Hacker Newsnew | past | comments | ask | show | jobs | submit | jcutrell's commentslogin

My problem with all of these kinds of things is that memory architecture is the whole point.

If all I needed was common memory space I'd just use symlinks and cloud sync, Obsidian or whatever.

But the context shaping is what makes memory useful in the first place, so just doing one stop shop memory is IMO about as useful as plain old markdown...


Plain old markdown with links is exactly what I use. But I split memory in 3 parts

1. a log of user comments, all of them collected in a chat_log.md file which is used to validate the agent still follows user intent

2. task level memory, a task.md file starts as intent, becomes plan, workbook with inlined results for each gate, and finally remains as documentation; same task.md is passed to judge agents and back; a project can have 100+ tasks logged in, the task is the natural unit of work

3. a project state mind map which tracks current known value of all decisions and intents, it is used to start the agent new sessions and updated after each task

This is it, a memory of user intent, one of agent work, and one of project state. I used this setup in over 100 projects. My harness uses hooks to constrain the agent

1. can't edit code files without an open task

2. the next current gate ("[ ] plan item") is displayed in the post tool use hook as an instruction pointer, auto-advances as current gate gets checked; this keeps the agent straight even in task.md files with 100s of gates

3. can't close a task until all gates are solved

4. a post user message hook appends to chat_log.md, which is cheap

The harness can be refined by optimizing task.md plan structure for various types of tasks, based on reflection. We can do reflection because we keep the 3 memory types.

Memory works for my harness because I don't split the place where memory sits from the place where work gets done and tracked. The plan items are this place. A single gate starts as intent and ends as a log like of work done. The task.md file is edited as it is solved.

https://github.com/horiacristescu/claude-playbook-plugin


Silly or not, precedent matters and labeling it silly is rhetorical. The impact is going to be critically important.


This really is the perfect time for something like MDX to shine.


With products coming out like this, many claim to do basically the same thing.

How is this better than Claude Code's built in agent orchestrator? Do I need 100 agent types? How do I know the trained agents here are somehow better? Specialization doesn't equate to "better" in every case.

I want to see the light but at this point it feels like these kinds of projects need a better way to benchmark how they are improving on the available state of the art.

It feels like in 2018, a new browser state management tool emerging. Why does this exist?


Most of the things on the linked doc's list of things Claude Code can't do, it definitely can.


I'd call this optimistic overengineering. Throw every fad at a problem, rather solving a problem iteratively.


This is what Apple promised a long time ago, and just couldn't quite connect on delivery.


I'm considering starting Tirz, but really want to go to retatrutide. Curious if you have a recommendation.


This could be modeled with stdev


Aside from it being "instructions for agents", I'm not sure I understand how this isn't just a markdown file that more or less reads like a readme that targets more junior engineers.


No, you nailed it. The rest is theater.


I am curious about how this compares to dataview. As a dataview user, I'm not immediately seeing something bases does that dataview doesn't, but I am not a power user.


Dataview can be used for queries that output tables, but its strength is letting you write essentially custom imperative Javascript code that renders stuff in notes dynamically (dataviewjs mode). Whereas "queries to tables" is more or less what Bases does, the dataviewjs mode will probably always be unique.


Garner Health | Data Engineer II | Full-time | NYC Onsite / Hybrid (4 days/week) | https://job-boards.greenhouse.io/garnerhealth/jobs/552040000... Garner Health (https://getgarner.com) is revolutionizing healthcare economics through advanced doctor performance analytics and innovative incentive models. Our platform is reshaping how organizations access high-quality, affordable care, powering decisions at leading healthcare systems and enterprise clients. We’ve doubled revenue annually for 5 years running, making us the fastest-growing company in our space. We’re hiring a Data Engineer II to play a pivotal role in building our enterprise-grade data platform from the ground up, ensuring secure data access across our rapidly scaling organization.

Stack: AWS, Snowflake, Argo, dbt, Terraform, Airbyte, JetStreamWork style: Hybrid in NYC. In-office up to 3 days per week.Target compensation: $120,000 - $160,000 + equity

Apply here: https://job-boards.greenhouse.io/garnerhealth/jobs/552040000... or email Jonathan.Cutrell [at] getgarner [dot] com


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: