#model-routing

Main agent plans and reviews; cheaper sidekick edits. Devin Fusion pattern for OpenCode

fak — the Fused Agent Kernel: one Go binary that turns a tool-using agent (Claude Code, Codex, Cursor, any OpenAI/Anthropic/MCP client) into a managed agent: cache-stable model traffic, context compaction + crash resume, nanosecond tool-call policy, local GGUF serving with SSD expert offload.

Personal, local-first desktop AI gateway for Windows, macOS, and Linux. Connect Claude Code, Codex, and Gemini CLI to OpenAI, Anthropic, Gemini, and compatible providers with protocol conversion, model-aware routing, quota visibility, and OS-protected credentials.

World-class Codex Skill and MCP harness for orchestrating Claude Code workers through CCSwitch multi-model routing.

Safe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated Fable 5 top rung. Not the cheapest router; the safest one inside Claude.

A shared knowledge vault + full software-engineering workflow for AI coding agents — run Claude Code and Codex in parallel with one memory, one plan.

Personal AI agent configuration hub: manages coding assistant setups (OpenCode, Claude, Copilot, Pi, Qwen), includes Headroom API proxy for LLM traffic compression, and integrated MCP server with persistent cross-session memory.

Hermes ARC (Adaptive Routing Core) — adaptive conversational orchestration plugin for Hermes Agent

Confidence-gated model routing for coding agents — run work at the cheapest model that can pass verification. SKILL.md, MIT.