CaptainASIC /
reckoner
Self-hosted dashboard that shows your AI and cloud account balances in one place
- 67 stars
- 1 stars since 3 Oct
- Python
- Updated 33 days ago
- Some experience
- Token & cost savings
If you use many AI APIs and cloud services, your credits and bills are scattered across a dozen consoles. Reckoner puts them on a single page so you can see what is left and what you have spent.
It has a FastAPI backend in Python and a React frontend. The backend stores your credentials in a local SQLite database and has one provider file per service. It polls each service in the background every 5 to 30 minutes, and the browser refreshes every 60 seconds.
Some providers work with a normal API key. Others, such as Anthropic, Mistral, Groq, CivitAI and Perplexity, need a session cookie or token copied from your browser's developer tools, so those setups may be less stable. The README marks some balances as best-effort. The author also ships a separate, closed-source iOS app; this repo is only the web version.
What it does
Many providers on one page
Covers AI services (OpenRouter, OpenAI, Anthropic, xAI, Mistral, Groq, Manus, Gemini, Perplexity and more) and cloud services (Railway, Vercel, Neon, RunPod, AWS, GCP).
Automatic and manual refresh
The browser refreshes every 60 seconds and the backend polls in the background. You can also force a refresh for one provider or all of them.
Credentials set in the app
Enter keys through a settings modal on each provider card, or use environment variables. They are saved in SQLite on your server.
Optional password gate
Set RECKONER_PASSWORD to require login for settings, or for the whole dashboard. Login tokens are JWTs that last 30 days.
Several ways to deploy
Run it locally, deploy two services on Railway, or build the included multi-stage Docker image.
What you could build
- Track remaining prepaid credits across OpenRouter, Anthropic, xAI and other AI APIs in one view.
- Watch month-to-date spend on AWS, GCP and Railway without opening each console.
- Host a private balance dashboard behind a password for yourself or a small team.
- Spot a nearly empty account before an API-powered app starts failing.
- Read the provider files to learn how to write a new balance checker.
Get started
Copy .env.example to .env and fill in credentials for only the services you use. Then run the backend and frontend locally (needs Python 3.11+, Node 22+, pnpm and uv), or build and run the Docker image.
git clone https://github.com/CaptainASIC/reckonerdocker build -t reckoner .docker run -p 8000:8000 --env-file .env reckonerCommands are copied from the project's README. Read it on GitHub for the full setup.
More in Token & cost savings
caveman
Makes coding agents answer tersely and shrinks the logs and output they read
rtk
A command-line proxy that shrinks shell output before your AI coding agent reads it
headroom
Shrinks tool outputs, logs, and files before your AI agent sends them to the model
codegraph
A local code knowledge graph that lets AI coding agents look up code in one call
freellmapi
One OpenAI-style API that routes across dozens of free LLM provider tiers
context-mode
Keeps bulky tool output out of your coding agent's context window
9router
Local proxy that routes AI coding tools to subscription, cheap, or free models
pxpipe
Local proxy that renders Claude Code's bulky context as images to cut input tokens
Switchyard
Routing library that picks which LLM handles each agent request
billion-context
A proxy that compresses long coding-agent chats so one session can run for weeks