QQiushiinclaw-stack.hashnode.dev·Mar 16 · 12 min readTeaching an AI to Attend Your Teams Meeting: A Real-Time Voice PipelineMicrosoft Teams has a lot of AI features now. Copilot can summarize meetings after the fact. It can generate action items. It can transcribe. What it cannot do — at least not in any form that worked for us — is let you summon an AI agent mid-meeting ...00
QQiushiinclaw-stack.hashnode.dev·Mar 10 · 7 min readFrom Code Completion to Code Team: How We Turned Claude Code into an Engineering DepartmentWe use Claude Code every day. It's excellent. It handles complex refactors, writes tests, navigates large codebases, and catches bugs we'd miss. But after months of running it as part of an autonomous multi-agent system, we noticed something: Claude ...00
QQiushiinclaw-stack.hashnode.dev·Mar 9 · 10 min readMemory System v2: Solving the Context Bloat ProblemIn our last post on building a persistent memory system, we described the MEMORY.md bloat problem: after six weeks, the file had grown to over 700 lines, and we fixed it by switching from inline content to pointer-based entries. The fix worked. MEMOR...00
QQiushiinclaw-stack.hashnode.dev·Mar 9 · 6 min readMaking iMessage Reliable with OpenClaw: 3 Problems and How We Fixed ThemOpenClaw can use iMessage as a communication channel — you text your AI agent, it texts you back. Sounds simple, but running it 24/7 on a Mac mini revealed three reliability issues that took weeks to fully diagnose. Here's what went wrong and how we ...00
QQiushiinclaw-stack.hashnode.dev·Mar 7 · 8 min readBuilding a Tri-Modal Knowledge Engine for CTF AgentsWhen Librarian gets asked about tcache stashing, it needs to return something more useful than what a base Claude model knows. The model has a general understanding of heap exploitation — it can describe what tcache is, explain the concept of a stash...00