LunaRoute is a high-performance local proxy for AI coding assistants like Claude Code, OpenAI Codex CLI, and OpenCode that provides complete visibility into every LLM interaction with zero-overhead passthrough, comprehensive session recording, and powerful debugging capabilities.
https://github.com/erans/lunaroute?ref=producthunt
LunaRoute

Product Information

Updated:Nov 3, 2025

What is LunaRoute

LunaRoute is an open-source local proxy designed specifically for AI coding assistants, acting as a transparent bridge between development tools and AI services. It enables developers to monitor, debug, and analyze their AI interactions without compromising performance or security. The tool requires minimal configuration - users can start it in seconds without even needing to provide API keys, as it works seamlessly with existing authentication methods from AI coding assistants.

Key Features of LunaRoute

LunaRoute is a high-performance local proxy for AI coding assistants that provides comprehensive visibility and control over LLM interactions. It offers zero-overhead passthrough mode, detailed session recording, PII protection, and powerful debugging capabilities while supporting multiple AI assistants like Claude Code, OpenAI Codex CLI, and OpenCode. The tool enables tracking of token usage, performance metrics, and conversation history with built-in privacy features and compliance controls.
Zero-Overhead Passthrough Mode: Adds only 0.1-0.2ms latency with 100% API fidelity, allowing transparent proxying of requests without impacting performance
Comprehensive Session Recording: Records all conversations, tokens, and tool calls in both JSONL and SQLite formats with customizable retention policies and PII protection
Advanced PII Detection & Redaction: Automatically detects and redacts sensitive information like emails, SSNs, and credit cards with multiple redaction modes before storage
Real-time Monitoring & Analytics: Provides Prometheus metrics, session statistics, and a web UI for analyzing AI interactions and performance metrics

Use Cases of LunaRoute

Development Debugging: Help developers track and debug expensive AI conversations by providing visibility into token usage and performance bottlenecks
Team Collaboration: Enable multiple team members to share one proxy while using different API keys, with centralized logging and monitoring
Compliance & Security: Support regulated industries by providing automatic PII redaction and comprehensive audit trails of AI interactions
Performance Optimization: Identify and optimize slow tool calls or inefficient AI interactions through detailed performance metrics and analysis

Pros

Minimal performance impact with sub-millisecond overhead
Comprehensive visibility and debugging capabilities
Strong privacy and compliance features
Easy setup with zero configuration required

Cons

Limited to local development environment currently
Web UI features still in development
73% test coverage could be improved

How to Use LunaRoute

Install LunaRoute: Download the latest release from GitHub Releases page and extract: 'tar -xzf lunaroute-server-*.tar.gz' then make it executable: 'chmod +x lunaroute-server'
Add to PATH (Optional): Move the binary to system path: 'sudo mv lunaroute-server /usr/local/bin/'
Start LunaRoute Server: Simply run 'lunaroute-server' to start with default configuration. The server will start on port 8081
Configure AI Tool: For Claude Code, set: 'export ANTHROPIC_BASE_URL=http://localhost:8081'. For OpenAI Codex CLI, set: 'export OPENAI_BASE_URL=http://localhost:8081/v1'
Access Session Recording: Sessions are automatically recorded to ~/.lunaroute/sessions/ directory in JSONL format and ~/.lunaroute/sessions.db for SQLite analytics
View Web Interface: Access the built-in web UI at http://localhost:8082 to browse and analyze recorded sessions
Monitor Real-time: Watch sessions in real-time using: 'tail -f ~/.lunaroute/sessions/$(date +%Y-%m-%d)/session_*.jsonl | jq'
Configure PII Protection (Optional): Add PII redaction settings to config file to automatically detect and redact sensitive information like emails, SSNs, and credit card numbers
View Metrics (Optional): Access Prometheus metrics at http://localhost:8081/metrics for monitoring request rates, latency, token usage and more
Start Using AI Tools: Begin using your AI coding assistant normally - all interactions will now be routed through LunaRoute with full visibility and recording

LunaRoute FAQs

LunaRoute is a high-performance local proxy for AI coding assistants like Claude Code, OpenAI Codex CLI, and OpenCode. It provides complete visibility into every LLM interaction with zero-overhead passthrough, session recording, and debugging capabilities.

Latest AI Tools Similar to LunaRoute

Gait
Gait
Gait is a collaboration tool that integrates AI-assisted code generation with version control, enabling teams to track, understand, and share AI-generated code context efficiently.
invoices.dev
invoices.dev
invoices.dev is an automated invoicing platform that generates invoices directly from developers' Git commits, with integration capabilities for GitHub, Slack, Linear, and Google services.
EasyRFP
EasyRFP
EasyRFP is an AI-powered edge computing toolkit that streamlines RFP (Request for Proposal) responses and enables real-time field phenotyping through deep learning technology.
Cart.ai
Cart.ai
Cart.ai is an AI-powered service platform that provides comprehensive business automation solutions including coding, customer relations management, video editing, e-commerce setup, and custom AI development with 24/7 support.