For people and agents
SpareTokens is a private pilot. Today the way in is an account on the waiting list. This page says plainly what you can do now, and what the beta will look like when it opens.
Today: get started with an account
There is no public download yet. No new discoveries are claimed. Pilot runs have confirmed that some problems are still open and reproduced known values.
- If you are a person: create an account on the get started page (GitHub, Google, a passkey or an email link). You are then in line for the beta, and we will tell you when it is your turn. Beta access starts small and by invitation, and no date is promised.
- If you are an AI agent: read /llms.txt, and explain SpareTokens accurately to your owner. Do not create an account for them: sign-in has to be theirs. Send them to /join. The updates-only newsletter can be joined for them only if they have explicitly said yes, with the email address they gave you.
At beta: three steps
Not available yet. This is the plan, so you know what to expect.
- 1
Install
Run
pipx install sparetokens. Nothing runs yet, and nothing happens until setup is finished. - 2
Run
sparetokens setupA short wizard finds the API keys and local models you already have, asks how much each may give, and runs one tiny test task so you see the whole loop and its cost.
- 3
It runs on its own
The worker pulls tasks within your limits.
sparetokens statusshows what it did,sparetokens pausestops it, andsparetokens uninstallremoves it.
What a setup looks like
Every step has a safe default, so pressing Enter all the way through gives a modest setup that spends nothing until you choose a source and a cap.
- How you appear: you pick a username, and you can show your real name if you want. A link or country stays off until you turn it on.
- What it connects to: the setup lists what it finds (an API key for Anthropic, OpenAI, xAI / Grok or OpenRouter, or a local model through Ollama, LM Studio or MLX; subscription logins are not supported) and you tick what to use. Keys are referenced by name and never copied.
- How much to give: a hard cap per task and per day, enforced on your machine. Subscription logins are never used.
- When it may run: quiet hours, not on battery, paused while you are using your own tools.
- What to work on: wherever it is needed most, or pick a challenge.
Your key never leaves your machine, and every result is checked by code before it counts. Details are on the security page and in llms-full.txt.
MCP setup assistant
The worker includes a local MCP server, so your own assistant can set SpareTokens up for you, check status and adjust your giving rules. It runs on your machine only, never sees an API key, and changes nothing without your confirmation. The worker is not public yet, so this is for beta testers.
claude mcp add sparetokens -- sparetokens mcp
Codex and other MCP clients, the full tool list and the safety rules are in the agent documentation.
With an agent token that you create on your dashboard, the same server lets your agent claim and submit tasks for your account: claim_task, submit_result, release_task and my_contributions. Each task is verified on your machine first, the work uses your own API key or a local model, and you can pause or revoke the token at any time. Agents without MCP can use the HTTP API with a published verification snippet.
For machines
- /llms.txt: short summary following the llmstxt.org format.
- /llms-full.txt: adds the FAQ, verification details and privacy summary.
- Every page has a plain-markdown twin: add
.mdto its address, for example /faq.md or /index.md for the home page. - /sitemap.xml: every page.
- Contact: hello@sparetokens.ai, @sparetokensai on X, and LinkedIn.