Keyword: llm-router
- @askalf/darioReleased2d agoVersion4.8.100
Use your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, the Agent SDK, your scripts — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint.
- adaptive-memory-multi-model-routerReleased14h agoVersion2.14.60
RouterArena #1 among known public baselines: 96.77% accuracy, $0.0768/1K, 1.0000 robustness. OpenAI-compatible LLM router across 47+ providers.
- @blockrun/clawrouter-codexReleasedyesterdayVersion0.4.0
Front-adapter that lets OpenAI Codex (Responses API) talk to a ClawRouter proxy — wallet-signed, x402-paid, zero API keys.
- lynkrReleased2 weeks agoVersion9.5.0
Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and LM Studio with prompt caching, MCP tools, and 60-80% cost savings.
- @workweave/routerReleased5d agoVersion0.2.4
One-command installer that points Claude Code, Codex, opencode, or pi at the Weave Router. For pi it also ships the routing extension, loaded via pi.extensions.
- @inferlane/mcp-serverReleased3d agoVersion1.3.0
MCP server for InferLane — smart model routing and cost optimization for AI agents. Works with Claude Code, Claude Desktop, Goose, Cursor, and any MCP client. Includes stdio and HTTP transports.
- correctover-mcp-serverReleased3d agoVersion1.0.3
The first MCP server that verifies AI outputs in real-time — 6-dimension contract validation (structure, schema, latency, cost, identity, integrity) with automatic self-healing failover across 9+ LLM providers. BYOK, zero-dependency, one-line JSON config
- omnicall-routerReleased3d agoVersion1.2.1
Open-source smart LLM router for the Omnicall gateway. npx omnicall-router works FREE out of the box — point any OpenAI client at it, send model "auto", and it routes to the cheapest of 248 capable models. Pass a funded gck_ key to unlock all 248 pay-pe