austinbaggio

| need a solution for context decay and relevant curation — with benchmarks that prove it is also more valuable than constant rediscovery (for quality and cost).

I agree. We are looking at some metr benchmarks, not expecting a simple answer to this, but do you have any in mind you find compelling?

What are you both looking for? What is the problem you want solved?

Oh got it - tool use

If you give it a try, I think that use case should work, but if not, I would be grateful if you told us what broke.

And also - I genuinely worry about vendor lock-in, do you?

I can't find it, but there's a good graph that shows Google search decline in share to GPT, but it excludes Gemini. With Gemini, it stays relatively on par. That's pretty much the answer with where one goes. LLMs are higher intent than search could ever be, and they are closer to you selling to yourself than a store selling to you since they have all of your user context

Yeah I get the dependency concern, and also I think about the trust and pricing challenge a lot. I might be getting ahead of my skis here, but living in a future world, assuming there is a local service, what would you want to see with a context management service for your team to actually use it? Or even better - pay for it?

Thanks everyone for the comments, really, I wasn't expecting this.

Quite a few of you have mentioned that you store a lot of your working context across sessions in some md file - what are you actually storing? What data do you actually go back to and refer to as you're building?

You store your project context in an ignored tmp folder? Share more plz - what does it look like? What do you store?

It sounds like you've used quite a few. What programs are you expecting? Assuming you're talking about doing some inference on the data? Or optimizing for some RAG or something?

In our experience, a lot of it is feel and dev preference. After talking to quite a few developers, we've found the skill was the easiest to get started with, but we also have a CLI tool and an MCP server too. You can check out the docs if you'd prefer to try those - feedback welcome: https://www.ensue-network.ai/docs#cli-tool

Since you've already thought about this problem, I'd love to hear your feedback after giving this skill a try. It should speed up at least your basic need of having to trigger the LLM to store the memory. One of our colleagues has found success asking at the end of a research session what he missed, how he could improve, etc.

Which of the 1000 is your favorite? There does seem to be a shallow race to optimizing xyz benchmark for some narrow sliver of the context problem, but you're right, context problem space is big, so I don't think we'll hurry to join that narrow race.

I assume this is with work? And also assume you do send data, you just need some service agreement or something like with AWS or Microsoft for GH?

Do you ever switch tools? I don't love the idea of my context being hostage of whatever LLM I choose first.

It is overwhelming. We have support for Cursor mcp as well, but you lose a lot of the auto-magic stuff you get with the Claude Code plugin. Unfortunately, skills are pretty sticky to the Claude Code stack. It is kind of the vim of AI coding agents. . . One of the goals for this tool was to address context management in a single place. i.e instead of setting up all of the rules, claude.md, and skill.md you just semantic query a specific namespace in your knowledge base.

the docs if you are curious: https://www.ensue-network.ai/docs

Good flag, we're still pretty early, I think the strict requirement for compensation disclosures is post 15 employees in CA? Did I get this wrong?

You can use it with summaries for sure, but summaries often miss edge cases and long sessions drift. This makes it easier to jump between tasks, come back days later, and reorient without missing something that the summarization or compaction might have gotten rid of. I've often found post-compaction, the memory of even the current session feels so much dumber.

It feels like Claude is taking more of the Android approach of a less opinionated, but more open stack, so people are bending it to the shape they want to match their workflow. I think of the amnesia problem as pretty agent-agnostic, though, knowing what happens while you're delivering product is more of an agent execution layer problem than a tool problem, and it gets bigger when you have swarms coordinating - Jaya wrote a pretty good article about this https://x.com/AustinBaggio/status/2004599657520123933?s=20

Do you find you want to share the .md with the teams you work with? Or is it more for your solo coding?

Honestly, very reasonable ask, you're not the first person to ask for a self-hosted version. We have a privacy policy we've drafted that is up-to-date with the current version of the product https://www.ensue-network.ai/privacy-policy.

The project is still in alpha, so you could shape what we build next - what do you need to see, or what gets you comfortable sending proprietary code to other external services?

Appreciate it - yeah, you're right, models don't work well when you just give it a giant dump of memory. We store memories in a small DB - think key/value pair with embeddings Every time you ask Claude something, the skill:

1. Embeds the current request.

2. Runs a semantic + timestamp-weighted search over your past sessions. Returns only the top N items that look relevant to this request.

3. Those get injected into the prompt as context (like extra system/user messages), so Claude sees just enough to stay oriented without blowing context limits.

Think of it like: Attention over your historical work, more so than brute force recall. Context on demand basically giving you an infinite context window. Bookmark + semantic grep + temporal rank. It doesn’t “know everything all the time.” It just knows how to ask its own past: “What from memory might matter for this?”

When you try it, I’d love to hear where the mechanism breaks for you.

How are you storing the agent context now?

Are you working with any projects to implement this yet?

How are you finding it as context grows? I've been thinking a lot about the storage part of this - getting context to agents, temporal and semantic search, going as complex as graph implementations. . . overkill?