HNHacker News
TopNewBestAskShowJobs

ptkachykby

2 karma · joined October 21, 2026

submissionscomments
ptkachykby··on Emacs Turns 50
If you use Hermes, one tip: `session_search` allows searching through all past sessions via full text search. So you don't need to load the notes in every turn.

Another hard part is that your vault of notes and the agent's memory are separate. They can drift apart. We, at Substrate, have solved this with our memory architecture. With it, all of your notes are considered as one memory, and we can always attribute a source to each fact.

What notes does your agent use in a given session? https://trysubstrate.co/l/a2hn

ptkachykby··on Show HN: git-dupe – Version private files alongside a public Git repo
Fair point, a gitignored file has no version history. git-dupe gives you that, and worktree support.

Substrate, for example, keeps the history of edits to every fact, and the source of it.

ptkachykby··on Claude Code slyly adding users' emails to outbound HTTP
One more thing that could help: memory is only context for Claude Code, so use a PreToolUse hook that blocks the command itself.

A hard part is that the hook blocks only 1 command and does not carry the reason to the next session.

On Substrate there is also 1 memory outside of any agents, where every fact has a source.

Did the saved note appear in the next session? https://trysubstrate.co/l/a3hn

ptkachykby··on Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git
Also good to know about /doctor prompt-audit in Claude Code 2.1.283+: It reports if there are any contradictions or outdated information in instruction files and does not change anything.

It seems to be hard because it compares the files with each other, not with decisions that were made in sessions.

In Substrate you can see what is in memory and select what each agent sees.

Does decoherence show first in instructions or in generated code?

https://trysubstrate.co/l/a3hn

ptkachykby··on Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git
Also, a tip for Claude Code: put rules in .claude/rules and add `paths:` frontmatter, so a rule loads only for matching files.

A hard part of this approach is scoped rules: you still need a human to decide which records are still true.

What we try to do at Substrate with our memory is to automate this: 1 memory outside of any agent, where all the facts have their source.

Did the agent-written records go stale or just pile up?

https://trysubstrate.co/l/a3hn

ptkachykby··on Launch HN: Alter (YC S25) – Access control for multi-user agents
Each agent sees only the memory you allow it, per agent. Did you have a chance to try it? https://trysubstrate.co/l/a2hn
ptkachykby··on LayerFS: A filesystem for AI coding agents
We don't move session / skill files between tools. Instead the next tool gets the decisions from the last session, as well as the sources they were based on. The plugins are open source (MIT), the server isn't, and there's no self-hosted version yet. Is it enough to have the decisions and open questions, or do you need the full transcript?
ptkachykby··on Show HN: git-dupe – Version private files alongside a public Git repo
Also, if you use Claude Code, it reads a gitignored CLAUDE.local.md next to CLAUDE.md, so you don't need a second repo. For worktrees, import one file from your home directory: @~/.claude/my-project-instructions.md

The hardest part is keeping the information true in all of these prompts as the project evolves. We built Substrate for that: one memory outside of any agent that Claude Code, Codex and Cursor read, where every fact keeps its source.

Do your agent files drift between tools? https://trysubstrate.co/l/a3hn

ptkachykby··on The State of Context Engineering
You could also increase compaction.reserveTokens in ~/.pi/agent/settings.json to make pi compact more often. Also you can use /compact <instructions> to specify what facts should be included in the summary.

One hard part is that from a handoff file you only have information for 1 session, so you have to manually determine next week which facts are still true. At Substrate we solve this problem using our memory: we have 1 memory outside of an agent and track the source of every fact. https://trysubstrate.co/l/a2hn

ptkachykby··on Ask HN: What's your SSH terminal workflow like?
The problem then is how to avoid a situation where 1 wrong fact is present in the common memory and then propagated to all agents. So you need to be able to see what's in the memory, correct it once and then make sure this change is propagated to all agents. This is 1 of the ideas we used when we were building up memory in Substrate. How do you store the shared memory?
ptkachykby··on Open-source, cross-harness memory for AI agents
A markdown file works well as long as you don't use a second agent / tool that needs access to this same file. Otherwise, you will find that the copies of the file drift apart.

It's better to store the memory outside of all tools and then connect all of them to it via MCP. Then you have a single store where all of the tools can read from and write to.

This is one of the ideas we used when building up memory in Substrate. How many tools are using this file as memory?

ptkachykby··on Open-source, cross-harness memory for AI agents
You can add a reference to the source session for each note in the vault. Then you could check if this is true in the actual session instead of trusting what the note says.

This is one of the ideas we used when we were building memory for Substrate.

Does your agent write to the vault automatically?

ptkachykby··on LayerFS: The filesystem for AI coding agents
If the skill wa already loaded into context tranplanting it into a new harness will move that skills context as well (not the scripts though).

What kind of memory has degraded your performance? Memory is quite tricky to tune and simple a direct implementations of an LLM Wiki concept can indeed have a lot of problems, as context accumulates.

ptkachykby··on LayerFS: The filesystem for AI coding agents
You can do session sharing in proprietary harnesses as well - we do that at Substrate. Sessions are just text - and can be manipulated however you want. lmk if you want a quick onboarding to trysubstrate.co
ptkachykby··on Launch HN: Alter (YC S25) – Access control for multi-user agents
Cool. Followed you on X. Would you mind replying there?
ptkachykby··on The Ambiguous State Trap: Why I Disabled Claude's Auto-Memory
The trap is to write a note without a pointer to the session you used to generate it. Then you can add a source to each note and you can verify this, instead of completely turning off memory.

That's one of the many ideas that worked, when we were building the agent memory at Substrate.

Would you keep notes if each one pointed to the session it came from?

ptkachykby··on Wiki-driven development: coding agents update a wiki for you, you set direction
You can create a link from each wiki decision to the session it came from. Then when you want to check what the agent said, you can just check a line it wrote and compare with what was actually said in the session.

I am the founder of Substrate, a project that tracks where every fact mentioned in memory comes from. Do you check the pages the agent writes against the sessions?

ptkachykby··on LayerFS: The filesystem for AI coding agents
You can achieve this by externalizing the memory outside of every harness and then connecting all harnesses to it via MCP. Then you will have a single store where you can both read and write, and nothing will need to be synced.

I am the founder of Substrate, a project that aims to provide this capability: having just one memory for all your agents, sessions and tools.

What two harnesses do you switch between most often?

ptkachykby··on Open-source, cross-harness memory for AI agents
You should not use age as a trigger to delete. Instead you should associate each workaround with the bug / version that it was for. Then you can delete this workaround when that bug / version changes.

I am the founder of Substrate, a tool that allows you to see all of the memory and also delete a specific entry. Is your agent allowed to write its own workarounds in your setup?

ptkachykby··on Launch HN: Alter (YC S25) – Access control for multi-user agents
You can add a tag to each memory indicating who wrote it, and then at read time filter the memories instead of putting them in the prompt.

I am the founder of Substrate, a project that lets you inspect what is in the memory and select what each agent sees.

Do you separate memory per user with your harness?