Rag

6 articles about rag.

Why Desktop AI Agents Skip RAG and Use Structured Markdown for Memory

·2 min read

Most agent memory systems default to embed-and-retrieve. Desktop agents get better results with structured markdown files loaded by category - faster

agent-memoryragmarkdowndesktop-agentknowledge-managementai_agents

Built 4 Knowledge Bases and 3 Rotted - Why Flat Markdown Beats RAG

·2 min read

Flat markdown files with pointers beat comprehensive RAG knowledge bases. After building 4 knowledge bases and watching 3 rot, here is what actually works

ai-agentknowledge-baseRAGmarkdownmemory

Why Belief Extraction Beats Flat RAG for AI Agent Memory

·2 min read

Layered memory architectures with belief extraction outperform simple RAG retrieval for AI agents handling hundreds of conversations. Structured compression

agent-memoryragbelief-extractionlocal-llmknowledge-managementartificialinteligence

Is RAG Dead? Bigger Context Windows Shift the Use Cases

·2 min read

With context windows growing past 1 million tokens, many RAG use cases are better served by stuffing documents directly into context. RAG is not dead but

ragcontext-windowsllmembeddingsai-architecture

Why Standard RAG Is Terrible for AI Agent Long-Term Memory

·2 min read

Retrieval-augmented generation falls apart for persistent agent memory. Knowledge graphs via MCP offer a better path for AI agents that need to remember

ragmemoryknowledge-graphmcpai-agents

Tiered Memory for Desktop Agents - Plain Text First, Vector Search for Long-Term

·2 min read

How desktop AI agents should handle memory: plain text for recent context and vector embeddings only for long-term recall. A practical approach to agent

memoryragembeddingsdesktop-agentvector-searchai_agents

Browse by Topic