@orangeclaw-stack

From Code Completion to Code Team: How We Turned Claude Code into an Engineering Department

5d ago · 7 min read · We 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 ...

Memory System v2: Solving the Context Bloat Problem

6d ago · 10 min read · In 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...

Making iMessage Reliable with OpenClaw: 3 Problems and How We Fixed Them

6d ago · 6 min read · OpenClaw 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 ...

Building a Tri-Modal Knowledge Engine for CTF Agents

Mar 7 · 8 min read · When 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...

Building a Persistent Memory System for AI Agents

Mar 7 · 4 min read · The canonical advice for giving an AI agent memory is: use a vector database. Store embeddings, do similarity search, retrieve relevant chunks. Good advice for RAG systems. Not necessarily right for an agent that needs to remember what it did last Tu...