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.; yantrikdb-server: YantrikDB is a cognitive memory engine designed for AI agents that goes beyond vector databases by implementing forgetting, consolidation, and contradiction detection. It provides token-efficient recall, proactive triggers, and a comprehensive API for memory operations, making it suitable for persistent AI systems.
Generate MVP agent harness blueprints for any business domain (CRM, ops, finance, healthcare)
Running as a network server for distributed memory operations