Guides & Cookbooks
Step-by-step guides and real-world cookbooks for Cadreen. Start with Why Cadreen, then pick the guide that matches what you're building.
How to Connect Cadreen
Start hereBase URL, API key, model name. Works with Cursor, opencode, LangChain, and any OpenAI-compatible tool.
Why Cadreen?
OverviewThe difference between a model and an intelligence layer. Outcomes, not features.
Cadreen CLI
CLIInstall the CLI. Chat, manage memory, test policies, and inspect traces from your terminal.
Model Provider
ReferenceThe /v1/chat/completions endpoint. Streaming, tool calling, reasoning content, what's different from OpenAI.
Governance Policies 101
GovernanceCreate policies, evaluate tool calls, understand the approval flow. Every action governed.
Tool Calling
AdvancedHybrid execution. Your tools pass through. Cadreen's tools execute with governance.
Cookbooks
Real-world recipes. Pick one, follow the steps, ship it.
How to save a pattern and run it with different inputs
AutomationBlueprints are reusable templates. Create one from a trace, run it with new parameters, automate it with schedules.
How to run blueprints automatically on a timer
AutomationAttach a schedule to any blueprint — daily, weekly, or cron. Pausing, resuming, and webhook events included.
How to set company-wide AI policies with one message
GovernanceWrite a policy in natural language. Cadreen enforces it across every surface — opencode, SDK, CLI, dashboard.
How to swap in Cadreen as your model provider
Getting startedChange two fields in your existing OpenAI-compatible code. Same messages, same tools — with intelligence added.
How to add human approval to any AI tool call
GovernanceGovernance blocks the tool call, returns a conversational prompt. Human says yes. No custom approval UI needed.
Building self-healing tool chains with precedent memory
ResilienceWhen tools fail, Cadreen classifies the error, fixes arguments, retries. Stores fixes as precedents for next time.
How to turn any REST API into a governed AI tool
IntegrationsUpload an OpenAPI spec. Cadreen auto-generates governed tools — credential-aware, failure-classified, health-checked.
How to audit every AI decision with intelligence traces
ObservabilityEvery response carries a trace ID. Fetch the full decision breakdown. Hash-chained for tamper detection.
How to make AI learn from repeated interactions
LearningCadreen spots repeated patterns and proposes turning them into reusable procedures. You approve. The system gets smarter.
How to review and act on what Cadreen suggests
LearningThe system spots patterns in your usage — recurring actions, time-based routines, automation opportunities — and proposes them as tasks. You decide what runs.
Building a governed CI/CD pipeline with Cadreen
DevOpsGo SDK in GitHub Actions. Cadreen assesses risk, checks policies, decides: deploy, handoff, or block.
How to share AI memory across opencode, dashboard, and scripts
MemoryOne workspace, five surfaces, zero sync code. A fact stored in one surface appears everywhere immediately.
How to enable GDPR, HIPAA, and PCI-DSS compliance in one call
CompliancePre-built compliance policy templates. One call. Your workspace enforces the standard across every tool call.