--- title: "Authora Dev (@authora) | Hashnode" description: "Authora Dev (@authora) writes on Hashnode. Read their latest articles and follow their work." url: "https://hashnode.com/@authora" --- @authora # Authora Dev @authora · Miami, Florida · Joined March 2026 ### [ASTs + Gemini: Building a Knowledge Graph to Fix Codebase Onboarding](https://authora.hashnode.dev/asts-gemini-building-a-knowledge-graph-to-fix-codebase-onboarding?utm_source=hashnode&utm_medium=feed) title: "Why AI coding agents keep forgetting your codebase (and how we fixed it with ASTs + Gemini)" published: false tags: \[ai, programming, tutorial, webdev\] Last week, I watched an AI coding agent make the same mistake for the third time in the sa... 5 min read · [authora.hashnode.dev](https://authora.hashnode.dev/asts-gemini-building-a-knowledge-graph-to-fix-codebase-onboarding?utm_source=hashnode&utm_medium=feed) [Apr 16](https://hashnode.com/posts/asts-gemini-building-a-knowledge-graph-to-fix-codebase-onboarding/69e0a09c65afa875154e687c) ### [Why Claude Mythos Needs Persistent Memory for Threat Detection](https://authora.hashnode.dev/why-claude-mythos-needs-persistent-memory-for-threat-detection?utm_source=hashnode&utm_medium=feed) title: "Why Claude Mythos Is Broken for Threat Detection Without Persistent Memory" tags: \[ai, security, programming, devops\] Last week, a threat-hunting workflow caught the same suspicious pattern three times. Not three different threats.The same on... 5 min read · [authora.hashnode.dev](https://authora.hashnode.dev/why-claude-mythos-needs-persistent-memory-for-threat-detection?utm_source=hashnode&utm_medium=feed) [Apr 16](https://hashnode.com/posts/why-claude-mythos-needs-persistent-memory-for-threat-detection/69e087bf87cf8cd2a441573d) ### [How I Solved AI Agent Amnesia With MCP Memory Servers](https://authora.hashnode.dev/how-i-solved-ai-agent-amnesia-with-mcp-memory-servers?utm_source=hashnode&utm_medium=feed) title: "Why AI coding agents keep forgetting everything (and how I fixed it with MCP memory)" published: true tags: \[ai, programming, tutorial, devops\] Last week, I watched an AI coding agent make the exact same mistake for the third time. It reintro... 5 min read · [authora.hashnode.dev](https://authora.hashnode.dev/how-i-solved-ai-agent-amnesia-with-mcp-memory-servers?utm_source=hashnode&utm_medium=feed) [Apr 15](https://hashnode.com/posts/how-i-solved-ai-agent-amnesia-with-mcp-memory-servers/69dfdbb236b14b7149f1f17a) ### [Solving LLM Memory Drift: Knowledge Graphs vs Vector Store Decay](https://authora.hashnode.dev/solving-llm-memory-drift-knowledge-graphs-vs-vector-store-decay?utm_source=hashnode&utm_medium=feed) title: "Why your AI agent gets dumber over time (and how to fix memory drift)" tags: \[ai, programming, devops, tutorial\] Last week, a coding agent in a test repo did something weird: it opened the right files, referenced the wrong API version, and co... 5 min read · [authora.hashnode.dev](https://authora.hashnode.dev/solving-llm-memory-drift-knowledge-graphs-vs-vector-store-decay?utm_source=hashnode&utm_medium=feed) [Apr 14](https://hashnode.com/posts/solving-llm-memory-drift-knowledge-graphs-vs-vector-store-decay/69de97e3bda3e980afd9ff8b) ### [Context Window Overflow? How Knowledge Graphs Fix AI Agent Memory](https://authora.hashnode.dev/context-window-overflow-how-knowledge-graphs-fix-ai-agent-memory?utm_source=hashnode&utm_medium=feed) title: "Why context windows keep breaking AI agents (and how knowledge graphs fix it)" tags: \[ai, programming, devops, security\] Last week, an agent in a coding workflow looked perfectly fine for the first 20 minutes. It knew the repo structure. It r... 5 min read · [authora.hashnode.dev](https://authora.hashnode.dev/context-window-overflow-how-knowledge-graphs-fix-ai-agent-memory?utm_source=hashnode&utm_medium=feed) [Apr 13](https://hashnode.com/posts/context-window-overflow-how-knowledge-graphs-fix-ai-agent-memory/69dd44c6af8a59bd53abf3d9)