# Lynkr

> Self-hosted, open-source LLM gateway for AI coding assistants that compresses tool tokens, caches prompts semantically, and routes by complexity across 14+ providers.

- **Category:** AI
- **Licence:** Apache-2.0
- **Latest version:** v9.6.0
- **Open source:** oss
- **Languages:** JavaScript, Rust
- **Platforms:** Docker, Docker Compose, Linux, NPM, Homebrew, Build from Source
- **Tags:** Mcp, Databricks, Agents, LLMOps, LLM, Claude, Ollama, Developer Tools, Ai Gateway, AI, Self Hosted, Codex, Cursor, Code generation, Claude code, Code assistant, Llama.cpp, Token optimization, Llm gateway, Llm proxy, Llm router, Claudecode, Semantic cache, Prompt Caching, Tier Routing

## Description

Lynkr is a Node.js gateway that fronts AI coding assistants — Claude Code, Cursor, the Codex CLI, Cline and Continue.dev — and answers both the Anthropic-style and the OpenAI-compatible endpoint formats, so clients need no code changes. On the way to the model it binary-compresses large JSON tool results (87.6% fewer tokens on a 60-item grep array in its own benchmark), drops tool schemas a request will not use, and answers near-duplicate prompts from a semantic cache in roughly 171ms with nothing billed. Each request can be scored for difficulty and sent to one of four tiers configured as provider:model pairs, keeping easy turns on a free local Ollama model while hard ones escalate to cloud capacity; sessions stay pinned to one model until a guard forces a re-route. A dashboard served under /dashboard reports spend, counterfactual savings, tier mix, routing accuracy, logs and provider health, alongside Prometheus metrics, health endpoints and a no-restart admin reload. Installation is a global npm package (also a Homebrew tap, a curl installer, Docker Compose or a source build), configuration is an interactive `lynkr init` wizard or a `.env` file, and the gateway listens on port 8081 with local SQLite files for its data. It is Apache 2.0 licensed, free, and the project itself notes that several provider entries are documented but not yet probed against live keys.

## Links

- [Homepage](https://github.com/fast-editor/lynkr)
- [Website](http://lynkrhq.com/)
- [Lynkr documentation](http://lynkrhq.com/docs.html)
- [GitHub Discussions](https://github.com/Fast-Editor/Lynkr/discussions)
- [DeepWiki](https://deepwiki.com/Fast-Editor/Lynkr)

---
Source: https://selfhost.directory/project/lynkr