Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/px0-ai/px0/memorygit clone --depth 1 https://github.com/px0-ai/px0What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01480 |
| Opus 5 | $0.00000 | $0.00740 |
| Sonnet 5 | $0.00000 | $0.00296 |
| Haiku 4.5 | $0.00000 | $0.00148 |
Grade A, and why
memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
px0 memory
What px0 knows about you, as opposed to what you have read.
The store already held two kinds of knowledge and neither was this one.
brain/ is material you deliberately ingested — posts, papers, docs — and it
answers questions about the world. guidelines/ is conventions you wrote down
and it shapes how output reads. Between them there was nothing that remembered
you: that standup goes out before 09:30, that "the API repo" means one
particular repository, that a person you keep mentioning is on your team.
So every run started from nothing, and every correction had to be made again the next time. That is the difference between a tool you operate and an assistant.
Implemented by px0/memory.py.
px0 memory [list] [--json]
px0 memory add "<text>" [--kind KIND] [--subject WHAT] [--pin]
px0 memory show <name> [--json]
px0 memory forget <name>
px0 memory search "<query>" [--json]
px0 memory suggest [--yes] [--json]
What it looks like on disk
One Markdown file per fact, under memory/, in the same shape as everything
else in the store:
---
kind: preference
subject: standup timing
learned: 2026-08-26
---
Standup goes out before 09:30, and never mentions unfinished work.
Kinds are fact, preference, person, project, and place. They are a
filing aid, not a schema.
Two things follow from that
A memory is editable, because it will be wrong. px0 writes these as a side
effect of conversations, and an assistant that silently accumulates
unreviewable beliefs about you is the failure mode to design against, not a
feature. Every one is a file you can open, correct, or delete — and every write
is a versioned change, so px0 changes list shows what px0 learned and when,
and px0 changes revert unlearns it.
Memory never leaves the machine on its own. It is inlined into prompts the
same way guidelines are — into the harness you already trust — and goes nowhere
else. px0 store export carries it, because an export is how a store reaches
your other machine and an assistant that forgets everything on the new one is
not one.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 185 lines · 0 tokens per session scan A 7482a2900db4
memory is a command published in the GitHub repository px0-ai/px0 (241 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,480 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
wiki-ingest
Ingest a source document into the LLM Wiki.
README
This folder gathers the project's 9 slash commands in a single place. Each command file specifies its traversal pattern (which Layer × Cycle cells it passes through, and in which cycle-stage flow) plus the Human Reviewer Gate. The nature of each role and the Layer × Cycle matrix have their SoT in…
wiki-discover
Discover unexpected connections in the LLM Wiki (Memex serendipity).
wiki-news
Search for latest news related to the LLM Wiki's key topics.
wiki-query
Query the LLM Wiki and synthesize an answer.
wiki-export
Export wiki to merged files for Claude.ai Project Knowledge.