Get paid to close your own issues.
Your community backs the issues they need with a few dollars each. Fix them yourself and keep the pool, or offload the work to a sandboxed agent you direct. Either way, when the fix merges, the pool pays you. And nothing runs until you press Start: no PR spam, ever.
One run, end to end
Little by little, it ships.
Small backings pool until there's enough to start. From there it's your call: fix it yourself and the pool is still yours, or press Start and steer the agent from funded to merged. It works for you, not the other way around. Scroll to follow one issue through an agent run.
See what's funded.
As community members back a public issue in your repo, CleverCrow keeps a single comment in sync with the funding pool. Take a funded issue on yourself, or put the agent on it; nothing runs without your direction.
Direct the plan.
Chose to offload this one? The agent drafts a plan in a credential-less sandbox, no git access, no push rights. Iterate until the approach fits your codebase, then greenlight it.
Codes and tests in isolation.
The agent implements the approved plan and opens a draft PR on an
agent/* branch. CI runs as normal; if it fails, send the
agent back to fix it.
Review on your terms.
Read the diff, leave feedback, request a revision, as many rounds as it takes, all in the open. Nothing merges until you're satisfied.
Merge, and get paid.
You merge, the pool settles: agent compute comes out at cost, CleverCrow takes 10%, and the rest is paid to you. Every settled issue shows the receipt, line by line.
Pebble queue is eventually consistent; crow is immediately thirsty
Funded · readysyrinxian/pitcher · issue #19
For backers
Fund the fix, not a fork.
That bug in your dependency that's blocked you for six months? Paying a stranger prices it in the hundreds and stalls waiting for one to bite. Here you back the issue with a few dollars, and the maintainer who knows the codebase drives the fix home and gets paid for it.
Back the issues you depend on.
Put a few dollars behind any open issue you depend on. Backings pool with other backers' until there's enough for the maintainer to press Start; your wallet stays untouched until they do. You're paying the maintainer who knows the codebase, not a stranger's weekend.
Your money pays the maintainer, not a markup.
Agent compute bills at cost, every charge itemised on your wallet ledger. When the fix merges, the pool pays the maintainer, and the receipt shows every line. If nothing merges, your money returns to your wallet.
Recruit the maintainer.
Repo not on CleverCrow yet? Back the issue anyway and the dashboard writes the invite for you to post on the thread. A backer with money already on the line is the credible version of "you should try this", and a funded pool waiting is the strongest onboarding pitch a maintainer can get.
For maintainers
How you get paid.
No invoices, no chasing. The pool settles the moment you merge, and the receipt shows every line.
Fix it yourself, or offload it.
The coding agent is a tool you can reach for, not the product. Take a funded issue on yourself and the pool pays you with zero compute spent. Or direct the agent when you want the leverage; compute bills at cost, only when you actually use it.
One flat fee, published.
CleverCrow's only fee is 10% of the pool at settlement. Agent compute passes through at raw cost, with no markup and no subscription. Every settled issue gets a line-item receipt: pool, compute, fee, payout.
Stripe payouts, monthly.
Connect a payout account once; Stripe handles the identity checks. Settled pools accrue to your balance and pay out monthly, with a $10 minimum that rolls forward. Available today for maintainers in the US, UK, EEA, Canada, and Switzerland.
Your backers show up on the repo.
A live comment on each backed issue shows visitors the pool and what the fix pays you. Merged PRs credit the backers who funded them, and a README badge counts the issues your community has shipped. The receipt is the marketing, on your repo, working for your next issue.
Fair question
Why not just run an agent yourself?
You could: coding agents are everywhere, and here the agent is optional anyway. Three honest reasons maintainers reach for CleverCrow's when they do want one.
The community pays you, not the other way around.
An agent on your laptop bills your card for other people's bug reports. Here the people who want the fix fund it: backers pool a few dollars against the issue, the run draws from the pool at cost, and when you merge, the rest of the pool is paid to you.
The whole workflow comes packaged.
Funding pool, plan approval gate, draft PR, CI-fix rounds, review-feedback rounds, settlement and refunds: one Start click runs the loop end to end, with you at every gate that matters. No terminal babysitting, no prompt wrangling, no copy-pasting CI logs.
The agent works in a padded room.
It runs in a credential-less sandbox: no git, no push rights, no tokens, no way to touch your repo. A separate, locked-down service applies the diff and opens the draft PR. That's a stronger boundary than an agent running on your machine with your keys loaded.
Aesop · The Crow and the Pitcher
Little by little does the trick.
One funded issue at a time, the work gets done. Your community funds it. You fix it yourself, or offload it to the agent. You ship it, and the pool pays you.