[{"data":1,"prerenderedAt":173},["ShallowReactive",2],{"repo-weave-os-router-en":3,"i18n-weave-os-router-en":170},{"mirrorPool":4,"detail":13,"relatedProjects":60},[5,9],{"key":6,"label":7,"base":8,"type":6},"github","mirror.github","https:\u002F\u002Fgithub.com\u002F",{"key":10,"label":11,"base":12,"type":10},"auto-proxy","mirror.autoProxy","https:\u002F\u002Fgithub.xxlab.tech\u002F",{"owner":14,"repo":15,"repoId":16,"repoUrl":17,"starCount":18,"language":19,"description":20,"languages":21,"screenshots":29,"homepage":30,"pushedAt":31,"ownerAvatar":32,"ownerName":33,"ownerBio":34,"lastSyncTime":35,"lastReleaseTime":36,"tags":37,"license":45,"category":46,"subgroup":47,"releases":48},"weave-os","router",1222789989,"https:\u002F\u002Fgithub.com\u002Fweave-os\u002Frouter",5563,"Go","Model router for agentic systems. Routes every prompt to the right model in \u003C50ms. Cut costs 40-70% with just an endpoint change.",{"Go":22,"Shell":23,"TypeScript":24,"Python":25,"PLpgSQL":26,"Dockerfile":27,"Makefile":27,"JavaScript":27,"CSS":28,"HCL":28},84.5,5.7,4.5,3.4,1.5,0.1,0,[],"https:\u002F\u002Fweaveos.com\u002Fproducts\u002Frouter","2026-10-04","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F174961884?v=4","Weave","ML to quantify engineering","2026-10-04T13:14:33.928663+00:00","2026-07-13T00:44:31Z",[38,39,40,41,42,43,44],"agentic-coding","ai-gateway","anthropic","claude-code","codex","model-router","openai-compatible","Apache-2.0","ai","LLM推理\u002F微调工具",[49],{"tag":50,"publishAt":36,"semVer":51,"prerelease":52,"assets":53},"hmm-model-v1",[28,28,28],true,[54],{"fileName":55,"sizeMb":56,"sha256":57,"downloadCount":58,"originUrl":59},"hmm-router-frozen-v1.tar.gz",5.65,"b326bda644aac86831bae47d0b69de008046f62324a4b93a1eba702581c174df",3847,"https:\u002F\u002Fgithub.com\u002Fweave-os\u002Frouter\u002Freleases\u002Fdownload\u002Fhmm-model-v1\u002Fhmm-router-frozen-v1.tar.gz",[61,79,108,128,140,157],{"owner":62,"repo":63,"repoId":64,"category":46,"subgroup":47,"language":65,"tags":66,"starCount":68,"ownerUid":69,"latestTag":70,"platforms":71,"lastReleaseTime":76,"downloadCount":77,"description":78},"ggml-org","llama.cpp",612354784,"C++",[67],"ggml",131695,134263123,"b11734",[72,73,74,75],"windows","mac","linux","other","2026-10-19T14:08:40Z",481,"A C\u002FC++ implementation for LLM and VLM inference with minimal setup and state-of-the-art performance, supporting multiple model formats with CLI, server, and built-in Web UI.",{"owner":80,"repo":81,"repoId":82,"category":46,"subgroup":47,"language":83,"tags":84,"starCount":101,"ownerUid":102,"latestTag":103,"platforms":104,"lastReleaseTime":105,"downloadCount":106,"description":107},"diegosouzapw","OmniRoute",1157102282,"TypeScript",[85,86,39,40,87,41,88,42,89,90,91,92,93,94,95,96,97,98,99,100],"a2a","ai-agents","claude","cline","copilot","cursor","deepseek","free-ai","gemini","kimi","llm-gateway","mcp","openai","openai-proxy","qwen","token-saver",72815,8016841,"v3.8.51",[72,73,74,75],"2026-09-30T01:41:50Z",4681,"A free MIT AI gateway providing a unified endpoint to 290+ providers and 500+ models with quota-aware auto-fallback and token compression.",{"owner":109,"repo":110,"repoId":111,"category":112,"subgroup":47,"language":113,"tags":114,"starCount":121,"ownerUid":122,"latestTag":123,"platforms":124,"lastReleaseTime":125,"downloadCount":126,"description":127},"AlexsJones","llmfit",1158588224,"tools","Rust",[115,116,117,118,119,120],"gguf","llm","localai","mlx","skill","unsloth",37743,1235925,"v1.1.17",[72,73,74],"2026-10-08T18:04:05Z",1447,"A command-line tool that recommends the best local LLMs for your hardware configuration, supporting multi-GPU, MoE architectures, and multiple quantization formats.",{"owner":129,"repo":130,"repoId":131,"category":46,"subgroup":47,"language":83,"tags":132,"starCount":133,"ownerUid":134,"latestTag":135,"platforms":136,"lastReleaseTime":137,"downloadCount":138,"description":139},"tashfeenahmed","freellmapi",1217040185,[],37411,9307356,"v0.16.5",[72,73,74,75],"2026-10-19T11:30:09Z",1332,"A unified API gateway aggregating 34 free LLM providers and 635 free model endpoints, offering approximately 7.4 billion free tokens per month with smart routing, automatic failover, and encrypted key storage.",{"owner":141,"repo":142,"repoId":143,"category":46,"subgroup":47,"language":144,"tags":145,"starCount":150,"ownerUid":151,"latestTag":152,"platforms":153,"lastReleaseTime":154,"downloadCount":155,"description":156},"jundot","omlx",1157171418,"Python",[146,147,116,148,118,149],"apple-silicon","inference-server","macos","openai-api",22858,64250138,"v0.7.1rc1",[73,75],"2026-10-15T18:23:10Z",2195,"An LLM inference server optimized for Apple Silicon with continuous batching and SSD caching, managed directly from the macOS menu bar.",{"owner":158,"repo":159,"repoId":160,"category":46,"subgroup":47,"language":19,"tags":161,"starCount":163,"ownerUid":164,"latestTag":165,"platforms":166,"lastReleaseTime":167,"downloadCount":168,"description":169},"yetone","magpie",1383809012,[41,42,91,162,116,148],"gemini-cli",16805,1206493,"v0.1.1293",[72,73],"2026-10-19T12:31:24Z",309,"Magpie is a locally running AI gateway that lets coding agents such as Claude Code, Codex, Gemini CLI and OpenCode use models like Kimi, DeepSeek, GLM and ChatGPT, with one-click menu bar switching and automatic failover to the next account when quota runs out.",{"description":171,"readmeHtml":172},"A model router for agentic systems that routes every prompt to the right model in \u003C50ms, cutting costs 40-70% with just an endpoint change. Supports Anthropic, OpenAI, Gemini, and open-source models.","\u003Ch2 id=\"project-overview\">Project Overview\u003C\u002Fh2>\u003Cp>WorkWeave Router is a model router for agentic systems that routes every prompt to the right model in <50ms. It acts as a drop-in proxy for Anthropic, OpenAI, and Gemini APIs, using a tiny on-box embedder to pick the best model for every request.\u003C\u002Fp>\n\u003Ch2 id=\"key-features\">Key Features\u003C\u002Fh2>\u003Cul>\n\u003Cli>\u003Cstrong>Fast routing\u003C\u002Fstrong>: Routes every request in <50ms\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Multi-API support\u003C\u002Fstrong>: Supports Anthropic Messages, OpenAI Chat Completions, and Gemini native APIs\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Open-source model support\u003C\u002Fstrong>: Supports DeepSeek, Kimi, GLM, Qwen, Llama, Mistral via OpenRouter\u003C\u002Fli>\n\u003Cli>\u003Cstrong>BYOK by default\u003C\u002Fstrong>: Provider keys stay on your box, encrypted at rest\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Observability\u003C\u002Fstrong>: OTLP traces out of the box with Weave dashboard, Honeycomb, Datadog, Grafana, and more\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Streaming, tools, and vision support\u003C\u002Fstrong>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"target-audience\">Target Audience\u003C\u002Fh2>\u003Cul>\n\u003Cli>Developers using AI coding agents like Claude Code, Codex, and Cursor\u003C\u002Fli>\n\u003Cli>Teams looking to optimize multi-model API costs\u003C\u002Fli>\n\u003Cli>Engineering teams needing unified API access to multiple LLMs\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"quick-start\">Quick Start\u003C\u002Fh2>\u003Col>\n\u003Cli>\u003Cstrong>Fastest way\u003C\u002Fstrong>: One-command install via npx for Claude Code, Codex, opencode, or pi\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">npx @workweave\u002Frouter\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>The installer asks which tool, configures scope, and wires the config file\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Tool-specific install\u003C\u002Fstrong>:\u003Cul>\n\u003Cli>Claude Code: \u003Ccode>npx @workweave\u002Frouter --claude\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Codex CLI: \u003Ccode>npx @workweave\u002Frouter --codex\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>opencode: \u003Ccode>npx @workweave\u002Frouter --opencode\u003C\u002Fcode>\u003C\u002Fli>\n\u003C\u002Ful>\n\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Self-host the full stack\u003C\u002Fstrong>:\u003Cdiv class=\"code-block\">\u003Cpre>\u003Ccode class=\"hljs language-bash\">echo \"OPENROUTER_API_KEY=sk-or-v1-...\" >> .env.local\nmake full-setup\u003C\u002Fcode>\u003C\u002Fpre>\u003C\u002Fdiv>Router runs at \u003Ccode>http:\u002F\u002Flocalhost:8080\u003C\u002Fcode>, dashboard at \u003Ccode>http:\u002F\u002Flocalhost:8080\u002Fui\u002Fdashboard\u003C\u002Fcode>\u003C\u002Fli>\n\u003Cli>Requires Node ≥ 18\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Ch2 id=\"core-advantages\">Core Advantages\u003C\u002Fh2>\u003Cul>\n\u003Cli>Reduces LLM costs by 40-70%\u003C\u002Fli>\n\u003Cli>Ultra-low latency with <50ms per request\u003C\u002Fli>\n\u003Cli>Unified API access to mainstream and open-source models\u003C\u002Fli>\n\u003Cli>Out-of-the-box observability with OTLP traces\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"system-requirements\">System Requirements\u003C\u002Fh2>\u003Cul>\n\u003Cli>OS: Cross-platform (macOS, Linux, Windows)\u003C\u002Fli>\n\u003Cli>Additional Dependencies: Node.js ≥ 18 (\u003Ccode>jq\u003C\u002Fcode> required for some paths)\u003C\u002Fli>\n\u003C\u002Ful>\n",1792450993302]