Skip to content

Agent Integration

WanSatya Campus edited this page Jun 18, 2026 · 1 revision

Rune does not compete with coding agents. It empowers them.


Overview

Rune is designed to work with any coding agent.

Examples:

  • Claude Code
  • Cursor
  • Codex
  • Gemini CLI
  • Aider
  • Roo Code
  • future agents

Rune does not depend on:

  • specific APIs
  • model providers
  • IDEs

The interface is simply:

.rune/

Architecture

           Coding Agent
                  │
                  ▼
             .rune/
                  │
      ┌───────────┴───────────┐
      │                       │
graph.json             file summaries
      │                       │
      └───────────┬───────────┘
                  ▼
             source code

Source code should be loaded last, not first.


Why Agents Need Rune

Modern agents often:

  1. receive a task
  2. search files
  3. read large amounts of code
  4. consume huge numbers of tokens

Humans work differently.

They begin with:

  • architecture
  • conventions
  • dependencies
  • mental models

Rune provides these layers.


Generic Workflow

User asks:

Add Google OAuth.


Without Rune:

User
 ↓
Agent
 ↓
Read 100 files
 ↓
100k tokens

With Rune:

User
 ↓
Agent
 ↓
.rune/
 ↓
graph.json
 ↓
file summaries
 ↓
3 files

Less context.

Faster reasoning.

Lower cost.


Claude Code

Example workflow:

Repository
│
├── src/
├── tests/
└── .rune/

Claude Code reads:

spec.md
graph.json
features/
files/

before loading source code.

Benefits:

  • reduced token usage
  • better architectural understanding
  • fewer unnecessary edits

Cursor

Cursor can leverage:

.rune/spec.md
.rune/conventions.md
.rune/graph.json

to understand:

  • architecture
  • coding style
  • dependencies

before invoking models.


Codex

Codex agents can use:

rune context

to identify relevant files.

Example:

rune context "Implement password reset"

Output:

{
  "related_files": [
    "auth.py",
    "user.py",
    "email.py"
  ]
}

Gemini CLI

Gemini CLI workflows become:

Task
 ↓
.rune/
 ↓
minimal context
 ↓
source code

instead of:

Task
 ↓
entire repository

Aider

Aider currently relies heavily on selected files.

Rune helps identify which files should be selected.

Example:

rune context "Add subscription support"

returns:

billing.py
subscription.py
settings.py

Roo Code

Multi-agent workflows benefit from:

ownership/
sessions/
features/

allowing specialized agents to focus on specific areas.


No Special APIs Required

Rune deliberately avoids:

  • SDKs
  • RPC protocols
  • servers

The contract is:

.rune/

Any agent capable of reading files can consume Rune.


Shared Understanding

Multiple agents can consume the same context:

Claude Code
Cursor
Codex
Gemini CLI
Aider

All reading:

.rune/

This creates:

  • consistent behavior
  • shared architecture
  • fewer conflicting edits

Future Possibilities

Possible integrations:

VSCode Extension

Expose:

rune context

inside the editor.


Cursor Plugin

Automatically prioritize relevant files.


Claude Code Adapter

Inject summaries before source code.


MCP Adapter

Expose:

spec.md
graph.json
features/

through Model Context Protocol.

These integrations belong outside the Rune core.


Recommended Workflow

Initialize:

rune init

Index:

rune index

Update after changes:

rune update

Retrieve context:

rune context "Add Google OAuth"

Then allow the agent to load source code only when needed.


Multi-Agent Future

Long-term architecture:

                 Human
                    │
                    ▼
                 Agent
                    │
          ┌─────────┴─────────┐
          │                   │
        MCP                Rune
          │                   │
      External Tools        .rune/

MCP provides capabilities.

Rune provides understanding.

Agents provide intelligence.


Design Principle

Rune should work with agents that do not exist yet.

Compatibility should come from:

  • files
  • standards
  • simplicity

not APIs.


Philosophy

Agents change.

Models change.

Editors change.

Repository understanding should remain.

Git stores history.

Rune stores understanding.

Rune Context

Git for repository understanding.


Introduction


Reference


Project


Ecosystem


Future RFCs

  • RCP-001 — Repository Format
  • RCP-002 — Plugin Protocol
  • RCP-003 — Graph Format
  • RCP-004 — File Summary Format
  • RCP-005 — Feature Map Format
  • RCP-006 — Ownership Metadata
  • RCP-007 — Session Memory
  • RCP-008 — Context Retrieval API
  • RCP-009 — Incremental Indexing
  • RCP-010 — Multi-Agent Coordination

Philosophy

Git stores history.

Rune stores understanding.

Clone this wiki locally