cd /news/ai-agents/open-source-tax-rules-for-100-countr… Β· home β€Ί topics β€Ί ai-agents β€Ί article
[ARTICLE Β· art-152273] src=github.com β†— pub= topic=ai-agents verified=true sentiment=↑ positive

Open-source tax rules for 100 countries that your LLM can use

OpenAccountants has published an open-source library of 1,903 AI tax skills covering 229 jurisdictions, of which 33 are accountant-reviewed and 38 named accountants are credited, with 20,132 questions answered through connected AIs as of a 2026-10-18 nightly sync. The skills are served to Claude, ChatGPT, Cursor, Windsurf and other MCP clients through a hosted connector at openaccountants.com/api/mcp, or self-hosted via the pip package openaccountants-mcp, so models can cite a fetched skill and its published review status instead of answering from training data. Each skill is labeled either accountant-reviewed, with the reviewer named in frontmatter and on the public VERIFIERS.md roster, or source-cited draft, and the project runs nightly maths checks, source-watch monitoring and a monthly refresh budget that refuses to publish any figure without a link.

read4 min views1 publishedOct 18, 2026
Open-source tax rules for 100 countries that your LLM can use
Image: Michielbdejong (auto-discovered)

Free AI skills (tax rules your AI follows) your AI can cite, with sources and published review status.

This library includes accountant-reviewed skills and source-cited drafts. Check each skill version's review record before relying on it; a named author is distinct from a professional reviewer. Skill content is source-available under the terms in LICENSING.md.

1,903 AI skills across 229 jurisdictions Β· 33 accountant-reviewed Β· 38 named accountants Β· 20,132 questions answered through connected AIs

<sub>Live from openaccountants.com β€” updated 2026-10-18 by the nightly sync.</sub>

Add the hosted connector to Claude, ChatGPT, Cursor, Windsurf or any MCP client:

https://www.openaccountants.com/api/mcp

Guided setup: openaccountants.com/connect

Then ask a question your AI would otherwise guess at:

"What's the combined sales tax rate in Manatee County, Florida for 2026?"

Without OpenAccountants, models answer from training data. With it, the answer can cite the fetched skill and its review status. Name a professional reviewer only when that skill version has a published review record.

You:    "I'm moving to Malta and selling my company next year. What tax do I face?"
          ↓  loads moving-to-malta-tax-residence, selling-a-company-in-malta
AI:     Residence and domicile Β· Remittance basis on foreign income
        Gain on the share sale Β· Participation exemption check
        ─────────────────────────────────────────
        Authored by Michael Cutajar CPA, ACCA (Malta)

Prefer self-hosting or manual files? #

  • pip MCP server:pip install openaccountants-mcp (mirrors this repo'spackages/ )
  • Manual: download your jurisdiction's folder frompackages/ and upload the files to your AI. Start with your country's main package;index.json is the machine-readable inventory.

Every skill is in exactly one state β€” and the repo greps honestly:

State Meaning
Accountant-reviewed A named, licensed accountant reviewed the complete skill. Their name is in the frontmatter ( reviewed_by: ) and onthe public roster
Source-cited draft Written from primary legislation, every figure cited to its source β€” not yet professionally reviewed

General reference, not advice. skills may be incomplete, outdated, or wrong for your facts. Have a qualified professional review outputs before filing, payment, or action.

Your name on the tax knowledge AI actually uses β€” with attribution built in:

  1. Build a skill for the work you know cold:openaccountants.com/skills/new . It publishes credited to you, and lands in this repo under your name.
  2. Review a skill in your jurisdiction β€” your name, credential and review date go on it, here and on every AI answer that cites it.
  3. Set your GitHub username inyour profile and your platform edits are committed to this repo asyou β€” your contribution graph reflects your work.

The current roster: VERIFIERS.md (generated nightly from the platform).

A tax library is only as good as its worst stale number, so machines re-check this one every night:

  • The maths check re-reads every guide and flags sums that do not add up, tax bands with gaps, totals that do not total, and years that disagree.
  • The source watch visits the official pages the figures came from and raises a hand when a page changes.
  • The refresh engine re-derives the stalest guides from official sources on a fixed monthly budget, refusing to publish any figure without a link.
  • The nightly exam tests whether AIs actually said what the guides say that day, or improvised. Improvisation gets caught, counted and fixed at the source.

The sync runs both ways: platform edits land here as commits under the author's own name, and merged PRs here flow back into what every AI serves, credited to you. A guide with an accountant's byline never changes without that accountant's one-click approval.

The whole story, in plain words: openaccountants.com/how-it-works

Edit skills/** only β€” everything else regenerates automatically:

  • packages/ ,index.json ,llms-full.txt β€” generated nightly; never edit in a PR
  • Merged source PRs are credited to you and must be confirmed as ingested before the next platform export
  • Full guide: CONTRIBUTING.md Β· Layout:docs/REPO-LAYOUT.md
What Where
Skill source (per jurisdiction) skills/
Per-country bundles (generated) packages/
Machine-readable inventory index.json
LLM entry point llms.txt
Python MCP server mcp/ Β·PyPI
Repo architecture + sync docs/REPO-LAYOUT.md Β·docs/WEBSITE-SYNC.md

API and platform integrations: openaccountants.com/for-developers

Independent, open-source review aids and calculation tools that complement the OpenAccountants guide library:

  • payday-super-checker (MIT) β€” Verifies superannuation contributions against Australian Payday Super deadlines (in force since 1 July 2026) and estimates SG charge exposure on late payments, with all workings and statutory assumptions disclosed.
  • div7a-loan-review (MIT) β€” Reviews Division 7A loan terms and minimum yearly repayments against the ATO benchmark interest rate, with fabricated inputs and explicit refusal boundaries.
  • xero-trial-balance-export (MIT) β€” Exports a Xero trial balance to CSV only when month-movement and YTD column pairs both balance exactly.
  • ato-benchmark-compare (MIT) β€” Evaluates business P&L statements locally against the Australian Taxation Office (ATO) small business performance benchmarks, surfacing variance flags and ratio analyses.

(External tools provide computational review assistance and do not constitute tax or legal advice.)

Contact: info@openaccountants.com Β· Security policy Β· Cite this repo

── more in #ai-agents 4 stories Β· sorted by recency
── more on @openaccountants 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain β€” perfect for shipping the agent you just read about.

$git push zahid main
β†’ Live at https://your-agent.zahid.host βœ“
Get free account β†’ Pricing
from €0/mo Β· no card required
LIVE [news/open-source-tax-rule…] indexed:0 read:4min 2026-10-18 Β· β€”