool decisions, approvals, and run history.

Start here

One command shows the whole governance loop

The 10-minute demo is the recommended first experience for developers evaluating RuleOak.

npm install
npm run integrate:10min
# search_docs: allowed
# send_external_message: approval_required
# delete_workspace_file: blocked

Platform shape

A small surface, with serious governance underneath

Interoperability

Built around a governance record protocol

RuleOak Core uses a versioned governance record protocol so SDKs, adapters, reports, and future connectors can share the same accountability model.

Protocol v1

Schemas and conformance checks for core governance records.

Adapter samples

LangGraph-style and CrewAI-style samples show how RuleOak can wrap existing agent flows.

Python bridge

Private-preview Python SDK guidance for emitting compatible governance records.