llms.txt
# Straion
> Straion is the governance layer for AI coding agents (Claude Code, Cursor, GitHub Copilot). It stores a team's engineering standards as structured, version-controlled rules, selects only the rules relevant to each task, validates the agent's plan before any code is written, and re-checks the resulting changes.
Straion keeps AI-generated code aligned with your architecture, security, and compliance standards, from the first prompt to merge. Import your existing AGENTS.md, CLAUDE.md, and .cursorrules files once, then manage everything from one central hub instead of scattered files that drift across repos. Rules are scoped by team, repository, language, and framework, so each task gets only the guidance that applies. It works alongside your AI coding tools; it governs, it does not generate.
## Product
- [Product overview](https://straion.com/product): What Straion does and how it governs AI coding agents.
- [How it works](https://straion.com/how-it-works): Rule selection by context, plan validation before code, and pull request enforcement.
- [AI coding guidance](https://straion.com/product/ai-coding-guidance): Guide Claude Code, Cursor, and Copilot with company-specific rules so AI-generated code follows your architecture, security, and quality standards.
- [Code review](https://straion.com/product/code-review): Automated pull request validation against non-functional requirements, so code stays aligned with company standards without manual review.
- [Requirements management](https://straion.com/product/feedback-on-requirements): Capture and manage your organization's requirements and keep specifications and code aligned at every step.
- [Pricing](https://straion.com/pricing): Plans and tiers (free tier to start, paid and enterprise tiers for teams).
- [Security and trust](https://straion.com/security): How Straion handles code and data. The CLI runs locally, source code is never stored, rules stay in your own Git, EU hosting, and no model training on your data.
## Solutions
- [Embedded software (MISRA)](https://straion.com/solutions/embedded-software): AI coding agents in MISRA C and C++ codebases. The applicable rules reach the agent before it plans, and every deviation carries a rule, a rationale, an approver and a date. Sits upstream of static analyzers such as Axivion, Polyspace, LDRA, Coverity and Parasoft, and carries no tool qualification of its own.
## Comparisons
- [AGENTS.md vs Straion](https://straion.com/product/straion-vs-agents-md): Why a static markdown file breaks down at team scale, with a before and after import example, and what Straion adds on top.
- [Straion vs custom skills](https://straion.com/product/straion-vs-skills): How Straion compares to custom skills in Claude Code and Cursor.
## Documentation
Every documentation page is also served as raw markdown: append `.md` to its path.
- [Getting Started](https://straion.com/docs/getting-started.md): A step by step guide to set up Straion: import your rules, install the CLI, and connect your first AI coding agent in under five minutes.
- [Prerequisites](https://straion.com/docs/prerequisites.md): What you need before you start using Straion: a workspace, a supported AI coding agent (Claude Code, Cursor, or Copilot), and access to your team's rules.
- [Core Concepts](https://straion.com/docs/core-concepts.md): What rules are and how Straion uses them to keep AI coding agents aligned with your standards
- [Import rules](https://straion.com/docs/import-rules.md): How Straion turns your existing standards and repository instruction files into structured, validated rule collections
- [Connect a repository](https://straion.com/docs/connect-repository.md): Store your rules as code in your own git repository and keep them in sync with Straion.
- [Rule file format](https://straion.com/docs/rule-file-format.md): The on-disk layout and file format for rules stored in a connected git repository.
- [Best Practices](https://straion.com/docs/best-practices.md): How to write clear, well-formed rules that AI coding agents can interpret correctly
- [Implement with rules](https://straion.com/docs/implement-with-rules.md): Use the straion-implement workflow to have Straion select relevant rules, validate your plan, generate constrained code, and check the output before you commit.
- [Validate specs](https://straion.com/docs/validate-specs.md): Check specs, RFCs, and design docs against your rules before implementation begins
- [Validate implementation plans](https://straion.com/docs/validate-implementation-plan.md): Catch rule violations in an implementation plan before any code is written
- [Validate code](https://straion.com/docs/validate-code.md): Validate a PR, diff, or AI-generated changes against your rules before merge
- [Automode](https://straion.com/docs/automode.md): Automode makes your agent look up your rules before it changes code, in every session.
- [Audit trail](https://straion.com/docs/audit-trail.md): Every rule Straion matches to a task needs a recorded decision before the agent can finish.
- [Live pane](https://straion.com/docs/audit-trail/live-pane.md): The straion-trail mod shows the audit trail in Claude Code while the agent works: what Straion corrected, what the agent fixed, and when Straion needs your approval.
- [Invite Users](https://straion.com/docs/invite-users.md): How to invite team members to your Straion organization: add email addresses, manage pending invites, and assign member roles.
- [SAML Single Sign-On (SSO)](https://straion.com/docs/sso.md): Connect Straion to your identity provider with SAML SSO: step-by-step setup guides for Okta, Microsoft Entra ID, OneLogin, and any SAML 2.0 provider.
- [SCIM Provisioning](https://straion.com/docs/scim.md): Automatically create, update, and deactivate Straion users from your identity provider with SCIM 2.0: setup guides for Okta, Microsoft Entra ID, OneLogin, and other providers.
- [CLI Reference](https://straion.com/docs/cli-api-reference.md): Reference for every Straion CLI command: login, logout, setup, and import-rules, with the options and flags each command accepts.
- [Troubleshooting](https://straion.com/docs/troubleshooting.md): Solutions to common Straion issues: agent setup checks, firewall and permission problems, skills that do not show up after setup, and SAML SSO and SCIM provisioning errors.
- [Example Prompts](https://straion.com/docs/example-prompts.md): Copy-paste prompts for common Straion workflows: build a feature end-to-end, plan an implementation, validate a spec, and validate code.
## Blog
- [See the Straion Audit Trail Live in Claude Code](https://straion.com/blog/audit-trail-in-claude-code): straion-trail is a Claude Code mod that shows what Straion corrected while the agent works, and tells you when it waits for your approval.
- [Automode: Straion Now Runs in Every Session](https://straion.com/blog/straion-automode): With Automode, your coding agent looks up your Straion rules in every session, without anyone calling a skill.
- [You Shouldn't Be Finding Rule Violations in Code Review](https://straion.com/blog/rule-violations-code-review): Straion turns every rule that applies to a change into a decision the agent has to resolve before the work is done, and every exception into one you approve.
- [Straion Rules Now Live in Git](https://straion.com/blog/straion-rules-now-live-in-git): Straion rules can now be managed in Git: versioning, pull request reviews, and full history.
- [Developers Asked Anthropic to Build This. We Did.](https://straion.com/blog/developers-asked-anthropic-to-build-this): A developer filed GitHub issue #14467 on claude-code describing exactly the problem Straion solves.
- [The Real Cost of Building AI Coding Governance](https://straion.com/blog/build-vs-buy-ai-coding-governance): Building your own AI coding governance layer sounds like a config project.
- [90% Rule Adherence](https://straion.com/blog/90-percent-rule-adherence-straion-coding-agents): When Claude Code runs with Straion, rule adherence climbs into the 90%+ range.
- [1M Tokens Won't Save Your Engineering Standards](https://straion.com/blog/1m-tokens-wont-save-your-engineering-standards): Sourcegraph data from 1,281 agent runs confirms the research: more context degrades AI coding performance.
- [Your AGENTS.md is costing more than you think](https://straion.com/blog/delete-your-claude-md-science-says-so): ETH Zurich research: LLM-generated AGENTS.md and CLAUDE.md files cut resolve rates and raise cost.
- [We raised €1.1M to fix AI coding drift](https://straion.com/blog/we-raised-1-1m-to-fix-ai-coding-drift): Straion announces its €1.1M seed round led by Marathon VC and outlines why autonomous engineering needs a rules layer to prevent AI coding drift.
## Company
- [About Straion](https://straion.com/about-us): The team and why Straion exists.
- [Blog](https://straion.com/blog): Research and writing on AI coding governance.
