Fast-Editor/Lynkr

Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.

What it solves

Lynkr is an LLM gateway designed to reduce token costs and latency for AI coding tools. It prevents users from being locked into a single provider and stops tools from sending raw, unoptimized tokens, which often leads to high bills and inefficient model usage.

How it works

Lynkr acts as a proxy between AI tools (like Cursor, Claude Code, or Codex) and LLM providers. It optimizes traffic through several mechanisms:

  • Tier Routing: It analyzes request complexity using anchor-embedding classification and a local LLM classifier to route simple tasks to cheap/local models and complex tasks to powerful cloud models.
  • Token Compression: It uses TOON/RTK compression to reduce the size of large JSON tool results (e.g., grep or file reads) by up to 84%.
  • Semantic Caching: It stores responses to similar queries, allowing it to serve repeated or paraphrased requests in under 300ms without billing any tokens.
  • Wrap Mode: It can wrap existing AI coding assistants to apply these optimizations without requiring code changes to the tools themselves.
  • Learning Loop: It uses a kNN router and bandit system to calibrate routing thresholds based on actual traffic outcomes.

Who it’s for

Developers using AI coding assistants (Cursor, Claude Code, Codex, Cline, Continue) who want to lower their API costs, maximize subscription limits, and integrate local models (via Ollama, llama.cpp, etc.) alongside cloud providers.

Highlights

  • Significant Token Reduction: Up to 84% fewer tokens on JSON tool results and 53% fewer tokens on tool-heavy requests.
  • Broad Provider Support: Compatible with 13+ providers, including local options like Ollama and cloud services like AWS Bedrock, Azure, and OpenAI.
  • Zero Code Changes: Integration is achieved by overriding the base URL in the tool settings.
  • Real-time Dashboard: Built-in telemetry to track spend, savings, and routing accuracy.
  • Advanced Code Intelligence: Optional integration with Graphify for AST-based structural code analysis to improve routing decisions.