Show HN: GoRoute – Native Go LLM Gateway for Coding Agents (< 12MB RAM) Developer ziuus released GoRoute, a single-binary LLM gateway written in Go that runs in a 5.1MB binary using under 12MB of RAM and serves coding agents such as OpenCode, Claude Code, Cursor, Codex CLI, Aider and Cline at http://127.0.0.1:8128. GoRoute handles OpenAI and Anthropic protocol normalization, Google Antigravity OAuth account rotation, session account affinity for prompt-cache preservation and 55 RTK filters that cut 70-90% of noise, positioning it against Node/Electron proxies the project says consume 600MB to 1.5GB of RAM. The gateway is installable via npm, npx, curl, Homebrew or go install, and a single `goroute setup all` command configures all 18 supported agents. Sub-10ms Latency • < 12MB RAM • 35 CLI Agents • A2A Protocol • Zero Node.js Overhead Quickstart -quickstart • Architecture -architecture • Supported Agents -supported-coding-agents • Benchmarks -benchmarks • Features -features • Cheatsheet -cli-cheatsheet GoRoute is an ultra-fast, single-binary LLM gateway engineered specifically for developers using autonomous AI coding agents OpenCode, Claude Code, Cursor, Codex CLI, Aider, Cline , etc. . Instead of running bloated Node/Electron proxies that consume 600MB to 1.5GB of RAM , GoRoute delivers identical multi-provider pooling, Google Antigravity OAuth rotation, Anthropic-to-OpenAI protocol normalization, and response caching inside a tiny 5.1MB footprint . ┌─────────────────────────────────────────────────────────────┐ │ YOUR CODING AGENTS │ │ OpenCode • Claude Code • Cursor • Codex CLI • Aider • Roo │ └──────────────────────────────┬──────────────────────────────┘ │ http://127.0.0.1:8128 OpenAI /v1 & Anthropic /v1/messages │ ▼ ┌───────────────────────────────────────────────────────────────────────────────────────────┐ │ ⚡ GOROUTE CORE │ │ │ │ ┌───────────────────────┐ ┌───────────────────────┐ ┌───────────────────────────────┐ │ │ │ Dual-Protocol SSE │ │ 55 RTK Filters │ │ Session Account Affinity │ │ │ │ OpenAI ⇆ Anthropic │ │ 70-90% Noise Cut │ │ Prompt Cache Preservation │ │ │ └───────────────────────┘ └───────────────────────┘ └───────────────────────────────┘ │ │ │ │ ┌─────────────────────────────────────────────────────────────────────────────────────┐ │ │ │ Autonomous Token Health Scheduler & Router │ │ │ │ Cascades across accounts on 429 quota or 503 limits; proactive refresh │ │ │ └─────────────────────────────────────────────────────────────────────────────────────┘ │ └──────────────────────────────────────────────┬────────────────────────────────────────────┘ │ ┌───────────────────────────────┼───────────────────────────────┐ ▼ ▼ ▼ ┌───────────────────────────┐ ┌───────────────────────────┐ ┌───────────────────────────┐ │ Google Antigravity Pool │ │ AWS CodeWhisperer Kiro │ │ OpenAI / Codex Direct │ │ Multi-Account • Sonnet │ │ Context Auto-Pruning │ │ OpenAI Compatible API │ └───────────────────────────┘ └───────────────────────────┘ └───────────────────────────┘ npm install -g goroute Or run directly via npx: npx goroute setup opencode curl -fsSL https://raw.githubusercontent.com/ziuus/goroute/main/install.sh | bash brew install ziuus/goroute/goroute go install github.com/ziuus/goroute/cmd/goroute@latest goroute auth login antigravity Securely links your Antigravity accounts into GoRoute's encrypted local storage ~/.goroute/vault.json . Auto-configure your favorite agent with one command: Configure OpenCode writes config + registers provider credentials goroute setup opencode Configure Claude Code goroute setup claude Configure OpenAI Codex CLI goroute setup codex Configure ALL 18 supported agents in one click goroute setup all Run GoRoute as a background service: Enable Linux background autostart systemd user unit, ~5MB RAM : goroute autostart enable Verify gateway status: goroute status Or launch any agent with zero configuration using the universal proxy injector: goroute run opencode goroute run claude goroute run aider --model openai/claude-3-7-sonnet Tested on Linux x86 64 under 500 concurrent streaming requests: | Benchmark Metric | Traditional Gateways Node/Next.js/Python | GoRoute Pure Go | Efficiency Gain | |---|---|---|---| | Idle Memory RSS | 580 MB – 1,450 MB | 5.1 MB | 99.1% less RAM | | Memory Under 500 Req Load | 850 MB – 2.1 GB | 16.5 MB | 98.0% less RAM | | Idle CPU Utilization | 1.5% – 6.0% background | 0.0% Sleep until epoll | Zero background waste | | Disk Footprint | ~180 MB node modules | 13 MB Static single binary | 14x smaller | | Cold Startup Time | 3,200 ms | 11 ms | 290x faster | | Gateway Port | 20128 | 8128 | Collision-free | goroute setup automatically configures paths, headers, authentication keys, and provider manifests for: | Agent | Command | Target Config File | Features Supported | |---|---|---|---| | Claude Code | goroute setup claude | ~/.claude/settings.json | Anthropic /v1/messages protocol + thinking | | OpenCode | goroute setup opencode | ~/.config/opencode/opencode.json | Full models catalog, auth.json registration | | Cursor IDE | goroute setup cursor | ~/.config/Cursor/User/settings.json | Custom OpenAI Base URL + /v1/embeddings | | OpenAI Codex CLI | goroute setup codex | ~/.codex/goroute.config.toml | Custom profile, auto-compaction | | Cline | goroute setup cline | ~/.cline/data/secrets.json | Act & Plan modes | | Roo Code | goroute setup roo | ~/.roo/settings-import.json | Custom OpenAI compatible profile | | OpenClaw | goroute setup openclaw | ~/.openclaw/config.yaml | Multi-agent execution harness | | Hermes Agent | goroute setup hermes | ~/.hermes/config.json | In-flight reasoning inspection | | Droid | goroute setup droid | ~/.droid/settings.json | Autonomous workspace workflows | | Grok-Build | goroute setup grok-build | ~/.grok/build.json | Native reasoning compiler | | Aider | goroute setup aider | ~/.aider.conf.yml | OpenAI base URL + git workflow routing | | Kilo Code | goroute setup kilo | ~/.local/share/kilo/auth.json | Custom gateway key | | Zed Editor | goroute setup zed | ~/.config/zed/settings.json | Assistant panel routing | | Letta / MemGPT | goroute setup letta | ~/.letta/config.json | Stateful agent memory gateway | | Warp Terminal | goroute setup warp | ~/.warp/settings.json | AI terminal command generator | | DeepSeek TUI | goroute setup deepseek-tui | ~/.deepseek/config.toml | Interactive terminal reasoning | | Charm Crush | goroute setup crush | ~/.config/crush/crush.json | Custom host setup | | Continue cn CLI | goroute setup continue | ~/.continue/config.yaml | Chat completions + vector embeddings | | + 17 more tools | goroute setup all | All local tools | 35 CLI agents configured in parallel with auto-backups | - Universal Multi-Protocol Gateway : - POST /v1/chat/completions OpenAI format + SSE chunks - POST /v1/messages Native Anthropic format + content block delta SSE streaming - POST /api/chat Native Ollama emulation - GET /mcp Model Context Protocol native SSE server - GET /.well-known/agent.json & POST /api/a2a/tasks A2A Protocol v0.3 - - Zero-Alloc In-Memory Cache : - Repeated agent queries e.g. title generation, linters, duplicate prompts hit the internal cache and return X-Cache: HIT with 0ms latency and 0 upstream tokens . - Repeated agent queries e.g. title generation, linters, duplicate prompts hit the internal cache and return - DuckDuckGo Web Search & Readability Scraper : - Built-in POST /v1/web/fetch and GET/POST /v1/search with zero API keys required. Converts fetched HTML to clean GitHub-flavored Markdown. - Built-in - Smart Quota Cascade & Multi-Account Pools : - Dynamically rotates across accounts with configurable strategies: Priority / Failover , Round-Robin , and Fair-Share . - Automatically isolates accounts on HTTP 429 quota exhaustion or 402 billing limits with proactive token cooldowns. - Dynamically rotates across accounts with configurable strategies: - Context Pruning & Token Optimization : - Single-pass $O N $ integer pruning algorithm trims duplicate prompt prefixes and keeps multi-turn transcripts within upstream limits without dropping active agent instructions. - Single-pass We welcome contributors Check out our open Good First Issues https://github.com/ziuus/goroute/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22 : - Adding a new provider adapter takes under 20 lines of pure Go in pkg/providers/ . - Adding a new CLI tool integration is just 1 struct entry in pkg/clitools/registry.go . - Read CONTRIBUTING.md https://github.com/ziuus/goroute/blob/main/CONTRIBUTING.md to get started in 2 minutes. GoRoute provides pre-compiled, optimized static binaries for all major platforms: | Platform | Architecture | Binary Format | Autostart Service | |---|---|---|---| | Linux | x86 64 , arm64 | Native ELF | systemd user service | | macOS | Apple Silicon arm64 , Intel x86 64 | Mach-O | launchd / CLI | | Windows | x64 , arm64 | Native .exe | Windows Task / CLI | | NPM Wrapper | Any Node.js 18+ environment | Universal JS runner | Auto-detects platform | Gateway Management goroute serve Start gateway server port 8128 goroute serve --no-dashboard Headless mode < 10MB RAM goroute autostart enable Enable system background service goroute autostart status Check service status goroute autostart disable Stop & disable service goroute status Health check & model listing Agent Setups goroute setup all Configure all 14 coding agents goroute setup