When it comes to AI Memory, everyone's arguing "RAG vs. grep" like it's a religious war. It's not. It's just a cost curve. I've gotten this question so many times that I thought I'd just share my thoughts. So here goes:
Vector search wins when your corpus is massive, messy, and unstructured. Thousands of docs, no clean boundaries, meaning matters more than exact words.
Filesystem plus grep wins when your corpus is structured and actually yours. A folder of markdown files you can open, read, and audit line by line. No infra required.
Anthropic already ran this experiment in production. Claude Code dropped its RAG pipeline for plain agentic search (grep, glob, read) and it outperformed the vector pipeline on real work. Not close.
But the benchmark wars are missing the actual point. It was never about picking one. It's about knowing what each layer is for.
Markdown is your source of truth. Portable, human readable, greppable, not locked to one provider. Memory you can actually own and move.
Vector search is an accelerant on top of that truth. A fast index for when the haystack gets too big for exact match to keep up.
Use either one alone and it breaks down:
- Markdown alone stalls at scale and struggles with paraphrasing or fuzzy recall
- Vectors alone turn your memory into a black box you can't read, audit, or export
The next step for memory infrastructure isn't picking a side. It's the filesystem as the ledger and RAG as the index on top of it, so memory stays legible and portable, and still fast when it needs to be.
This is the exact direction we're building with AI Context Flow: markdown as the portable, ownable source of truth, with retrieval layered on top instead of replacing it.
If your memory only exists as embeddings inside someone else's vector DB, that's not memory. That's a lease.
Which team are you on?
Ancher
AI Context Flow
@vincentwu800 Thanks! Yes, developer context management is absolutely in the roadmap. We're soon dropping extensions for Claude and ChatGPT desktop, along with a VS Code extension.
RiteKit Company Logo API
@hira_siddiqui1 An idea for you: you might provide an organized library of common language chucks to include in prompts. I feel like a lot of us are just guessing. Maybe start with product? service? Care to choose your Technologies, data sources, etc.?
AI Context Flow
@osakasaul we will be adding meta-settings on individual memory buckets soon. So this is on the roadmap!
Termdock
Congrats on the launch. This is a real pain point finally getting treated.
As someone who works with AI daily and builds with it, I bounce between ChatGPT, Claude, and Gemini all the time. The tiring part isn’t the models. It’s retyping project context, brand voice, and tech details over and over. AI Context Flow turns that into save once, use anywhere. That angle lands.
Your memory approach makes sense in practice. Keep the last turns. Summarize the middle so decisions and facts survive. Use semantic vectors for the deeper stuff. Separate queries from data so questions don’t leak into “things to remember.” These are the traps people hit in real workflows.
For people who work across tools, the mental load drops. Fewer background paragraphs. More attention on the problem at hand. Looking forward to what you ship next.
AI Context Flow
@hcyt exactly! you explained it better than I could :)
Hope you enjoy using the product!
Congrats on the launch! Does it only apply to chrome or also applicable on other browsers?
AI Context Flow
@yuzulele09 it works on Chrome, Brave, Opera and Edge browsers currently.
Support for Mozilla is on the roadmap.
That's really interesting idea. Is there an app for it?
AI Context Flow
@s_muneeb not an app yet, but a lot of people have been asking for mobile support, so we are discussing it internally.
We do have MCP servers that we will launch soon.
You will have a lot of data about people! How do you store it?
AI Context Flow
@alextroitsky so glad you asked this!
So, the data is stored in vector dbs but is end-to-end encrypted and processed in Trusted Execution Environments (TEEs) - so only the user has ownership of their data and can decide where do they divulge which information.
Agnes AI
Very interesting concept! AI memory is getting more and more attention. Just curious - how do you index different memories context?
AI Context Flow
@cruise_chen I'm so glad you asked, because we've built a sophisticated multi-layered memory indexing system that mimics how human memory actually works.
Here's how we index different memory contexts:
1. Three Tiers of Memory (Like Human Memory)
- Short-term memory: We preserve the last 3 conversation turns verbatim - this is your "working memory" that keeps the immediate context fresh
- Mid-term memory: Older conversations get intelligently summarized using LLM, extracting key facts, decisions, and entities - think of it as your brain consolidating information while you sleep
- Long-term memory: All uploaded documents and contexts are converted to semantic vectors (1024-dimensional embeddings using BGE-large-en-v1.5) and stored in AWS S3 Vectors for retrieval
2. Intelligent Query-Data Separation
Before indexing, we use LLM to analyze user input and separate it into:
QUERY: What they're asking
DATA: What they're providing
This prevents "memory pollution" where questions get mixed with actual information you want to remember.
3. Multi-Tenant Isolation
Every memory is indexed with hierarchical metadata:
userId → profileId → context/file → chunks
This means your memories are completely isolated per user and per profile (like having separate notebooks for different projects).
4. Semantic Chunking & Retrieval
Documents aren't stored as raw text - we:
- Break them into semantic chunks
- Generate vector embeddings (capturing meaning, not just keywords)
- Use cosine similarity for retrieval (finding conceptually related content, even with different wording)
5. Context-Aware Optimization
We dynamically optimize what memory to use based on:
- Token budget (no overwhelming the AI with too much history)
- Semantic relevance (only pull memories that matter for the current query)
- Conversation continuity (balance between efficiency and context preservation)
The magic? Unlike traditional keyword search, our vector-based indexing understands meaning.
Ask "What's my Python code for authentication?" and it'll find your login implementation even if you never used the word "authentication" in your original document.
It's serverless, scales automatically, and because we're using AWS S3 Vectors, there's no infrastructure to manage - just pure memory intelligence!
Hope this gives you a sense of how much work has gone into this seemingly small memory extension!
Would love your feedback if you are deep into the AI memory space!