rness

Agent governance for GitHub organizations

One organization. Many repositories. Many agents. One source of truth.

Rness is the governance layer for AI-native engineering teams — connecting organizational context, rules, decisions and engineering knowledge to the agents your teams already use.

npm create rness

No new agent. No new workflow. No new configuration format.

Your GitHub organization
github.com/acme
rnessagent governance
app1
Claude Code
app2
Codex
app3
Cursor
existing workflow — unchanged

Your AI agents shouldn't each have their own understanding of your organization.

Rness gives your organization one source of truth for agent context, rules, decisions and engineering knowledge.

Principle

Centralized governance. Decentralized development.

Adoption

Keep using the agents you already use. Rness makes them understand your organization.

01 — The problem

AI development is becoming distributed. Organizational knowledge shouldn't be.

github.com/acme
acme/
├── app1
│ ├── CLAUDE.md
│ ├── AGENTS.md
│ └── .cursor/rules
├── app2
│ ├── CLAUDE.md
│ └── AGENTS.md
└── app3
└── .github/copilot-instructions.md
3 repositories · 4 formats · 0 shared source of truth
Fragmented context

Different agents and repositories contain different pieces of organizational knowledge.

Cross-project drift

Rules and standards get copied between repositories and become inconsistent.

Lost decisions

Architecture decisions, plans and specifications become disconnected from the agents implementing them.

No organizational visibility

Engineering leaders cannot easily see what governance applies to which repository, or how AI-assisted development is evolving across the organization.

02 — Introducing Rness

A governance layer above your agents.

Rness does not replace your agents or redefine their configuration systems. It provides the organizational layer that connects them.

AI models
Claude · GPT · Gemini · …
Provide intelligence
AI agents
Claude Code · Codex · Cursor · Copilot · …
Execute development tasks
Agent governance
rness
Governs the organizational context and policies agents operate in
Engineering system
GitHub · CI/CD · Cloud · Infrastructure · …
System of record for code and development
Context
StandardsArchitectureProduct
Rules
SecurityTestingGit
Decisions
ADRsPlansSpecs

Agents execute. Rness governs.

03 — Cross-repository governance

One organization. Every repository.

Define shared context and governance once. Apply it across every repository in the organization.

The repositories remain independent. Rness provides the organizational context around them.

github.com/acme/
.rnessorganization source of truth
app1
app2
sdk
contracts
infrastructure
$ rness org/app1
$ rness org/app2
Same organizational context. Different repository.
04 — Cross-agent governance

Define once. Govern every agent.

Claude Code remains Claude Code. Codex remains Codex. Cursor remains Cursor. Rness provides the shared organizational layer around them.

No new agent. No new workflow. No new configuration format.

rness
organizational truth
Claude Code
existing workflow
Codex
existing workflow
Cursor
existing workflow
05 — Organization-wide context

Give every agent the context it needs — without duplicating it everywhere.

Organization-level context is inherited by every repository. Each repository adds only what is specific to it.

context
Organization
├── Product contextinherited
├── Engineering principlesinherited
├── Security policiesinherited
├── Architecture principlesinherited
├── app1
│ └── repository-specific contextlocal
├── app2
│ └── repository-specific contextlocal
└── app3
└── repository-specific contextlocal
06 — Policy enforcement

Turn engineering standards into organizational policy.

Policies carry a scope — organization, repository, directory or file pattern — so the right rule applies at the right level.

Native agent configuration files stay where they are. Rness does not ask developers to replace them.

policies
Organization
├── Security
│ ├── secrets policy
│ ├── dependency policy
│ └── smart contract policy
├── Engineering
│ ├── testing
│ ├── TypeScript
│ └── Git
└── Architecture
├── API standards
└── data standards
Scope
Organization
Repository
Directory
File / pattern
07 — Architecture memory

Your agents should understand not only what to do — but why.

Architecture decisions become organizational memory instead of isolated documents — and reach the agents implementing them.

decisions
ADR-001PostgreSQL is the primary database
AcceptedOrganization
ADR-014GraphQL is the public API
Acceptedapp1
ADR-021Use viem for EVM interaction
Acceptedcontracts
08 — Plans and specifications

Connect what you're building to why you're building it.

Specs, plans and decisions are linked — so an agent implementing a plan knows the spec behind it and the decisions that constrain it.

Rness connects the knowledge agents need before and during implementation.

Product
Spec
Plan
Implementation
Agent
SPEC-012Unified lending API
PLAN-027Implement Morpho adapter
ADR-031Standardize market identifiers
09 — Product in action

See Rness in action

A developer opens a repository and starts their agent — exactly as they do today.

app1 — zsh
$ cd app1
$ claude
rness
Organizationacme
Repositoryapp1
AgentClaude Code
Applicable governance
Security standards
Engineering standards
Architecture principles
ADR-014
PLAN-027
> Implement the new lending endpoint
Context resolved
Organization rules12
Repository rules7
Relevant ADRs3
Active plans2
Security policies4
Claude Code continues in the same session.

Claude remains Claude. The developer remains in the same workflow. Rness provides the organizational governance around it.

10 — Before / after
Before
app1
├── CLAUDE.md
├── AGENTS.md
└── .cursor/rules
app2
├── CLAUDE.md
└── AGENTS.md
app3
└── .github/copilot-instructions.md

Context is fragmented across repositories and agents.

With Rness
.rness
app1
app2
app3
Claude · Codex · Cursor · Copilot

Governance is centralized. Workflows remain decentralized.

Centralized governance. Decentralized development.

11 — A new layer in the stack

A new layer in the AI development stack.

Coding agents are not what Rness competes with — they are what it governs. The relevant comparison is between the layers that address organization-wide AI governance.

Layer / capability
Coding agents
Claude Code · Codex · Cursor · Copilot
Project rules
CLAUDE.md · AGENTS.md · .cursor/rules
Agent governance
Rness
Execute coding tasks
Repository instructions
Cross-repository governanceLimitedLimitedCore
Cross-agent governanceLimitedLimitedCore
Organization-wide contextLimitedLimitedCore
Policy enforcementLimitedPartialCore
ADR / architecture memoryPartialPartialCore
Decision traceabilityLimitedCore
Context inheritancePartialPartialCore
Configuration driftLimitedPartialCore
Agent auditabilityLimitedCore

Categories, not vendors. Coding agents execute tasks. Project rules instruct a single repository. Agent governance spans the organization — every repository, every agent.

12 — Context inheritance

The right context, at the right scope.

Organizational knowledge can be inherited and specialized as work moves closer to the code.

OrganizationRepositoryDirectoryFile
Organization
RulesSecurityArchitecture
inherits · specializes
Repository
app/api/contracts/
inherits · specializes
Directory
contracts/src/
inherits · specializes
File
*.sol
13 — Configuration drift

Know when your repositories drift from organizational policy.

Rness compares each repository against the organization's governance and surfaces what has drifted — before it reaches an agent.

rness/acme
Organization
24
Repositories
4
Agents
18
Policies
Governance status
app1✓ compliant
app2✓ compliant
app3drift detected
app4✓ compliant
Drift
app3/security policy
app7/outdated architecture rule
app12/missing testing standard
14 — Decision traceability

Know why an agent made a change.

Every change can be traced back through the rule, decision, specification and plan that shaped it. Organizational traceability — not surveillance of individual developers.

Change
Applicable rule
Architecture decision
Specification
Plan
Agent execution
PR #184·acme/app1
Claude Code
Changed
packages/lending/src/market.ts
Relevant governance
ADR-031SPEC-012SEC-004
Agent
Claude Code
Decision
Standardized market identifier
15 — Product architecture

.rness — the organization-level source of truth.

.rness is not another agent configuration format. It is the organizational knowledge and governance layer that connects to the agent-specific configuration systems you already have.

github.com/acme/
.rness/
app1/
app2/
app3/
sdk/
contracts/
.rness/
context/Organizational context
rules/Engineering rules and standards
security/Security policies
architecture/Architecture principles
decisions/ADRs
specs/Specifications
plans/Plans
16 — Developer workflow

Nothing changes for developers.

01
Connect

Connect your GitHub organization.

02
Govern

Define organizational context, standards, policies, decisions, specs and plans.

03
Keep coding

Developers continue using Claude Code, Codex, Cursor, GitHub Copilot or other agents exactly as before.

Rness works around your workflow, not against it.

17 — CLI

Governance you can run from the terminal.

Inspect, resolve and sync organizational governance without leaving the shell.

rness createCreate or join an organization
rness addAdd a repository to the workspace
rness syncSync organizational governance
rness contextResolved context
rness validateCheck the context and its blocks
rness upgradeMove to a new CLI version
rness loginReach private repositories
acme — zsh
$ rness status
Organizationacme
Repositories24
Agents4
Governance
Context
Standards
Security
ADRs
Specs
Plans
Drift detected
app3 / security policy
18 — Trust & architecture

Your repositories remain the source of code. Rness becomes the source of organizational agent knowledge.

GitHub
code
history
pull requests
rness
agent context
governance
organizational knowledge
decisions
policies

Rness does not replace GitHub. It sits beside it — and points your agents at what your organization has decided.

Give every AI agent the same understanding of your organization.

One source of truth. Every repository. Every agent.

npm create rness

Agents execute. Your organization governs.