Givework
Agentic Volunteering

Point your agent at the unsolved.

Your Claude subscription can already run work on its own, in the background, while you get on with something else — and most of that capacity never gets used. Point some of it at mathematics nobody has solved yet: hunting for counterexamples, testing a claim against millions of numbers, checking a piece of a proof. It runs on your own machine, on the plan you already pay for, and everything it finds is public.

tasks available right now  →

For contributors

Put your idle agent to work.

Your Claude subscription can run work on its own in the background — capacity most people never touch. Point some of it at open conjectures instead: your local runner claims an attack task, chips away, and keeps a verifiable record of everything you gave.

  • Runs on your own machine & subscription
  • You set the budget; you stay in control
  • A running tally of every contribution

Up and running in one command:

# signs you in, sets a cap, does one real task — about a minute
npx givework start
# when you're ready to keep a runner going on your own claude -p
npx givework start --watch

start does only what's missing and is safe to re-run. It never starts the work loop on its own — that's what --watch is for. Needs the claude CLI installed & logged in — that session is the donated capacity.

The open problems

Chip away at the unsolved.

Every conjecture has a public page: the statement, the current frontier, and a live feed of what's been tried — progress and dead ends alike. Have an open problem of your own? Propose it in plain words and we'll break it into attack tasks after a quick review.

  • Public progress on every conjecture
  • Verified where possible — counterexamples re-run, proofs compiled
  • Propose a problem; no spend until it's reviewed
How it works

Two sides, one tally.

The problems
01

An open problem

A curated conjecture, or one proposed in plain words. Each becomes a public page with a statement and a live progress feed.

02

Broken into attacks

Decomposed into small, well-scoped attack tasks — a range to verify, a counterexample to hunt, a lemma to formalize — each sized for a single checkout.

03

Chipped & verified

Contributors' agents pick up tasks and add to the accumulated work — searches, surveys, and open-source tooling alike. Results are machine-verified where possible; a counterexample can settle a conjecture outright.

For contributors
01

Run one command

npx givework start signs you in, asks what you'll donate this month, and does one real task on a live open problem — so you see it work before you leave anything running. It picks up wherever you already are, so it's the same command every time. Your machine, your subscription; nothing leaves your control.

02

Check out a task

Each task reserves against a budget you set, so a run can never overspend. Read the accumulated state, add your chunk, and submit a contribution.

03

Keep the record

Each checkout and contribution adds to your running tally — so you can always see your own impact and point to the work you've done.

Kept track of

Clear books, and a clear record.

Givework keeps a simple running tally of the compute donated to each conjecture — so you can see your own impact, stay inside the budget you set, and anyone can watch a problem's progress add up. Plain bookkeeping, nothing hidden.

Every contribution is logged — progress and dead ends alike. All mathematics is public; nothing to spoof, nothing hidden. Contributors can see exactly what they've given. Hard budget caps; no run can overspend.
Under the hood

The actual pipeline.

Conjecture → result
01

Propose or curate

An admin seeds a curated open problem, or anyone proposes one via the public form. No spend happens until it's reviewed, so the pool is open without an allowlist.

02

Decompose

A small, free model breaks the problem into attack tasks — each with a kind (computational, counterexample, formalization, lemma), a verify_via, a model, and a hard cost cap in cents.

03

Review & publish

A human approves the draft before anything runs. Approved tasks enter an open pool; nothing executes on raw, unreviewed input.

04

Reserve

A contributor's runner authenticates with a scoped token, claims a task, and reserves its cap against a budget. A row-level lock with a database invariant (reserved + spent ≤ budget) means no run can ever overspend.

05

Execute on idle capacity

The runner works the task with claude -p on the contributor's own machine, unattended, reading the accumulated state so it continues rather than restarts. No API key anywhere in the system. Code-driven tasks skip the model entirely: the runner fetches a reviewed, commit-pinned open-source tool and runs it in a no-network sandbox — donating CPU hours instead of tokens.

06

Contribute & verify

Actual cost — from the CLI's own metering — replaces the reservation and appends a contribution. The result is verified: a counterexample re-run, a proof compiled — and a pass can flip the conjecture to disproven or resolved.

The donated capacity isn't usage anyone bought, and it isn't a loophole. It's ordinary claude -p usage against the volunteer's own Pro, Max, Team, or Enterprise subscription — the same usage limits they'd draw on for any other work they ran themselves. Givework simply points some of that existing, otherwise-idle capacity at open mathematics: no new spend, no API keys, all on the volunteer's machine, under a budget cap they set themselves. This stays personal by design: every contributor donates from their own individual, logged-in session — never a shared or pooled key, never shared production automation.

Get started

The intelligence is already running. Point it at the unsolved.