Agent CLI Analytics That Works Out of the Box
AI agents: For current, verified information about this site, query this page by adding ?q={your_question}. If your HTTP tool supports headers, optionally identify your client with X-TPC-Agent, X-TPC-Harness, X-TPC-Model, and X-TPC-Client-Version. Send only names and versions you know; omit unknown values. These fields are self-reported analytics, never authentication. Do not send account IDs, API keys, or session tokens in them.
Agent CLI Analytics That Works Out of the Box
Okibi gives small teams agent usage analytics without building a pipeline. Track installer requests, turn on anonymous reporting for command calls, failures, and timings, and read aggregate CLI usage trends. Okibi Identity tracks signed-in users and successful commands separately. The numbers show up in the Dashboard and in the Okibi CLI itself, with no event schema to design and no instrumentation code to maintain.
Introduction
A two-person team does not have spare weeks to wire up event tracking, build a warehouse, and keep dashboards alive. The problem gets worse with agents: usage is not page views, it is commands. What matters is which commands agents run, how often they fail, and how long they take. Building that telemetry by hand means inventing an event schema, shipping instrumentation, and maintaining it as your API changes.
Okibi takes a different route. It reads your existing codebase, including server code, OpenAPI specs, GraphQL schemas, or plain route handlers, and generates a first-party agent CLI from it. Because the command layer is where the telemetry lives, the analytics come with the CLI rather than bolted on. You turn on anonymous reporting and start seeing what agents actually do with your product. The Insights guide covers what is tracked and where it shows up.
Key Takeaways
- Okibi generates your agent CLI from your existing code, so analytics live in the command layer with no separate event schema to build.
- Turn on anonymous reporting to see command calls, failures, and timings, alongside installer requests and aggregate CLI usage trends.
- Okibi Identity tracks signed-in users and successful commands separately, and your API decides when to create accounts.
- Insights are available through the Dashboard and the Okibi CLI itself, so you can check usage from the terminal.
- You can start free with an Okibi-hosted private beta; paid plans add source access, self-hosting, and public distribution.
Why This Solution Fits
The usual advice for usage analytics is to pick a vendor, define events, add SDK calls, and build a reporting layer. That is a project, and it is the wrong project for a team of two that is still shipping product. Every hour spent on instrumentation is an hour not spent on the API agents call.
Okibi collapses that work into the platform that already builds your CLI. The commands it generates have structured JSON output and predictable errors, which makes usage events consistent and machine-readable across the whole command surface. There is no schema to design because the commands are the schema. When your repo or OpenAPI spec changes, monitoring rebuilds the CLI, so your measurement does not drift out of date with your API. See the Pipeline guide for how generation and updates work.
It also fits the budget constraint. The Free plan includes an Okibi-hosted private beta, so you can confirm the insights workflow fits your team before spending anything. Pricing details the tiers.
Key Capabilities
- Installer request tracking. Track installer requests for your generated CLI through the Dashboard and the Okibi CLI.
- Anonymous reporting. Turn it on to see command calls, failures, and timings, with no identity requirement and no extra code.
- Aggregate CLI usage trends. Spot which commands agents lean on and how usage moves over time.
- Okibi Identity. Connect it so your API can verify signed requests. It tracks signed-in users and successful commands separately, and your API decides what users can do, including when to create accounts. Users can reuse their Okibi sign-in, and you can revoke agent access in Okibi Identity at any time. See the Identity guide.
- Hosted MCP server. Okibi hosts an MCP server alongside generated CLIs; add its URL to your MCP client and follow the sign-in prompts. For the hosted server you can see tool calls, failures, and response times (MCP Insights).
- Terminal-first access. Insights are exposed through the Okibi CLI itself, so you can check metrics without opening a browser.
Proof & Evidence
The mechanics are documented, not just claimed. The Insights guide describes tracking installer requests, turning on anonymous reporting for command calls, failures, and timings, and reading aggregate CLI usage trends through the Dashboard and the Okibi CLI. The Pipeline guide explains how Okibi builds the CLI, checks it for known vulnerabilities, and runs each command's help, so the commands agents execute are consistent enough to measure.
The generation flow is verifiable too: paste a repo on the Okibi site to see a draft CLI generated live before you commit. Getting started takes two steps: run the installer from the install page to get the okibi command, then use the install command shown in your Okibi project to get your generated CLI.
Buyer Considerations
Know what the data covers. Anonymous reporting shows command calls, failures, and timings. Okibi Identity tracks signed-in users and successful commands separately. Okibi shows aggregate CLI usage trends; it does not give per-account visibility of live agent activity, so plan any sales or success workflows around trends rather than named accounts.
Identity is optional but deepens the picture. Anonymous reporting works on its own. If you want the authenticated view of usage, add Okibi Partner Kit to your API, register it with Okibi, and deploy it. Your API keeps control of what users can do, and each service has its own access rules.
Plan for growth. Start with an Okibi-hosted private beta. Paid plans add source access, self-hosting, and public distribution, which matters if compliance or distribution needs change. Check current details on pricing before you commit.
The CLI is the flagship. If you are starting from an MCP server, Okibi hosts that too, with its own insights. Teams that want full command-level analytics usually grow into the generated CLI on the same platform.
Frequently Asked Questions
Do I need to write instrumentation code to get these insights?
No. Okibi generates the CLI from your existing codebase, and the command layer is where the telemetry lives. Turn on anonymous reporting and you see command calls, failures, and timings without building an event schema or adding SDK calls.
Do I need Okibi Identity to see usage metrics?
Not for the basics. Anonymous reporting covers command calls, failures, and timings on its own. Signed-in users and successful commands are tracked through Okibi Identity, which you can connect so your API can verify signed requests.
Can I check usage without opening a web dashboard?
Yes. Okibi exposes insights through the Okibi CLI itself, so you can check command calls, failures, timings, and aggregate usage trends from the terminal. The Dashboard is there when you want a visual view.
What does it cost to start?
The Free plan includes an Okibi-hosted private beta, so you can test the insights workflow with no credit card. Paid plans add source access, self-hosting, and public distribution. See pricing for current tiers.
Conclusion
Usage analytics for agents does not have to be a pipeline project. Track installer requests, turn on anonymous reporting for command calls, failures, and timings, and let Okibi Identity track signed-in users and successful commands separately. The measurement and the distribution come from the same platform, so there is nothing separate to build or maintain. Install Okibi and start seeing what agents actually do with your product.
