Supercharge AI Agents, Safely

n2-QLN: Intelligent Tool Router & Semantic Search Layer for MCP. Connect 1,000+ tools through 1 interface. Prevent AI model confusion and maximize context window efficiency

Raven is a context firewall for OpenCode. It routes noisy search, docs, web, GitHub, and MCP calls through a free focused agent before they hit your main model. saving cost and context!

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

Semantic routing for MCP tools - .NET library that indexes MCP tool definitions and returns the most relevant tools via vector search

Budget-aware context compilation and context firewall for tool-heavy AI agents.

A retrieval-gated skill architecture for LLM agents that scales to hundreds of tools by exposing only the top-K relevant capabilities per request.

Orchestration MCP Server - Routes tool calls to MCP backends

A governed skill system for long-horizon human-AI collaboration.

Resource-first MCP hub for routing upstream MCP servers through one small local tool surface.

Intelligent tool routing extension for pi coding agent - automatically selects the best tool stack for each task

LangGraph is a powerful framework built on LangChain that enables the creation of stateful, multi-step, and agentic workflows using directed graphs. It simplifies complex LLM orchestration by allowing conditional branching, memory, and tool integrations in a visual and modular way.

Intelligent routing layer for AI agents: recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.

Smart MCP router that routes tools by intent and reduces context rot for LLM hosts

Route semantic tool requests through one MCP router to simplify AI access to 1,000+ tools in n2-qln

Clean-room AI agent workspace patterns for mock tool routing, approval gates, and dry-run traces.

Rust/Burn neural pre-router for Hermes Agent toolset selection; 19 routes incl. X search, Kanban, media, social, productivity.

An AI assistant with hot-pluggable MCP tool servers — one Router Agent, dynamic tool discovery, and LLM-powered routing. Built with FastAPI, Redis, Ollama, Streamlit, and Prometheus.

On-device tool-routing models for the kAir iOS super-app. Qwen3.5-0.8B + LoRA on Apple Silicon (MLX-LM); 5-tool closed catalog with frozen JSON schema; three-layer artifact pipeline (HF → GGUF → Core ML / ONNX). Research / experimental.