AgentGuard

Agent-native quality engine for LLM code generation. AgentGuard provides structured guidance to your AI agent — it never calls an LLM itself.

878+ monthly installs · Explore Marketplace · Documentation

🎬 Video Tutorials

New to AgentGuard? Watch the demo series:

🇪🇸 Spanish versions also available — see full playlist

Why AgentGuard

AI agents generate code fast. But without structure, they hallucinate imports, skip error handling, and produce inconsistent architecture.

AgentGuard gives your agent a disciplined framework — without replacing it. It's the quality layer between your AI and your codebase.

What It Does

AgentGuard is an MCP server that gives your AI agent (Claude, GPT, Gemini, etc.) a disciplined process for generating production-ready code:

1. Skeleton → file tree with responsibilities
2. Contracts & Wiring → typed stubs with import connections
3. Logic → function-by-function implementation
4. Challenge → self-review against quality criteria
5. Validate → static analysis (syntax, lint, types, imports)

Your agent does the thinking. AgentGuard provides the framework.

Installation

pip install rlabs-agentguard

That's it. One command, no extras, no API keys needed.

Configure Your IDE

Claude Desktop / Claude Code

Add to your MCP config:

{
  "mcpServers": {
    "agentguard": {
      "command": "agentguard-mcp"
    }
  }
}

Cursor / Windsurf

Add to .cursor/mcp.json or equivalent:

{
  "mcpServers": {
    "agentguard": {
      "command": "agentguard-mcp"
    }
  }
}

Python (direct)

python -m agentguard  # starts MCP server on stdio

Quick Example — What You Get

Ask your agent: "Build a REST API for task management using AgentGuard"

AgentGuard's skeleton tool returns a structured file tree:

src/
├── app.py              # FastAPI application entry point
├── config.py           # Environment and app configuration
├── models/
│   └── task.py         # Task SQLAlchemy model
├── routers/
│   └── tasks.py        # CRUD endpoints for /tasks
├── services/
│   └── task_service.py # Business logic layer
└── tests/
    └── test_tasks.py   # Endpoint + service tests

Then contracts_and_wiring generates typed stubs with all imports wired:

# src/routers/tasks.py
from fastapi import APIRouter, Depends, HTTPException
from ..services.task_service import TaskService
from ..models.task import Task, TaskCreate, TaskUpdate

router = APIRouter(prefix="/tasks", tags=["tasks"])

@router.get("/", response_model=list[Task])
async def list_tasks(service: TaskService = Depends()) -> list[Task]: ...

@router.post("/", response_model=Task, status_code=201)
async def create_task(payload: TaskCreate, service: TaskService = Depends()) -> Task: ...

Your agent fills in the logic. AgentGuard ensures the structure is right from the start.

Tools

Agent-Native (structured guidance — no API key)

Utility

Built-In Archetypes

+ 61 community archetypes on the AgentGuard Marketplace — browse, install, and publish your own.

Marketplace

Install community archetypes:

# From the AgentGuard marketplace (agentguard.rlabs.cl)
# Use the reload_archetypes tool after installing

How It Works

AgentGuard is agent-native: every tool returns structured prompts and criteria that your AI agent processes. The tool never calls an external LLM.

Your Agent (Claude, GPT, etc.)
    │
    ├── calls skeleton(spec, archetype) ─────→ returns L1 file tree prompt
    ├── calls contracts_and_wiring(spec, skeleton) → returns L2+L3 stubs prompt
    ├── calls logic(file, function) ─────────→ returns L4 implementation prompt
    └── calls get_challenge_criteria() ──────→ returns review criteria
    └── calls validate(files) ───────────────→ returns static analysis results

The agent reads the prompt, generates the code, validates it, and loops back if criteria aren't met. AgentGuard provides the structure — your agent provides the intelligence.

Development

pip install -e ".[dev]"
pytest tests/
ruff check agentguard/

Latest Release

See CHANGELOG.md for the full version history.

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines on:

• Setting up your dev environment
• Creating custom archetypes
• Submitting pull requests

Looking for a place to start? Check out issues labeled good first issue.

License

MIT — see LICENSE.