AI-powered intelligence platform for analyzing codebases of any size, from small projects to enterprise monorepos.
lyra-intel is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view nirholas/lyra-intel --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Lyra Intel is a tool that helps developers and security teams understand large codebases quickly. It uses AI to find bugs, security issues, and technical debt, and can analyze millions of lines of code. You can run it locally or in your own cloud, keeping your data private.
Lyra Intel is a comprehensive, production-ready intelligence platform designed to understand, secure, and improve codebases of any size. It combines deep code analysis (AST parsing, dependency graphs, complexity metrics) with AI-powered insights (OpenAI, Anthropic, or local models), semantic code search, security scanning (secrets, OWASP, CVE detection), knowledge graphs, and forensic analysis. With over 70 specialized components, it enables end-to-end analysis, security scanning, AI integration, and more. The platform is actively developed and used in enterprise deployments. It supports Docker and Kubernetes for easy deployment.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 31 days ago.
25 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Secure a legacy codebase by scanning for vulnerabilities and creating a remediation plan.
Onboard new developers by building a searchable knowledge base and finding code examples.
Plan a framework upgrade by analyzing impact and generating a step-by-step migration plan.
Understand technical debt by quantifying it, tracking trends, and prioritizing fixes.
Review pull requests with AI-powered insights, security checks, and complexity analysis.
When using external AI models (OpenAI, Anthropic), code snippets may be sent to third-party servers. Use local models for sensitive code.
The tool requires significant computational resources for large codebases; ensure adequate infrastructure.
25
Stars
4
Forks
0
Issues
MIT
License
A terminal dashboard to monitor AI coding agents like Claude Code and Codex CLI in real-time.
A bridge between Streamable HTTP and stdio MCP transports, enabling flexible MCP server connectivity.
A full-stack AI Red Teaming platform for securing AI ecosystems with comprehensive scanning and evaluation.
2 security/trust notes recorded.
Setup difficulty is 3/5.