Weckr

Public roadmap

Roadmap

What we have shipped and what we are building next. No promised dates, just an honest map of where this is going.

Shipped

24

Building next

15

Months live

4

Shipped

24
  1. Foundation
  2. Shipped

    TypeScript SDK

    @weckr/sdk on npm. Wraps OpenAI, Anthropic, Gemini in two lines.

  3. Shipped

    Python SDK

    weckr-sdk on PyPI. Same interface, full Python support.

  4. Shipped

    Live dashboard

    app.useweckr.com. Cost, revenue, and margin in one view.

  5. Shipped

    OpenAI support

    gpt-4o, gpt-4o-mini, gpt-3.5-turbo. Token counts captured server side.

  6. Shipped

    Anthropic support

    claude-opus-4, claude-sonnet-4, claude-haiku-4-5.

  7. Shipped

    Gemini support

    gemini-2.5-pro and gemini-2.5-flash.

  8. Margin core
  9. Shipped

    Per-user margin tracking

    See exactly which users cost more than they pay. Per LLM call. Real time.

  10. Shipped

    Per-feature cost breakdown

    Know which features in your app are the most expensive to run.

  11. Shipped

    Unprofitable user alert

    Amber banner on the dashboard the moment a user goes negative.

  12. Shipped

    Zero added latency

    Fire-and-forget logging. Your LLM calls are never blocked by Weckr.

  13. Cost control
  14. Shipped

    Spending caps

    Monthly spend limits per plan. Block the call or downgrade automatically.

  15. Shipped

    Auto model routing

    When a user crosses their cap, silently swap to a cheaper model in the same provider.

  16. Shipped

    Model recommendations

    Spots features paying for a heavy model on simple tasks. Estimates the saving.

  17. Shipped

    Pricing recommendations

    From real usage data, suggests what to charge per plan for healthy margins.

  18. Real-time alerts
  19. Shipped

    Agent loop detection

    When a user burns 50k tokens in 5 minutes, Weckr fires an alert in seconds. Catches runaway agents before the bill arrives.

  20. Shipped

    Slack alerts

    A Slack ping the moment the velocity threshold trips. Per-project webhook, no global config.

  21. Shipped

    Email alerts

    Same trigger as Slack, delivered via email through Resend. HTML payload with the metric + a link to the user.

  22. Shipped

    No-code settings panel

    Set caps, alert thresholds, Slack webhook, and email recipient straight from the dashboard. No code changes.

  23. Distribution
  24. Shipped

    Multi-project support

    Track multiple products under one account. Switch projects in one click.

  25. Shipped

    MCP server for Claude

    npx -y @weckr/mcp. Ask Claude directly which users are costing you money.

  26. Shipped

    Demo without signup

    Full clickable dashboard with realistic seeded data at /demo.

  27. Shipped

    Break-even calculator

    Interactive tool at /calculator to see if your pricing actually clears costs.

  28. Framework integrations
  29. Shipped

    LangChain integration

    Boundary-wrap pattern documented for LangChain users. Wrap the underlying OpenAI client; chains stay untouched.

  30. Shipped

    CrewAI integration

    Same boundary-wrap pattern. Loop detection works on every CrewAI agent that goes through the wrapped client.

Today

Building next

15
  1. Notifications
  2. Next

    Margin alert cron

    Configurable per-user margin threshold that scans nightly and pings Slack/email when crossed. Settings UI is live; cron is next.

  3. Next

    Email weekly digest

    Every Monday: last week’s AI cost, top 3 expensive users, margin trend.

  4. Next

    Cost alerts by feature

    Not just by user. Get pinged when a specific feature spikes.

  5. Integrations
  6. Next

    Stripe integration

    Connect Stripe and Weckr pulls your real plan prices automatically.

  7. Next

    Webhook support

    Send cost and margin events to your own systems in real time.

  8. Next

    Native LangChain callbacks

    Drop-in CallbackHandler so chains and agents log cost without manual boundary-wrapping. Current pattern stays supported.

  9. Next

    LlamaIndex integration

    Automatic cost tracking for LlamaIndex pipelines.

  10. Provider reach
  11. Next

    Streaming support

    First-class support for streamed LLM responses. Chat UIs and real-time apps.

  12. Next

    Azure OpenAI support

    Full support for Azure-hosted OpenAI deployments.

  13. Next

    Mistral support

    Mistral models. Built for EU founders who need EU-hosted inference.

  14. Next

    Cohere support

    Cohere Command models.

  15. Team + scale
  16. Next

    Team seats

    Invite co-founders and team members to your Weckr dashboard.

  17. Next

    Data export

    Download all your cost and margin data as CSV or JSON anytime.

  18. Next

    Self-hosted option

    Run the Weckr backend on your own infrastructure. For security-sensitive teams.

  19. Next

    Public cost badge

    A badge for your README showing live monthly AI spend. Open accounting for AI SaaS.

Missing something?

We do not have a vote button or a backlog form. Open a discussion on GitHub (public, permanent, we reply to every one), or email hello@useweckr.com if you’d rather keep it off the public record.

Open a discussion →Get notified when features ship