August 3, 2026· ~4 min readopenspec-pi: Spec-Driven Development, Built Into Your Agent<img src="/images/diagrams/openspec-pi.svg" alt="Diagram of openspec-pi showing how the pi agent auto-injects openspec context into the system prompt,
July 30, 2026· ~5 min readAgentMemory for .NET: Using Neo4j Knowledge Graphs as AI Agent Memory > **Teaser:** Neo4j's AgentMemory SDK for .NET brings graph-backed memory to AI agents — episodic, semantic, and procedural memory types stored as no
July 30, 2026· ~6 min readApplying the CaRE Protocol to Agent Benchmarks: Compute-Aware Evaluation for Skill and Memory Harnesses > **Teaser:** CaRE — the compute-aware remasking evaluation protocol that reversed published MDLM rankings — has been applied to our two open-source
July 30, 2026· ~6 min readGemini API Managed Agents: 3.6 Flash, Hooks, and Serverless Agent Orchestration > **Teaser:** Google's Gemini API now runs managed agents — persistent, stateful AI agents deployed as serverless endpoints with built-in tool execut
July 27, 2026· ~9 min readZot vs Pi vs OpenCode: A Hard Look at AI Coding Agent Harnesses<img src="/images/diagrams/zot-vs-pi-vs-opencode-benchmark.svg" alt="Benchmark comparison of zot, pi, and opencode showing startup time, memory usage,
July 9, 2026· ~6 min readThe AI Agent Stack 2026 — Production Architecture # The AI Agent Stack 2026 — Production Architecture By mid-2026, a clear architectural consensus has emerged beyond framework wars: agents are not m