AI Agent Capability Router for Claude Code, Codex CLI, self-hosted LLM relays, OpenRouter-compatible gateways, and automation workflows.

claude-node lets Python directly run, supervise, and integrate the real local Claude Code runtime. It preserves native CLI capabilities through stream-json, explicit session lifecycle, and process-level control — not another high-level agent framework, but a thin runtime layer for embedding Claude Code into your own systems.

Markdown protocol for multi-vendor AI agent teams — capability cards, bandit routing, and lessons that compound.

Local-first LLM routing layer for agentic coding workflows, provider delegation, and cost-aware subagent execution.

A local-first home for AI agents, routing tasks to the right model while keeping your workspace flexible, private, and resilient.

Read-only Codex token auditing, adaptive model routing, and experimental Sol-Terra-Luna orchestration skills.

Deterministic, auditable agent/skill dispatch for Claude Code. A typed seven-decision scoring kernel runs after the router has read the conversation — post-cognitive routing instead of prose-scanning. Auto-generates its catalog from skill sidecars and agent frontmatter.

Internal routing component and reference registry for Codex skills

A model-agnostic Agent Skills library for explicit routing, bounded context, and verifiable agent behaviour.

Route tasks between Claude Code and Codex CLI — Subscription Efficiency Maximizer for AI coding subscriptions ($40-$400/mo)

Ranks your installed Claude Code skills/agents for a task and routes to the best one — and learns from your ratings.

Intelligent MCP router for AI subagents with config-driven rules and LLM semantic tagging

A local multi-agent AI chat workspace with model routing, presets, and real-time room updates.

Letitbe Router: semantic routing plus adaptive limit-aware scheduling for AI agents and models

The Registry Pattern for AI Agents: Build, Connect, and Route Multi-Agent Systems with Ease.

Workflow registry and cost-aware routing policy layer for local coding agents.

Simulated AI-agent architecture workbench with provider routing, queueing, deterministic output, metrics, API, and dashboard.

Cost-aware AI agent routing across Codex and WorkBuddy—save premium intelligence for the work that truly needs it.

This Python tool employs multi-agent routing to efficiently handle diverse tasks: one agent generates QR codes, while another retrieves and processes data from a CSV file. Depending on the user's query, the appropriate agent is dynamically selected to provide accurate responses or actions.

A practical way to route Codex tasks to the right model and reasoning tier, with five agent profiles, a local dispatcher, and receipts that confirm what actually ran.