capability-routing

Decision Infrastructure for the AI Era. 🧠✨️🤺

Host-aware model routing for coding agents. Python library + MCP server for Claude Code, Codex, Gemini CLI, Copilot, Cursor, and Aider.

Provider-agnostic AI gateway with capability-based routing, in-memory rate limiting, and observability hooks.

无极军团 3.0：面向 Codex 的智能工作中枢。以自然语言组织 Skill、插件与 MCP，保留白帽判断、有界执行与证据驱动进化。公开开发中。

Distributed Cognitive Operating System (DCOS): A capability-oriented architecture for modular AI orchestration with specialized Cognitive Cells.

A zero-dependency validator that turns capability-router soft rules into hard, testable checks — truncation-safety, structural, drift. / 路由体检器。

An execution kernel for AI systems featuring agent orchestration, capability routing, memory coordination, policy enforcement, workflow execution, and runtime management.

Make LLMs from different vendors collaborate as one team. Capability-based task routing across Claude / GPT / Gemini / Ollama. Lead dispatches → broker filter-broadcasts → workers (any LLM, any host) pick up matching tasks. Single-vendor stacks already have subagents — this is for when the right tool for the job lives in another vendor's stack.

Explainable, constraint-preserving MCP/model routing with durable Tasks, bounded local Runs and verifiable outcomes. Developer preview.

AI business solution delivery console with capability routing, pain-point analysis, tool selection, deliverable generation, and KPI validation.

Capability-oriented runtime that translates math problems into executable Python using LLMs.

Selecting and Governing LLMs: a 2026 decision framework for choosing, evaluating, buying, and operating language models across SMB, mid-market, and enterprise — with a runnable eval harness.

Live Technocore onboarding, Sybil-aware Agent Passports, opt-in capability routing, setup diagnostics, activity observations, and non-repeating service ideas.