makecindy
Featured
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.
AgentDoctor
AgentDoctor is a CLI tool that performs health checks on a repository's AI coding agent configuration (instructions, ignore rules, permissions, MCP setup) using local static analysis without requiring API keys or uploading data.
Stars
10
7-day growth
No data
Forks
3
Open issues
5
License
MIT
Last updated
2026-07-29
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It fills a gap as a dedicated audit tool for AI agent environments, analogous to Lighthouse for web pages or ESLint for code, helping teams catch misconfigurations early before they cause security or performance issues.
Who it is for
- DevOps and platform engineers managing AI agent setups
- Developers using AI coding agents like Cursor, Claude Code, or Codex
- Security-conscious teams wanting to prevent sensitive data exposure in agent contexts
- Teams adopting AI coding agents and needing configuration consistency
Use cases
- Audit a repository's agent configuration before deployment or CI
- Detect sensitive environment files that might be ingested by agents
- Identify large instruction files that could degrade agent context performance
- Verify that agent ignore rules and MCP scopes are properly configured
Strengths
- Zero-config first run: works offline with no API key needed
- Detects agent configurations for multiple platforms (Cursor, Claude Code, Codex) with pluggable adapters
- Provides deterministic, categorized findings (security, context, instructions, MCP) with exit codes for CI integration
- Privacy-focused: never uploads source code by default and enables telemetry only on opt-in basis
Considerations
- Currently in beta (v0.1.1-beta) with scoring and safe auto-fixes still planned; not yet production-ready
- Limited to static analysis of configuration files; cannot detect runtime misconfigurations or agent behavior
- Only supports a predefined set of agent adapters (Cursor, Claude Code, Codex); other agents require custom adapters
README quick start
Installation
Description
Local CLI that audits coding-agent configuration for security, instructions, context, and MCP — no API key or code upload by default.
Related repositories
Similar projects matched by category, topics, and programming language.
0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
mereyabdenbekuly-ctrl
Featured
clodex-ide
Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.