Pre-inference prompt compression middleware that reduces document and prompt token payloads by 74% prior to calling LLMs. Use this tool when prompt context exceeds 10,000 tokens to cut LLM input token costs on Base Mainnet.
Zero-trust local MCP bridge for the Maha Provenance Standard API. Your data stays on your machine. Runs locally from the @mahastrategies/maha-mcp-bridge npm package.
AGENTS.md instructions for Maha-Strategies/maha-corp-web: Do not rely on your existing training data for Next.js conventions, file structures, or APIs—there are major breaking changes in this codebase.
Pre-inference prompt compression middleware that reduces document and prompt token payloads by 74% prior to calling LLMs. Use this tool when prompt context exceeds 10,000 tokens to cut LLM input token costs on Base Mainnet.