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.; entroly: Entroly is a context engineering engine that compresses an entire codebase into the AI context window using variable-resolution representation, removing duplicates and boilerplate. It achieves 78% fewer tokens per request, improves AI responses over time via reinforcement learning, and works with any AI coding tool via MCP server or HTTP proxy. The Rust-based core ensures sub-10ms overhead.
Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
Optimizing context for coding agents like Cursor and Claude Code