rigour

@rigour-labs/rigour

Hosted

0 Stars 4 次浏览 rigour-labs 更新于 2026-08-23

Quality gates for AI agents. Lint, test, build checks with memory persistence.

开发者工具

MCP 服务配置

复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用

{
  "mcpServers": {
    "@rigour-labs/mcp": {
      "args": [
        "@rigour-labs/mcp@2.17.1"
      ],
      "command": "npx"
    }
  }
}

可用工具（5 个）

该服务在 MCP 协议中暴露的工具，AI 可按需调用

tavily_search 14 个参数需填 1 项 Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

必填参数：query

tavily_extract 6 个参数需填 1 项 Extract content from URLs. Returns raw page content in markdown or text format.

Extract content from URLs. Returns raw page content in markdown or text format.

必填参数：urls

tavily_crawl 11 个参数需填 1 项 Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

必填参数：url

tavily_map 8 个参数需填 1 项 Map a website's structure. Returns a list of URLs found starting from the base URL.

Map a website's structure. Returns a list of URLs found starting from the base URL.

必填参数：url

tavily_research 2 个参数需填 1 项 Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.

Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.

必填参数：input

服务介绍

馃洝锔� Rigour

Local-first quality gates for AI-generated code.
Rigour forces AI agents to meet strict engineering standards before marking tasks "Done".

Zero cloud. Zero telemetry. PASS/FAIL is always free.

馃殌 Quick Start

npx rigour init     # Initialize quality gates
npx rigour check    # Verify code quality
npx rigour run -- claude "Build feature X"  # Agent loop

馃洃 The "Vibe Coding" Trap

AI agents often fall into a cycle of "Guess and Hope":

Agent makes a change.
Agent claims "Task 100% complete" or "CI will pass now."
Agent pushes to remote.
CI Fails (Type error, lint failure, broken test).

This is "Vibe Coding"鈥攖he agent is hallucinating success based on narrative, not execution.

Rigour breaks this cycle. It forces the agent to face the same cold, hard verification tools (ruff, mypy, vitest) that CI runs, but locally and immediately. Rigour turns a "claim of victory" into a "proof of execution."

馃攧 How It Works

Agent writes code 鈫� Rigour checks 鈫� FAIL? 鈫� Fix Packet 鈫� Agent retries 鈫� PASS 鉁�

The rigour run command loops until your agent achieves PASS or hits max iterations.

馃寳 Rigour Modes

Mode	Control	Use Case	Loop
Advisor	Suggestive	Code reviews & IDE suggestions	Single pass
Supervisor	Enforcement	CI/CD gates & Autonomous agents	Iterative (Auto-fix)

[!TIP]
This workflow uses Supervisor mode for CI/CD, ensuring that any AI-generated code meets all quality gates before merge.

鈿欙笍 What Gets Checked

Gate	Description
File Size	Max lines per file (default: 300-500)
Hygiene	No TODO/FIXME comments allowed
Complexity	Cyclomatic complexity limits (AST-based)
Required Docs	SPEC.md, ARCH.md, README must exist
Safety Rails	Protected paths, max files changed
Context Alignment	Prevents drift by anchoring on project patterns

馃 Works With

Claude Code: rigour run -- claude "..."
Cursor / Cline / Gemini: Via high-fidelity MCP server (rigour_check, rigour_explain)

馃摉 Documentation

[馃摎 Full Documentation 鈫抅(https://docs.rigour.run/)

Quick Links
Getting Started	Install and run in 60 seconds
CLI Reference	All commands and options
Configuration	Customize quality gates
MCP Integration	AI agent setup
Concepts	How Rigour works

馃洜锔� CLI Commands Reference

For a complete reference, visit docs.rigour.run/cli/commands.

Command	Purpose
`rigour check`	Validates staged changes against safety rules
`rigour check --ci`	CI mode with appropriate output
`rigour init`	Setup Rigour in project
`rigour explain`	Detailed explanation of validation results
`rigour run`	Supervisor loop for iterative refinement
`rigour studio`	Dashboard for monitoring

馃И CI Integration

- run: npx rigour check --ci

See full example for GitHub Actions setup.

馃摐 License

MIT 漏 Rigour Labs

"Rigour adds the engineering."

查看源码项目主页