NewsMacroNasiko Launches TokenOps, an AI-Agent Spending Tracker With Budget Controls

Nasiko Launches TokenOps, an AI-Agent Spending Tracker With Budget Controls

Author: CryptoBriefing·

Key Takeaways

  • •TokenOps enforces per-agent budgets with alerts issued at 80% of the configured limit and automatic pauses once spending hits 100%.
  • •OpenRuntime proxies all agent calls through a single server process, allowing cost attribution across multiple providers, including OpenAI and Gemini.
  • •Token usage and costs are broken down along three dimensions: by individual agent, by team, and by model.
  • •The runtime bundles an LLM router, MCP gateway permission management, loop-prevention mechanisms, and OpenTelemetry observability, with effective routing estimated to reduce token spend by up to 50%.
  • •TokenOps requires no SDK migration, supports coding agents such as Claude Code and Codex, and can be deployed either self-hosted or through a hosted option.
Nasiko Launches TokenOps, an AI-Agent Spending Tracker With Budget Controls

Nasiko, a technology company based in Palo Alto, announced on November 16, 2026 the launch of TokenOps, a set of spending-tracking and budget-control features built into its OpenRuntime platform. The company's pitch is straightforward: show what every AI agent costs, and stop it automatically when it runs out of allowance.

Budget Alerts and Automatic Pauses

Operators can set a budget for individual agents. When spending reaches 80% of the configured limit, the system sends an alert. When spending hits 100%, TokenOps pauses the agent's operations automatically.

That hard pause is the enforcement point for the runaway scenarios the runtime's bundled loop-prevention tooling targets: as long as an agent keeps making calls, providers keep metering tokens against it, so the ceiling is what turns an open-ended bill into a capped one.

The feature also breaks down token usage and associated costs along three dimensions: by individual agent, by team, and by model. Tokens are the units AI providers use to meter and bill usage, so tracking token consumption is effectively tracking the meter that determines the bill.

A Middle Layer for Cost Attribution

TokenOps is a feature rather than a standalone product. It lives inside OpenRuntime, which Nasiko describes as a control plane for AI agents. Technically, OpenRuntime runs as a single server process that proxies the calls AI agents make. Because every request flows through it, the platform can attribute costs across multiple providers, including OpenAI and Gemini.

That cross-provider view is the core of the spending tracker. Without a middle layer, each provider's bill arrives separately, and stitching the figures together becomes a manual task. It is also why the budget caps sit at the proxy: a limit enforced above the frameworks holds regardless of which provider an individual agent is pointed at.

Bundled Tooling

The open-source runtime bundles several other tools alongside the new budget controls:

  • An LLM router for model routing, which directs requests to different models
  • Permission management through an MCP gateway, handling which agents can access which tools
  • Mechanisms to prevent infinite loops, in which an agent keeps calling itself or a tool without end
  • Observability through OpenTelemetry traces, including automatic logging of tokens used and costs incurred

On the routing side, potential token spend reductions are estimated at up to 50% through effective routing.

Compatibility and Deployment

According to the project's materials, no SDK migration is necessary. Existing agents and workflows can keep running as they are while teams adopt centralized budget governance.

The platform supports popular coding agents, including Claude Code and Codex. Custom agents can be deployed in a containerized environment using Docker.

Operators can choose between deployment models: the platform can be self-hosted, or teams can use a hosted option. The project is publicly available on GitHub, where it has drawn significant community engagement — and because the code is open, operators can examine the controls directly before putting them in charge of budgets.

A Year of Steady Releases

TokenOps is the latest step in a year of steady releases for Nasiko. The company introduced its core control plane in May 2026. In September, it onboarded onto the DigitalOcean Marketplace, giving the platform another distribution channel. The November launch layers financial controls on top of the infrastructure that was already in place.

The “Agent Estate” Problem

Nasiko frames the broader problem around what it calls the “agent estate” — the growing collection of AI agents that teams run across different frameworks. Individual agent frameworks may track their own usage, but a cross-framework, cross-provider view requires something that sits above all of them. That sprawl, the company says, is the gap it is trying to fill.

Source: CryptoBriefing

Disclosure: The original article was edited by Diego Almada Lopez.