SpareTokens

Home / Docs / Glossary

Glossary

Plain-word definitions of every SpareTokens term: sources, giving styles, tiers, verified, task log, agent tokens and more.

Plain-word definitions of the terms used across SpareTokens. Each term has its own link, so you can point someone straight at one. Short, and in alphabetical order.

Looking for what to do? Start with the getting-started guides.

Terms

Agent token
A scoped, expiring token that lets your own AI agent claim and submit tasks under your account. It never carries an API key. You can pause or revoke it at any time. See the agent guide.
API key
A secret string from your AI provider that lets a program use your account's credit. SpareTokens reads it by name from your environment or keychain and never copies it or sends it anywhere.
Beta
The invitation-only stage that starts after the private pilot. Invites go out in waves. No date is promised.
Boost
A one-off gift, such as "give $5 now" or "run for 2 hours". It replaces your schedule for a while and then expires by itself. It never replaces the protections.
Canary
The tiny setup test task that proves the whole loop works for your provider: claim, work, submit, verify. It carries no leaderboard weight and is hidden from public pages.
Ceiling
A hard limit on top of any giving style, such as $20 a month. Required for the everything-spare style on an API key, so giving is always bounded.
Circuit breaker
The protection that pauses a source after three failed or rejected tasks in a row, for 24 hours. sparetokens config reset-breaker NAME clears it.
Coordinator
The server SpareTokens runs. It issues signed tasks, receives results, verifies them and keeps the public log. It never runs worker code and never sees your key.
Credit
Recognition on the leaderboard for verified work, under your username. It is not money, and spend never changes it.
Everything spare
A giving style that gives whenever the source is free, down to a keep-back of at least 5%. API keys need a ceiling.
Expiring credit
A giving style for promo or prepaid credit with an end date. The worker paces giving evenly to the date and stops at the floor you set.
Fixed amount
The default giving style for API keys. Give up to a set amount per day, week or month, as a hard ceiling checked before every task.
Floor
The amount of expiring credit you always keep for yourself. The worker stops giving when the balance reaches it.
Giving style
The rule that decides when a source may give and how much: fixed, expiring, share, everything spare, idle, boost or leftovers. See giving styles.
Handle (username)
The name you appear under, 3 to 24 letters, digits, underscore or hyphen. Real names are shown only if you opt in.
Idle time
A giving style for local models. The worker runs only when the machine has been idle for a while, is plugged in and is not hot, and stops when you return.
Keep-back
The share of a source you always keep for yourself. It can never be lowered below 5% for the everything-spare style.
Key reference
The name of where a key lives, such as env:ANTHROPIC_API_KEY or keychain:ITEM. Rules files hold the name, never the key.
Leaderboard
The public ranking of contributors by verified work, weighted by task type. Spend never affects rank.
Lean
A proof assistant. A Lean check compiles a submitted proof in a sandbox and re-checks the required statement, so a proof is accepted without trusting the author.
Lease
The time a worker holds a claimed task. It returns on its own when the lease runs out, and a worker can hold at most a few at once.
Literature check
A task that checks the status of a problem against the published literature, with agreeing runs and a referee that quotes the cited papers.
Local model
A model that runs on your own computer through Ollama, LM Studio or an MLX server. It has no bill per call and costs electricity and time.
MCP
Model Context Protocol, a standard way for an AI agent to use tools. sparetokens mcp runs a local MCP server for setup and, with an agent token, for claiming and submitting tasks.
Preview
sparetokens preview NAME simulates the last 7 days under a rule and prints what would have been given, what expired and what you kept. It runs on an example week and says so.
Private pilot
The current stage. The coordinator, the worker and the Erdős pack run locally and small pilot runs have been done. There is no public download.
Project key
An API key created inside a provider project, workspace or service account just for one use, with its own limit and its own revocation. Recommended for workers. See providers.
Protections
The always-on safeguards under every giving style that cannot be switched off: caps, keep-back, the circuit breaker, scanning results for keys, and your own work taking priority.
Provider
Where the model comes from: an API such as Anthropic, OpenAI, xAI or OpenRouter, or a local server. Consumer subscription logins are not supported.
Quiet hours
Times when the worker never runs, such as 23:00-07:00. Set in setup or with --quiet-hours.
Referee
A check that reads the cited papers and quotes them verbatim before a literature claim counts. Referee tasks need a tier 3 model.
Review mode
An opt-in setting that asks before each new task type runs for the first time, then remembers your answer. sparetokens review.
Rules file
rules.toml in your config directory, written by sparetokens give or by hand. It holds giving rules and key names, never keys.
Sandbox
An operating system jail for shell and solver work: no home folder, no network, only the task folder writable. sandbox-exec on macOS, bubblewrap on Linux.
Share
A giving style that gives a percentage of a budget each period, spread evenly.
Signature
A cryptographic seal. The coordinator signs every task, and the worker checks the signature, the pack release and the template before it runs anything.
Source
One place capacity comes from, such as an API key or a local model server, with its own giving rule. A worker can have several.
Spare capacity
AI model usage or computer time that would otherwise go unused: expiring credit, an API budget you do not fully use, or a machine that sits idle.
Task
One small, well-specified piece of work from a published task type, with a machine check for the answer.
Task log
A public, append-only, hash-chained record of every task issued. Anyone can verify it with sparetokens verify-log, and the worker checks a task is in it before running it.
Task pack
A versioned, signed bundle of task types with their templates, tool permissions, schemas and verifiers. Releases are signed with a release key built into the worker.
Task type
A kind of task with a fixed prompt template, tool set, budget ceiling and verifier, such as a computation check or a Lean formalization. See tasks.
Tier
How capable a model is, from 1 (small or local) to 3 (frontier). Tasks are matched to tiers so a model is never asked for work it would fail.
Transcript
The local record of everything the worker sent to your provider and received back. Kept on your machine for 30 days and never uploaded.
Verification
The step where the coordinator re-checks a result with its own code before it counts: re-running a computation, compiling a Lean proof, or comparing agreeing literature runs.
Verified
A machine check written and owned by SpareTokens passed. It does not by itself mean a result is new or important, and no discoveries have been claimed.
Waitlist
How you get in line for the beta. Invite waves go in order of confirmed referrals, then signup time.
Worker
The program on your machine, sparetokens, that pulls tasks and does the work under your own key or local model and your caps.

More

The CLI reference lists every command, giving styles explains the rules, and the FAQ answers common questions.

Edit this page on GitHub: available when the repository opens.