agents-best-practices: A provider-neutral Agent Skill library for designing, auditing, and refactoring agentic harnesses compatible with Codex and Claude Code. It covers the full control plane of an agent runtime: typed tool design, permission checks, context management, memory, and observability. Targeted at developers building production-ready agent systems across any domain or AI provider.; houtini-lm: Houtini LM connects Claude Code to a local LLM server or any OpenAI-compatible API, offloading bounded tasks to reduce token costs. It provides tools, performance tracking, and model routing for efficient delegation. Claude remains the orchestrator for complex reasoning, while cheap local models handle grunt work.
Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
Generate test stubs