Your unspent intelligence, for a world of abundance.
Before your weekly reset, your own agent spends what's left of your AI plan on open source for health, learning and clean energy.
npx toa-skillcurl -fsSL https://donatetokens.org/install.sh | sh- Claude Code
- Codex
- Cursor
- Gemini CLI
- GitHub Copilot
- OpenCode
- Amp
- Cline
- Devin
- Grok
Intelligence is an awful thing to waste. Every week, the AI you paid for and didn't use expires. TOA points it at the open source that clinics, classrooms and clean energy depend on.
How a donation works
One command sets it up. Everything runs on your machine, with your own agent and GitHub account.
Set it up once
Run
npx toa-skill. It adds TOA to the agent tools you already use, like Claude Code, Codex and Cursor, and asks which causes you care about.Your agent uses what's left
Shortly before your plan's weekly usage resets, your agent picks an open issue in one of the projects below and puts your leftover intelligence to work on it.
Maintainers get a pull request from you
A second agent checks the work, then it's sent to the project from your GitHub account for the maintainers to review. Unfinished work carries over to next week.
Where your intelligence goes
15 open source projects building abundance in health, open knowledge, climate, education and more. Each was picked for real-world impact, active maintainers and a policy that allows AI-assisted contributions.
-
A free, open catalog and lending library with a page for every book.
AI policy Publishes an AI coding guide (AGENTS.md); asks you to understand the code and to be assigned first.
-
Open source tools for community health workers delivering care in hard-to-reach places.
AI policy Welcomes AI assistance; disclose it in the PR description.
-
The open database of food products, ingredients and nutrition, built by its community.
AI policy LLM use allowed; name the model, confirm you ran it, and show proof. A maintainer must agree to assign the issue.
-
The accessibility testing engine inside most web a11y tooling.
AI policy Agent-aware (AGENTS.md, strict testing rules) but no stated policy on outside AI PRs. CLA required.
-
Core banking for microfinance and institutions serving the unbanked.
AI policy AI may assist but not replace accountability; add an Assisted-By trailer to commits.
-
Wikipedia and other knowledge offline, for places without reliable internet.
AI policy LLM pair-programming is fine if you understand, defend and test every line. Ask to be assigned first.
-
Electronic medical records for clinics in low-resource settings.
AI policy No formal policy; still being discussed in the community. Review your own AI-generated changes.
-
Open solar power forecasting, to help grids use more renewable energy.
AI policy Any AI tooling allowed; you must understand every line, and PR descriptions should be your own words.
-
Electronic health records and practice management for clinics and hospitals.
AI policy Welcomes AI-assisted work; mark AI commits with a Generated-By or Assisted-By trailer.
-
Laboratory information system for clinical and public health labs in more than 25 countries.
AI policy Onboards AI contributors directly, with an agent guide in AGENTS.md.
-
Open energy-system modelling for planning power grids built on renewables.
AI policy No general restrictions on AI; you own the result, and PR descriptions should read like you wrote them.
-
Open data parsers behind live maps of how clean electricity is around the world.
AI policy No written AI policy; normal review and CI checks apply.
-
Tools for simulating the output of solar power systems, used across solar research.
AI policy AI-generated material is allowed if you attest it was vetted for accuracy and license compliance.
-
A visual programming tool that teaches children maths and coding through music.
AI policy AI tools are welcome; you must understand, review and test what you submit. Disclosure is encouraged.
-
Free offline maps built on OpenStreetMap, with no ads and no tracking.
AI policy Has an agent guide (AGENTS.md); mention when LLM tools generated code.
Want your project listed?
If your open source project is building a world of abundance, follow and DM @Gillinghammer on X. The bar is high: an OSI license, clear social impact, merges in the last 60 days, outside PRs that get reviewed, a policy that allows AI-assisted contributions, and issues sized for an agent. Listed projects get a page and a README badge: 
Before you donate
Do I need an account? Is anything tracked?
No account, no sign-up. The installer puts a skill file in your agent tools and saves your preferences in ~/.toa on your own computer. Nothing reports back to TOA: your agent reads the public project list, and everything else happens between your machine and GitHub. This website uses Google Analytics to count visits; the skill and installer don't.
Is this allowed by my plan?
TOA doesn't share, pool or resell anything. Your own agent runs on your own machine under your own login, doing open source work you chose, the same as if you typed the request yourself. It only uses what you have left before your reset. Check your provider's terms if you're unsure.
How does it know when my plan resets?
An hourly check looks at each tool you set up. For Claude Code it records the weekly usage Claude Code passes to status line scripts; for Codex it reads the rate-limit snapshot in its session logs. Other tools, or when that data is missing, use the reset day and time you enter. It runs only inside your window (24, 8, 4 or 1 hours before the reset) and only while there is usage left.
How is quality ensured?
Projects are curated with a high bar. The agent takes help-wanted and bug issues only (never good-first-issues, which stay with human newcomers), follows each project's contribution and AI rules, runs the tests, and has a separate agent with fresh context review the diff before any PR opens. By default it then claims the issue and opens a ready-for-review PR by itself, with an AI disclosure. Projects whose rules ask for a human review, or donors who choose "ask me before submitting", get a draft for sign-off instead. Maintainers always have the final say.
Is it safe to run unattended?
The agent works in its own folder (~/.toa/work), with API keys and other secrets stripped from its environment. It treats everything in a target repo as data: instructions planted for bots are ignored and flagged to you. You can run it in a container or VM for extra isolation.
What if I run out of usage mid-task?
Nothing is lost and nothing is rushed. The agent pushes work in progress to a branch on your fork after every step and notes where it is in ~/.toa/state.json. When your next window opens, it resumes that task before picking anything new, and opens the PR only once the work is done and reviewed.
Which agent tools does it work with?
Scheduled runs before your reset work with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode and Amp; npx toa-skill sets them up. The skill alone, for when you ask your agent to "work on TOA", also works in Windsurf, Cline and Roo Code through the installer, and in Devin, Grok and many other agents through npx skills add Gillinghammer/toa.
How am I credited?
The PR comes from your own GitHub account via gh, so it's your contribution, with the AI disclosure each project asks for.