# Talooner

> Talooner is a deterministic PR guard for GitHub and GitLab. Your repository declares its policy as tln rules; rules decide every verdict, and a model is consulted only where a rule asks.

Talooner is the first line of defense against AI slop: a deterministic guard that reads
every pull request against the policy declared in the repository (`.talooner/rules.tln`,
written in tln — https://tln-lang.org/)
and approves, blocks, or routes it to the right person or team. Same commit, same rules, same
verdict. It runs self-hosted on the agent orchestration platform you already use —
OpenClaw, Hermes Agent, OpenTalon and others.

Talooner doesn't store any of your data because it runs on infrastructure you self-host: there is no hosted tier, the only call home is a daily license check (key, nonce, version — never code or PR data), the
CI runner is a container that keeps nothing, and facts, review history and LLM
credentials live only on your own servers.

## Docs

- [Install — as a pipeline step](https://talooner.dev/install/#pipeline): install Talooner as a step in your CI pipeline
- [Onboard a repository](https://talooner.dev/onboard/): draft a repository's first rules and tests with one command, or with the downloadable agent skill
- [How it works](https://talooner.dev/how-it-works/): the end-to-end flow, where a model fits, and which agents it works with
- [Automated QA](https://talooner.dev/automated-qa/): rules that decide when to deploy a preview and verify it with generated scenarios
- [Design checks](https://talooner.dev/design-checks/): compare the rendered UI of a PR with its design file (Figma first) and gate on design.* facts
- [Security checks](https://talooner.dev/security-checks/): check a PR's preview against an access policy in the repo, with agents acting as different roles, and block the merge on any access violation
- [Rules](https://talooner.dev/rules/): a full worked ruleset with its .tln.test suite and the facts rules can match on
- [Vibe coding](https://talooner.dev/vibe-coding/): why vibe-coded products need oversight, and how onboarding, agent testing and security checks provide it
- [The future of LLM review](https://talooner.dev/llm-review/): the cost of asking a chat LLM versus a context decision model (Jev, SubQ Snap), with the math
- [Full text](https://talooner.dev/llms-full.txt): every page above plus the example rules, in one file

## Example rules

- Secrets & tokens (require): Anything touching SSO config, access tokens or credentials is routed to security — automatically.
- Authorization (require): An agent quietly dropping an authorize! call is exactly the slop a tired reviewer misses.
- Supply chain (require): Hallucinated or freshly added packages get a license and supply-chain pass before they land.
- Doc drift (LLM) (block): The one place a model enters — because a rule asked. Its typed answer re-enters as a fact; the rule decides.
- Migrations (require): Schema changes go to the DBA with a checklist, not to whoever happens to be online.
- Auto-approve (approve): The payoff: small, green, documented changes off every sensitive path merge with no human in the loop.
- Tested (block): Policy is code, so it ships with tests. tln test fails CI the moment a rule drifts.

## Pricing

- Open Source (€0/month): Unlimited rules and PRs; Unlimited public repositories; AI review included; Triage fork PRs before a maintainer spends time on them
- Starter (€29/month): 150 PRs / month; 1 repository; Unlimited rules; Approve, block and route PRs
- Pro (€99/month): 750 PRs / month; 5 repositories; Unlimited rules; AI review included
- Team (€249/month): 2,000 PRs / month; 10 repositories; Unlimited rules; AI review and automated QA included
- Business (€499/month): 5,000 PRs / month; 25 repositories; Unlimited rules; Every module included
- Enterprise (contact us): Custom PRs / month; Unlimited repositories; Every module included; Help drafting your rulebook; Priority support

## Optional

- [Free demo or open-source license](https://talooner.dev/#pilot): a form on the home page issues a 10-day key at once; open-source applications are reviewed and extended