LeanMCP: Run AI Agents in Production. Own Your Stack
Open-Source Agent Runtime. Production-Grade Governance. Zero Vendor Lock-in

Search for a command to run...
Open-Source Agent Runtime. Production-Grade Governance. Zero Vendor Lock-in

Checkr is a voice + text AI companion built at NexHacks designed to remove barriers to mental health support for college students, via a conversational interface that acts, not just chats by connecting to real tools in the moment. What Checkr Does Wh...
Built at NexHacks (CMU) and submitted as a LeanMCP Add-on Track winner, Neocortex is an MCP server designed to help AI coding assistants reason over large GitHub repositories without resorting to whole-file context dumps. With meaning-based search, i...
With 240+ teams participating in NexHacks at Carnegie Mellon, WashedMCP stood out by tackling two of the most common failure modes in AI-assisted coding: costly search and setup repetition. WashedMCP is a token-efficient semantic code search MCP serv...
We're thrilled to announce the top three winners from the LeanMCP track at NexHacks hosted at Carnegie Mellon University! These outstanding projects demonstrated creative and practical applications of LeanMCP - pushing the boundaries of context-effic...

After reading OpenAI 2025 State of Enterprise AI report and OpenRouter 2025 State of AI Report. I Find some interesting things ☕️

In 2025, the Model Context Protocol (MCP) has matured as the open standard for connecting AI agents to external tools, prompts, and resources - backed by the Agentic AI Foundation (under Linux Foundation) since its donation by Anthropic and OpenAI. W...
