LynkrSelf-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.
Why switchBoth 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.
Full comparison → freellmapiOpenAI-compatible proxy that stacks free tiers of 18 LLM providers (~1.7B tokens/mo) behind one /v1 — smart routing, failover, per-key quota tracking; Claude Code and Codex shims included.
Why switchBoth are self-hosted OpenAI-compatible gateways that multiplex providers with automatic fallback for coding CLIs. 9router optimizes paid usage (subscription→cheap→free routing, token compression); FreeLLMAPI exists purely to stack and stay under 18 providers' free-tier caps.
Full comparison → free-claude-codeProvider-backed proxy that runs Claude Code, Codex or Pi on 25 cloud and local providers — fcc-* launchers, local Admin UI with validation, per-tier model routing, IDE/Discord/Telegram hookups.
Why switchBoth are self-hosted gateways pointing Claude Code/Codex-class CLIs at many providers. 9router leans on routing policy (subscription→cheap→free fallback, token compression); FCC leans on UX — launchers, validation UI, native model-picker integration, IDE configs.
Full comparison → CLIProxyAPITurns your coding-CLI subscriptions (Claude Code, Codex, Antigravity, Kimi, Grok) into a local OpenAI/Gemini/Claude-compatible API — multi-account rotation in one Go proxy.
Why switchTwo directions of the same arbitrage: 9router points coding CLIs at 40+ providers; CLIProxyAPI exposes your CLI subscriptions as an OpenAI/Claude/Gemini-compatible endpoint for any client.
Full comparison → headroomContext compression layer for agents: squeezes tool outputs, logs, files and RAG chunks 20-95% before the LLM — reversible, local-first; library, proxy, one-command agent wrap, or MCP.
Why switchSame wire, same goal — cut coding-agent token spend at a local proxy. 9router is a multi-provider routing gateway with tool_result compression as a feature; Headroom is compression-first with content-aware routers, reversibility and no routing opinions.
Full comparison → codexmateLocal-first CLI + web dashboard for your coding agents — switch providers, browse sessions across Codex/Claude Code/Gemini CLI, share skills, queue tasks, and bridge Codex/Claude to any API.
Why switchOverlapping job of pointing coding CLIs at arbitrary providers: 9router is a dedicated self-hosted gateway with auto-fallback across 40+ providers; Codex Mate does it via built-in Codex/Claude protocol bridges as one feature of its control plane.
Full comparison → litellmOpen-source AI gateway: call 100+ LLM providers in OpenAI format via a Python SDK or self-hosted proxy — with cost tracking, virtual keys, guardrails, load balancing and logging.
Why switchBoth are self-hosted gateways routing to many providers with fallback; 9router aims at coding CLIs, LiteLLM at app/SDK developers.
Full comparison → quotioNative macOS menu-bar front-end for CLIProxyAPI: pool your Claude, Codex, Qwen and Copilot accounts behind one local proxy with live quota bars, auto-failover and one-click CLI wiring.
Why switchBoth point any coding CLI at pooled backends with subscription-first fallback. 9router is cross-platform, reaches 40+ API providers and compresses tool_result payloads; the Quotio stack only fronts subscriptions you already own, but tracks their remaining quota natively and shows it in the menu bar.
Full comparison →