9router vs Lynkr
Self-hosted gateway pointing any AI coding CLI (Claude Code, Codex, Cursor, Cline) at 40+ providers, with subscription→cheap→free auto-fallback and tool_result compression for 20-40% token savings. — versus — Self-hosted LLM gateway wrapping Claude Code, Cursor or Codex with zero code changes — strips unused tools, compresses JSON tool results ~88%, semantic-caches, tier-routes easy work to local models.
Both are self-hosted LLM gateways that wrap coding agents (Claude Code/Codex/Cursor/Cline) with zero code changes and cut tokens by compressing tool_result payloads, then route across backends. 9router optimizes for cost/uptime — 40+ providers, multi-account round-robin, subscription→cheap→free auto-fallback. lynkr optimizes for efficiency — strips unused tools, semantic-caches, and tier-routes easy work to local models. Pick by whether you need free-provider breadth or local-model routing.
| 9router | Lynkr | |
|---|---|---|
| Stars | 22k | 531 |
| Forks | 3.8k | 57 |
| Language | JavaScript | JavaScript |
| License | MIT | Apache-2.0 |
| Last activity | 6 days ago | 5 days ago |
| Topics | gateway, coding | coding, local, gateway |
| Curated connections | 5 | 7 |
9router — the curator's take
The 'never hit a rate limit again' gateway: run it on localhost, point Claude Code / Codex / Cursor / Cline / Copilot at its OpenAI-compatible endpoint, and it round-robins your accounts and cascades Subscription → cheap ($0.2-0.6/1M) → free (Kiro, OpenCode) providers so a job never dies mid-flight, while RTK compresses tool_result payloads (git diff, grep, ls) to shave 20-40% of tokens. Best when you juggle several provider subscriptions/keys and keep exhausting quota. NOT for you if you want one stable premium model (free-tier fallbacks vary in quality/availability), if routing traffic through third-party free providers raises data-privacy concerns, or if you want savings from smarter code retrieval rather than payload compression. Overlaps heavily with lynkr — pick 9router for free/multi-account fallback breadth, lynkr for tool-stripping, semantic caching and local-model routing.
Lynkr — the curator's take
Use it when your Claude Code/Cursor subscription limits or API bill hurt: `lynkr wrap claude` is a one-liner, and compression + routing SIMPLE-tier traffic to a free Ollama model genuinely stretches quotas. Also the escape hatch when corporate policy forces traffic through Databricks/Azure/Bedrock. NOT a model server — it only routes, so pair it with Ollama or another backend. Skip it for light usage: a proxy is one more moving part with a big config surface (tiers, budgets, cache), and semantic caching can serve stale hits on near-duplicate prompts. If you only want provider switching without the token tricks, plain LiteLLM is the boring default.