A few weeks ago we released the open-source Stigg Agent SDK, which governs every LLM call your agents make. Today, Stigg runs inside your agent orchestration layer, giving your orchestrator the monetization context it was missing: entitlements, credits, and budgets, at every step of a run.

🆕 What's new?

Complex agentic workflows run on an orchestrator. That layer decides which model to call, which tool to run, and when to hand a step to a sub-agent. Every one of those decisions has a cost, and until now the orchestrator had no idea what the customer is entitled to or how much budget is left.

The Stigg Agent SDK now natively supports the following orchestrators: Vercel AI SDK, LangChain & LangGraph, and Google ADK.

💡 Why it matters

• Decide during the run, not after it: Billing usually counts spend after the run, when it's too late to change what the agent did. Stigg moves the decision into the run, so you no longer have to choose between letting agents overspend (leaking revenue) and blocking the whole run up front (losing the outcome).
• Fall back to a cheaper model instead of failing: Give an agent a budget per model. When a customer's premium-model allowance runs dry, the next step answers with a cheaper model instead of stopping the run.
• Charge for premium tools: Monetize tools such as web search, code execution, or data enrichment per use. Each governed tool call is checked before it runs and metered after it succeeds.
• Run agents in parallel on a shared credit pool: Each agent gets its own allocation from the customer's pool, so one runaway agent can't drain the budget for the rest of the workflow.
• Track usage per customer, per agent, and per tool: Usage is attributed to the agent that made each call, so you can track cost and adoption without stitching logs together, and price from what runs actually cost.
• Price from real runs: Stigg meters each run end to end, so you know what a workflow actually costs. Use that data to make pricing and packaging decisions, whether you use token-based or outcome-based pricing, and keep iterating as your costs change or as your agents deliver more value.
• See Stigg in your existing traces. Every check and usage report shows up as an OpenTelemetry span, so Stigg appears in Langfuse, LangSmith, and similar tools with no extra configuration.

⚒️ Get started

1. Install the latest version of the Agent SDK: npm install @stigg/agent-sdk-js
2. Read the orchestrator guides: Vercel AI SDK, LangChain & LangGraph, Google ADK

📦 Availability

Agent orchestrator support is available in the Stigg Agent SDK v0.7.7 or later.

We are excited to announce that we have extended the Stigg Agent SDK to include out-of-the-box support for solo.io and agentgateway gateways.

🆕 What’s new?

You can now use the Stigg Agent SDK to automatically meter token usage, enforce access limits, and govern costs for every LLM call routed through these gateways without any heavy lifting.

💡 Why it matters

Managing autonomous AI agents requires granular control over access and budgets. By extending our native gateway support to include solo.io and agentgateway, we've made it easier to plug Stigg directly into the AI infrastructure you already rely on. Usage and cost metrics are intercepted and extracted natively, saving your engineering team from having to write and maintain custom metering logic.

⚒️ Get started

1. Upgrade to the latest version of the Agent SDK: npm install @stigg/agent-sdk-js
2. Read the Agent SDK documentation
3. Explore the open source library

📦 Availability

Support for solo.io and agentgateway is available to all customers using the Stigg Agent SDK v0.7.7 or higher. 

We're excited to announce that you can now bill customers for subscriptions to paid plans using invoices and payment links directly through our Airwallex integration!

🆕 What’s new?

We are bringing the power of manual invoice billing and interactive payment links to vendors using Airwallex! You can now seamlessly generate open invoices and share Airwallex-powered payment links directly from the Stigg app.

Whether you're handling B2B sales where the buyer isn't the end-user, or accommodating customers who prefer to pay via wire transfer, this update ensures you can manage these diverse billing scenarios effortlessly while leveraging your existing Airwallex setup.

💡 Why it matters

• Maximize Global Revenue: By bringing payment links to Airwallex, you can now tap into their vast network of over 160 local payment methods, making it easier for your international customers to subscribe using their preferred payment options.
• Streamlined Cross-Border Billing: Generate and share PDF invoices with your Airwallex multi-currency account details. This allows you to request payment via wire transfer in over 20 currencies, reducing foreign exchange friction for your global B2B buyers.
• Seamless Self-Serve with Global Reach: Once a customer pays via the Airwallex payment link, their payment method becomes the default on file. All subsequent subscription updates and renewals happen automatically, allowing you to easily scale your self-serve motion globally.
• Unified Finance Operations: Keep your billing operations consolidated. By utilizing payment links and manual invoices through your Airwallex integration, you maintain a single source of truth for your multi-currency cash flow and subscription management within Stigg.

⚒️ Get started

No complex setup is required. To start generating invoices and sharing payment links using your Airwallex integration, check out our detailed guides:

• Bill customers using invoices
• Subscribe using a payment link

📦 Availability

Invoices and payment links are now fully supported and available immediately for all environments configured with the Stigg Airwallex integration.

🍿 See it in action

Stigg's new pricing is now generally available or all new customers, with a generous free plan, flexible monthly billing, and pricing that scales with your product's usage.

🆕 What's New

Our new pricing introduces:

• Four plans for every stage: Build (Free), Pro, Scale, and Bring Your Own Cloud (BYOC), from early-stage development to enterprise-scale workloads.
• A production-ready free plan: Build includes 10,000 managed entities and 5 million usage events per month, so you can run Stigg in production for free.
• Usage-based pricing: Pricing is based on managed entities, monthly usage events, and event ingestion capacity, rather than seats or subscriptions.
• Predictable overages: Pro customers can exceed their included allowances at fixed overage rates, without interruptions to usage.
• Flexible billing: Choose between monthly and annual billing.
• Core capabilities on every plan: Credits, entitlements, usage metering, and governance are available across all plans, including Build.

⭐️ Why It Matters

Our new pricing removes barriers to getting started with Stigg. With a production-ready free plan and monthly billing, early-stage companies can adopt Stigg without an upfront commitment.

As your product grows, pricing scales with the entities and usage events Stigg manages, giving you a predictable path from your first integration to enterprise-scale usage.

📦 Availability & Migration

The new pricing is available now for all new Stigg accounts.

For existing customers, the transition works as follows:

• Free customers: Automatically migrated to the new Build plan. No action is required.
• Existing self-service customers: Can opt in to the new pricing from the Stigg app. Changes take effect at the end of the current billing period.
• Existing Scale customers: Your current plan and commercial agreement remain unchanged.

Explore the full plan comparison and pricing details on our Pricing page.

If you have questions about your migration, contact your Stigg account team or reach out to support.

🍿 See it in action

Usage Governance is now generally available to all Stigg customers, across all plans. No beta access or special enablement is required.

Define and enforce usage limits across organizations, teams, users, and AI agents, with real-time control over credit and product usage throughout your customers' hierarchies.

With GA, we've improved performance, expanded visibility, and introduced stable APIs for production use.

🆕 What's new?

• Client-side caching with Redis: Reduce enforcement latency with faster Governance checks.
• Entity type archiving: Archive entity types that are no longer needed without deleting their configuration.
• Governance data export: Export Governance data through Stigg's existing data export feature for external analysis and reporting.
• Expanded audit logs and webhooks: Track Governance activity for better visibility into hierarchy and entitlement changes.
• Stable APIs and SDKs: Governance endpoints have moved to the v1 REST API, with corresponding SDK and Sidecar updates.

💡 Why it matters

As AI products scale, teams, users, and agents need individual usage limits while sharing resources and budgets across an organization.

Usage Governance lets you model these hierarchies, monitor consumption, and enforce limits in real time, without building custom infrastructure.

Now available across all Stigg plans, with improved performance, reporting, and stable APIs for production integrations.

⚒️ Get started

1. Define your hierarchy: Create entity types for departments, teams, users, or agents.
2. Configure usage limits: Assign limits and define enforcement across the hierarchy.
3. Integrate enforcement: Use Stigg's APIs, SDKs, or Sidecar to check access and report usage.
4. Monitor consumption: Track usage and remaining balances in the Stigg app.

Explore the Usage Governance documentation, or get started faster with AI using Stigg's MCP server and updated Governance Skill.

📦 Availability

Already using Governance from the Private Beta? Review the updated documentation for the stable v1 API and SDK changes.

REST-based SDKs

• TypeScript: v0.1.0-beta.66

Services

• Sidecar service: v10.4.0
• Persistent cache service: v4.3.0

🍿 See it in action

We've rolled out a refreshed navigation experience to all Stigg customers, making it easier to explore the platform and find what you need.

As Stiggcontinues to evolve, our new sidebar brings clearer organization, updated branding, and room for our growing capabilities.

🆕 What's new?

• Four collapsible groups: Dashboard, Catalog, Management, and Developer, organizing capabilities into clear, easy-to-navigate sections.
• Updated account menu: Quick access to documentation, the status page, and the dark/light theme toggle.
• Dedicated Usage section: Easily find your account's plan and usage information.

💡 Why it matters

Less time navigating, more time building. The refreshed sidebar makes Stigg's expanding capabilities easier to discover and manage.

📦 Availability

The new navigation is live for all Stigg customers. No action required - just log in and explore!

🍿 See it in action

🆕 What’s new

You can now decide whether to grant credits for unused time when canceling subscriptions directly from the Stigg app. When initiating a cancellation, a dedicated toggle lets you choose whether to prorate and issue credits back to the customer or cancel without granting credit balance.

⭐️ Why it matters

Previously, customizing credit behavior during cancellation was only possible programmatically via the Stigg API. Canceling a subscription through the app defaulted to standard prorating rules, requiring manual API calls or developer support whenever you needed to cancel without granting credits.

With this update, customer support, sales, and operations teams have full control over cancellation outcomes directly within the dashboard - streamlining dispute handling, policy enforcement, and contract terminations without engineering overhead.

📦 Availability

This functionality is available across all Stigg environments that are integrated with a billing solution.

⚒️ Get started

When cancelling a subscription in the Stigg app:

1. Select the cancellation timing: immediately, on a specific date or end of billing period.

2. When selecting immediately or on a specific date, select the cancelation behavior: grant credits for unused time or not.

3. Confirm the cancellation.

🍿 See it in action 

We are excited to announce that you can now connect your Stigg environments to Airwallex with just a click of a button using our new OAuth integration!

🆕 What’s new?

Previously, configuring payment gateways required juggling API keys and manually managing secrets. With this update, we've replaced the manual setup with a seamless OAuth flow. You can now securely authenticate and integrate Stigg with Airwallex in seconds, directly from the Stigg app.

💡 Why it matters

• Instant Setup: Connect your environments instantly without hunting down or copying and pasting credentials.
• Enhanced Security: OAuth provides an industry-standard connection, eliminating the need to manually handle or store sensitive API keys.
• Zero Friction: Spend less time configuring infrastructure and more time focusing on your product and pricing strategy.

⚒️ Get started

To connect, navigate to the Integrations tab in the Stigg app, select Airwallex, and click "Connect with Airwallex". You'll be redirected to log in and authorize the connection, then routed right back to Stigg. 

🍿 See it in action

You can now reserve credits before an AI operation starts and settle the actual cost once it completes.

With Reserve & Settle, Stigg secures an estimated credit amount upfront, prevents concurrent requests from reserving the same balance, and automatically releases unused credits. It's designed for AI workloads where the final cost isn't known in advance, such as LLM completions, agent runs, and long-running jobs.

🆕 What's new?

• Reserve credits upfront - Secure an estimated amount before an operation starts, ensuring those credits are available even when multiple requests run concurrently.
• Settle the actual cost - Consume the credits used when the operation completes, automatically releasing any unused reserved amount.
• Automatically release expired reservations - Set an expiration time so abandoned or failed operations don't leave credits locked indefinitely.
• Safely retry requests - Use reservation IDs to prevent duplicate reservations or settlements.
• Track reserved balances - See reserved credits separately from consumed credits, with a clear record of reservation and settlement activity.

💡 Why it matters

AI workloads don't always have predictable costs. An LLM response might use fewer tokens than expected, an agent might execute multiple steps, or several requests might compete for the same credit balance.

Reserve & Settle lets you secure credits before work begins and charge for actual consumption afterward - without building custom reservation, refund, or reconciliation logic.

⚒️ Get started

1. Reserve credits - Call the reservation endpoint through Stigg's REST API or SDK before starting your AI operation.
2. Execute your operation - Run your LLM request, agent workflow, or background job while the reserved credits remain unavailable to other requests.
3. Settle the actual usage - Use the reservation ID to settle the final credit amount. Any unused reserved credits are automatically released.

Reservations also support expiration timeouts, ensuring abandoned operations don't leave credits locked indefinitely.

📦 Availability

Reserve & Settle is available through Stigg's REST API and REST SDKs.

REST-based SDKs

• TypeScript: v0.1.0-beta.62
• Python: v0.1.0-beta.53
• Go: v0.1.0-beta.54
• Java: v0.1.0-beta.54
• Ruby: v0.1.0-beta.59
• C#: v0.11.0

🍿 See it in action

We are excited to announce the release of the Stigg Agent Governance SDK, an open-source solution built on top of Stigg's highly scalable infrastructure, that empowers you to seamlessly meter, enforce, and govern every LLM call your product and its agents make!

🆕 What’s new?

Managing autonomous AI agents requires granular control over limits, costs, and access. The new Agent Governance SDK solves this by wrapping the LLM or gateway client you already use. By simply calling stigg.wrap(client) once, every subsequent model call goes through three critical steps:

1. Meter usage: Token counts (and costs, where supported) are automatically read from each response and reported to Stigg straight from the provider, making usage metering completely hands-off. The SDK includes native support for 18 LLM providers and gateways, including: OpenRouter, LiteLLM, Cloudflare, Databricks, Amazon Bedrock, OpenAI, Anthropic, Google Gemini, Groq, Mistral, Deepseek, Perplexity, Ollama, TypeSafe (Jev) and more. Supporting additional vendors is as easy as initializing the SDK with a recipe that defines the mapping logic.
2. Enforce access: Before a call even leaves your environment, the SDK checks that the agent has enough credits or metered capacity to perform its task. Agents that have hit their limit are blocked before they reach the provider, preventing unexpected costs.
3. Govern usage: Give each agent its own identity and budget under your teams and organizations. You’ll know exactly which agent spent what, and you can stop a single runaway agent without disrupting the rest of your system.

💡 Why it matters

• Native support for common LLM providers and gateways: Building custom metering logic takes time away from your core product. Our LLM and LLM gateway wrapping capabilities intercept calls natively, extracting usage and cost metrics automatically so you don't have to. 
• Enterprise-grade scale: The SDK is powered by Stigg's enterprise-grade infrastructure. Enjoy peace of mind with high-throughput metering capable of ingesting up to 1M+ events per second, and low-latency access enforcement that returns decisions in under 10ms.
• The power of Open Source: We've made the Agent SDK fully open source. This gives your engineering team complete transparency into how your LLM requests are handled in the request path, the flexibility to inspect and contribute to the code, and the freedom to easily customize the SDK for proprietary endpoints or internal architectures.

⚒️ Get started

1. Install the Agent SDK: npm install @stigg/agent-sdk-js
2. Read the Agent SDK documentation
3. Explore the open source library

📦 Availability

The Agent Governance SDK is available in public beta for all customers.

🍿 See it in action

Watch how simple it is to add metering, access enforcement, and governance to your AI agents: