{
 "schema_version": 1,
 "generated": "2026-10-26",
 "url": "https://dedupedai.com/best-ai-repos-for/llm-gateways-and-routers/",
 "task": "LLM gateways and model routers",
 "question": "What is the best open-source LLM gateway or router?",
 "answer": "The best open-source AI repos for LLM gateways and model routers right now are Litellm, CC Switch and Experiential. LiteLLM is the standard gateway pick: one OpenAI-format API for 100+ providers with cost tracking; CC Switch manages model and provider config for Claude Code, Codex and other coding tools from one desktop app.",
 "md": "https://dedupedai.com/best-ai-repos-for/llm-gateways-and-routers/index.md",
 "repos": [
  {
   "repo": "BerriAI/litellm",
   "title": "Litellm",
   "url": "https://dedupedai.com/use-cases/berriai-litellm/",
   "github": "https://github.com/BerriAI/litellm",
   "what": "LiteLLM is an open source AI Gateway and Python SDK that lets you call 100+ LLM providers through one OpenAI-format interface, with cost tracking, guardrails, and load balancing.",
   "who": "Developers and platform teams who call several LLM providers and want one API format, or who need a shared gateway for a team.",
   "stars": 61803,
   "language": "Python",
   "requirements": [
    "Python and the uv package manager installed",
    "API keys for the LLM providers you plan to call, such as OpenAI or Anthropic",
    "For the gateway use cases: a machine to run the proxy server on and a LiteLLM master key or virtual key for clients"
   ],
   "uc_count": 5,
   "use_cases": [
    {
     "title": "Call 100+ LLM providers through one OpenAI-format API",
     "url": "https://dedupedai.com/use-cases/berriai-litellm/call-100-llms-with-one-openai-format-api/"
    },
    {
     "title": "Run a shared self-hosted AI Gateway for your team",
     "url": "https://dedupedai.com/use-cases/berriai-litellm/run-shared-ai-gateway-with-virtual-keys/"
    },
    {
     "title": "Give LLM calls access to MCP server tools",
     "url": "https://dedupedai.com/use-cases/berriai-litellm/give-llm-calls-access-to-mcp-tools/"
    }
   ],
   "best": {
    "title": "Call 100+ LLM providers through one OpenAI-format API",
    "url": "https://dedupedai.com/use-cases/berriai-litellm/call-100-llms-with-one-openai-format-api/",
    "difficulty": "Intermediate",
    "time": "30 minutes",
    "agents": [],
    "steps": [
     "Install the SDK with uv add litellm",
     "Set the provider keys as environment variables, such as OPENAI_API_KEY and ANTHROPIC_API_KEY",
     "Call completion from Litellm with a model such as openai/gpt-4o",
     "Change the model string to anthropic/claude-sonnet-4-20250514 and run the same call again"
    ],
    "md": "https://dedupedai.com/use-cases/berriai-litellm/call-100-llms-with-one-openai-format-api/index.md"
   }
  },
  {
   "repo": "farion1231/cc-switch",
   "title": "CC Switch",
   "url": "https://dedupedai.com/use-cases/farion1231-cc-switch/",
   "github": "https://github.com/farion1231/cc-switch",
   "what": "CC Switch is a desktop app for Windows, macOS and Linux that manages the config of Claude Code, Claude Desktop, Codex, Gemini CLI, OpenCode, OpenClaw, Hermes Agent and other coding CLIs. It switches API providers in one click from 90+ presets, can route requests locally with format conversion and failover, and manages MCP servers, Skills and Prompts in one place, so you stop hand-editing JSON, TOML and YAML files. The only official site is ccswitch.io.",
   "who": "Developers who use more than one coding agent or more than one model provider and keep breaking config files by hand.",
   "stars": 148400,
   "language": "Rust",
   "requirements": [
    "Windows 10+, macOS 12+ or Linux with glibc 2.35+",
    "API keys or plans for the providers you add"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Switch Claude Code or Codex providers in one click",
     "url": "https://dedupedai.com/use-cases/farion1231-cc-switch/switch-claude-code-providers-in-one-click/"
    },
    {
     "title": "Add MCP servers and Skills once, sync them to every agent",
     "url": "https://dedupedai.com/use-cases/farion1231-cc-switch/sync-mcp-servers-and-skills-across-agents/"
    },
    {
     "title": "See token usage, spend and quotas across your coding agents",
     "url": "https://dedupedai.com/use-cases/farion1231-cc-switch/check-token-usage-across-coding-agents/"
    }
   ],
   "best": {
    "title": "Switch Claude Code or Codex providers in one click",
    "url": "https://dedupedai.com/use-cases/farion1231-cc-switch/switch-claude-code-providers-in-one-click/",
    "difficulty": "Beginner",
    "time": "10 minutes",
    "agents": [],
    "steps": [
     "Download CC Switch from the GitHub releases page (macOS users can use Homebrew)",
     "Open the page for Claude Code, Codex or another tool",
     "Add a provider from the presets and enter its key",
     "Click to switch; only the endpoint, key and model change, and the original config is backed up first"
    ],
    "md": "https://dedupedai.com/use-cases/farion1231-cc-switch/switch-claude-code-providers-in-one-click/index.md"
   }
  },
  {
   "repo": "experientiallabs/experiential",
   "title": "Experiential",
   "url": "https://dedupedai.com/use-cases/experientiallabs-experiential/",
   "github": "https://github.com/experientiallabs/experiential",
   "what": "Experiential is an open source gateway and router for agent workflows. It puts hosted, BYOK and local models behind one OpenAI-compatible API, lets you control which users and agents can use which models and how much they can spend, and turns production traffic into a custom router or model optimized for quality, speed and cost.",
   "who": "Developers and teams running coding agents or LLM apps who want one endpoint for many models, with spending limits and a path to cheaper routing.",
   "stars": 13003,
   "language": "Python",
   "requirements": [
    "Python with pip to install the package",
    "Provider keys for the models you want to route to (hosted, BYOK or local)",
    "For Capture: macOS, Python 3.13 or newer, and approval for its extension and certificate",
    "Optional: an account on the hosted platform, and Tinker for fine-tuning an open source model"
   ],
   "uc_count": 3,
   "use_cases": [
    {
     "title": "Run one local gateway in front of all your models",
     "url": "https://dedupedai.com/use-cases/experientiallabs-experiential/run-one-openai-compatible-gateway-for-all-your-models/"
    },
    {
     "title": "Repoint Claude Code, Cursor and Codex at one gateway",
     "url": "https://dedupedai.com/use-cases/experientiallabs-experiential/point-your-coding-agents-at-the-hosted-gateway/"
    },
    {
     "title": "Turn your agent traces into a cheaper router",
     "url": "https://dedupedai.com/use-cases/experientiallabs-experiential/turn-agent-traces-into-a-cheaper-router/"
    }
   ],
   "best": {
    "title": "Run one local gateway in front of all your models",
    "url": "https://dedupedai.com/use-cases/experientiallabs-experiential/run-one-openai-compatible-gateway-for-all-your-models/",
    "difficulty": "Beginner",
    "time": "15 minutes",
    "agents": [
     "claude-code",
     "codex",
     "cursor"
    ],
    "steps": [
     "Run pip install experiential",
     "Run exp to start a local OpenAI-compatible gateway; the setup wizard picks provider, model and reasoning effort, then shows defaults for the public alias, identity and the $50.00 command budget before printing a one-time key",
     "Choose a public alias such as opus-5 and capture the issued key",
     "Set the key with export EXP_GATEWAY_KEY=..., then send the curl request from the README to http://127.0.0.1:8000/v1/chat/completions with your alias as the model and the key in the Authorization header"
    ],
    "md": "https://dedupedai.com/use-cases/experientiallabs-experiential/run-one-openai-compatible-gateway-for-all-your-models/index.md"
   }
  },
  {
   "repo": "Alishahryar1/free-claude-code",
   "title": "Free Claude Code",
   "url": "https://dedupedai.com/use-cases/alishahryar1-free-claude-code/",
   "github": "https://github.com/Alishahryar1/free-claude-code",
   "what": "FCC is an open-source Python proxy that lets coding agents such as Claude Code and Codex use free, paid, and local models from many providers through one Admin UI.",
   "who": "Developers and power users who want to run terminal, IDE, or browser coding agents on low-cost or free model providers.",
   "stars": 62032,
   "language": "Python",
   "requirements": [
    "A macOS, Linux, or Windows computer with a terminal",
    "An API key from at least one provider in the README catalog, such as NVIDIA NIM",
    "Permission to run the install script from the README"
   ],
   "uc_count": 4,
   "use_cases": [
    {
     "title": "Run Claude Code on free models through FCC",
     "url": "https://dedupedai.com/use-cases/alishahryar1-free-claude-code/run-claude-code-on-free-models/"
    },
    {
     "title": "Keep a coding session running during provider outages",
     "url": "https://dedupedai.com/use-cases/alishahryar1-free-claude-code/keep-coding-through-provider-outages/"
    },
    {
     "title": "Run a Codex session on a project folder in the browser",
     "url": "https://dedupedai.com/use-cases/alishahryar1-free-claude-code/run-codex-sessions-in-the-browser/"
    }
   ],
   "best": {
    "title": "Run Claude Code on free models through FCC",
    "url": "https://dedupedai.com/use-cases/alishahryar1-free-claude-code/run-claude-code-on-free-models/",
    "difficulty": "Intermediate",
    "time": "30 minutes",
    "agents": [
     "claude-code"
    ],
    "steps": [
     "Run curl -fsSL \"https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh\" | sh on macOS or Linux, or the PowerShell command from the README on Windows, and choose Claude Code when prompted.",
     "Run fcc-server on Linux, or open Free Claude Code from the desktop or Start menu on Windows or macOS.",
     "Open the Admin UI URL from the server log, open NVIDIA NIM under Providers, click Add key, paste your key, and click Save.",
     "Leave MODEL on the default or search the dropdown, then click Apply.",
     "Run fcc-claude and select an FCC model from Claude Code's native /model picker."
    ],
    "md": "https://dedupedai.com/use-cases/alishahryar1-free-claude-code/run-claude-code-on-free-models/index.md"
   }
  }
 ]
}