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.
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…
Also good to know about /doctor prompt-audit in Claude Code 2.1.283+: It reports if there are any contradictions or outdated information in instruction files and does not change anything.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…
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…
Each agent sees only the memory you allow it, per agent. Did you have a chance to try it? https://trysubstrate.co/l/a2hn
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…
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…
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…
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…
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…
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…
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…
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
Cool. Followed you on X. Would you mind replying there?
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…
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…
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…
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…
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…
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.
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…
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…
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…
Each agent sees only the memory you allow it, per agent. Did you have a chance to try it? https://trysubstrate.co/l/a2hn
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…
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…
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…
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…
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…
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…
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…
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
Cool. Followed you on X. Would you mind replying there?
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…
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…
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…
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…
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…