Hacker News: anatoliikmt

New comment by anatoliikmt in "Show HN: Continual Learning with .md"

anatoliikmt — Thu, 16 Apr 2026 09:04:04 +0000

Yes, exactly. I made the Context Layer into a skill where I describe the structure. So when I say, "reindex", the agent knows to check and update the index files. Also it knows if it modifies any file, it needs to also update the index. Works really well!

New comment by anatoliikmt in "Show HN: Continual Learning with .md"

anatoliikmt — Thu, 16 Apr 2026 00:09:38 +0000

I found progressive discovery works very well. I have an INDEX.md file in every folder with a table describing what files are in that folder and what they do.

New comment by anatoliikmt in "Show HN: LangAlpha – what if Claude Code was built for Wall Street?"

anatoliikmt — Wed, 15 Apr 2026 16:36:08 +0000

Very cool! I see the default way to collect data in the tool comes from Ginlix API, so I was wondering what is the self-hosting story? Is there a way to achieve the same functionality as the default website?

New comment by anatoliikmt in "Show HN: Druids – Build your own software factory"

anatoliikmt — Wed, 15 Apr 2026 16:31:34 +0000

Currently looking for a good solution for exactly this. Druid looks very cool and thought-through. Two major blockers for me to use it in my workflow:

- Sandbox-only environment. For certian workflows I may want to run agents directly on my machine. - No Cursor agent support. Cursor supports ACP, so should in principle plug-in neatly in the existing framework.

New comment by anatoliikmt in "Show HN: Continual Learning with .md"

anatoliikmt — Wed, 15 Apr 2026 15:50:07 +0000

Using the same approach for dev documentation storage: https://ctxlayer.dev/

Has been working for me for a couple of months already. So far human curation of context is the way to go.

New comment by anatoliikmt in "Ask HN: How is AI-assisted coding going for you professionally?"

anatoliikmt — Mon, 16 Mar 2026 02:16:22 +0000

Has been a game-changer for me. The following cases are where it shines:

- Figuring out the architecture of a project you just came into

- Tracing the root cause of a bug

- Quickly implementing a solution with known architecture

I figured out that above all, what makes or breaks success is context engineering. Keeping your project and session documentation in order, documenting every learning you've made along the way (with the help of AI), asking AI to compose a plan before implementing it, iterating on a plan before it looks good to you. Sometimes I spend several hours on a plan markdown document, iterating on it with AI, before pressing "Build" button and the AI doing it in 10 minutes.

Another important thing is verification harness. Tell the agent how to compile the code, run the tests - that way it's less likely to go off the rails.

Overall, since couple of month ago, I feel like I got rid of the part of programming that I liked the least - swimming in technicalities irrelevant for the overall project's objectives - while keeping what I liked the most - making the actual architectural and business decisions.

I wrote a blog recently about the approach that works for me: https://anatoliikmt.me/posts/2026-03-02-ai-dev-flow/

And this is a tool for context engineering I made specifically to support such a flow: https://ctxlayer.dev/

Bureaucratic way of efficient AI-assisted development

anatoliikmt — Wed, 04 Mar 2026 14:10:54 +0000

Article URL: https://anatoliikmt.me/posts/2026-03-02-ai-dev-flow/

Comments URL: https://news.ycombinator.com/item?id=47247584

Points: 1

# Comments: 0

Show HN: A human-curated, CLI-driven Context Layer for AI agents

anatoliikmt — Wed, 25 Feb 2026 11:09:51 +0000

The Context Layer is my take on treating context as a first-class, external layer that exists and evolves alongside your codebase. It's an agent-agnostic CLI tool designed for keeping long-lived project context structured and accessible across projects.

It's intentionally human-curated - nothing is auto-collected or inferred. The goal is control, granularity, and explicit structure rather than embeddings or opaque memory systems.

I've been using it across a few projects so far. Curious to hear from others experimenting with AI-assisted workflows!

Website: https://ctxlayer.dev/

Tutorial: https://ctxlayer.dev/docs/

GitHub: https://github.com/anatoliykmetyuk/ctxlayer

Comments URL: https://news.ycombinator.com/item?id=47150033

Points: 2

# Comments: 0