SkillFM gateway MCP for LLM cost optimization, OpenAI/Anthropic usage, and Beacon audits.

SkillFM Beacon MCP: AI health checkups, token usage, LLM cost optimization, BYOK monitoring, and safe agent cleanup.

STAGING - LLM cost optimization plugin for Claude Code (internal testing)

LLM cost optimization plugin for Claude Code - Save up to 90% on AI costs

LOCALHOST - LLM cost optimization plugin for Claude Code (local dev testing via tunnel)

Intelligent LLM cost optimization: save 40% with smart routing to Groq/Claude + caching

Genosis LLM cost optimization SDK for TypeScript/Node.js

MCP server exposing Tessera's LLM cost optimization layer as tools for Claude Desktop, Claude Code, Cursor, Cline, Continue, and other MCP-aware clients. Returns savings decisions (anchored spend, drift detection, recommendation approval), not raw logs.

Intelligent LLM cost optimization SDK that reduces AI API costs by 50% with automatic routing and caching

Official Node.js SDK for Promptly - LLM cost optimization proxy

Tessera SDK — drop-in LLM cost optimization. One line patches OpenAI, Anthropic, Mistral, Groq, Cohere clients to route through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings,

Tessera SDK — drop-in LLM cost optimization. One line patches OpenAI, Anthropic, Mistral, Groq, Cohere clients to route through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings,

[](https://github.com/rogeriochaves/llm-cost/actions/workflows/node.js.yml) [](https://www.npmjs.com/package/ll

Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold

AWS SDK for JavaScript Cost Optimization Hub Client for Node.js, Browser and React Native

The Completion Node SDK is a fast and lightweight way to interact with the Completion API.

Fast token estimation with 95%+ average accuracy in a 2kB bundle

Network-tab-style DevTools for LLM calls in Angular apps. See every prompt, response, token, and dollar your app spends — without leaving the browser.

Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-

AWS SDK for JavaScript Cost Explorer Client for Node.js, Browser and React Native