alice-memory

alice-memory is a skill for Claude Code, Codex from samrusani/AliceMemory. It costs 28 tokens per session (739 once invoked), scanned A, original, MIT.

A durable-memory procedure for saving and retrieving user information with Alice. It supports remembering facts, recalling stored information, and resuming ongoing work.

In plain words
What is it for?
Use it to store lasting information, search memory or imported sources, and recover the next action or recent changes.
Why use it?
It helps preserve useful context between sessions so the agent does not rely only on the current conversation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to store lasting information, search memory or imported sources, and recover the next action or recent changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samrusani/alicememory/alice-memory
Install

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.

Any agent
npx skills add samrusani/AliceMemory --skill alice-memory
Clone the repo
git clone --depth 1 https://github.com/samrusani/AliceMemory

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for alice-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/samrusani/alicememory/alice-memory/github.svg)](https://agentmods.dev/skills/samrusani/alicememory/alice-memory)
Your own site
<a href="https://agentmods.dev/skills/samrusani/alicememory/alice-memory"><img src="https://agentmods.dev/badge/skills/samrusani/alicememory/alice-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for alice-memory

Your own site · 80×15
<a href="https://agentmods.dev/skills/samrusani/alicememory/alice-memory"><img src="https://agentmods.dev/badge/skills/samrusani/alicememory/alice-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00739
Opus 5 $0.00014 $0.00369
Sonnet 5 $0.00006 $0.00148
Haiku 4.5 $0.00003 $0.00074

Measured 8d ago against content hash 9bab37724a80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

alice-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 8d 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.

agent-skills/hermes/alice-memory/SKILL.md · 65 lines

What it actually says

Hermes Alice Memory Skill

Use Alice as the user's durable local memory and continuity layer.

Default loop: remember, recall, continue.

  1. Call alice_memory_commit whenever you learn a durable fact worth keeping, including when the user has not asked you to remember it. It is the write verb for ordinary memory and what it records is immediately recallable.
  2. Call alice_recall to search memory and imported sources.
  3. Call alice_resume to pick work back up: last decision, next action, open loops, recent changes.

alice_capture and alice_context_pack are full-surface tools. Use them only when the server lists them. Capture stores a source; its passages come back from alice_recall under sources, as material to read and quote rather than as facts Alice asserts. Candidates stay unsearchable until a reviewer promotes them. Import is a source. Commit is a fact. Print the receipt field after a capture or commit so the user sees what was stored. Do not tell the user they must clear a review queue before a note is usable.

Your host may prefix these tool names with the server name. Read the names from the host's own tool list rather than assuming the bare form.

Rules:

  • never directly mutate trusted memory or the database
  • never bypass Alice policy
  • never request sensitive domains unless needed and allowed

Default identity:

{"agent_id":"hermes","agent_type":"personal_assistant","permission_profile":"trusted_local_agent","project_scope":[]}

Default scope is broad but policy-filtered. Avoid health, family, spiritual, legal, financial, and regulated unless the user explicitly enables that scope.

Good ambient commit, nobody asked for this one:

{"title":"Preferred daily planning format","canonical_text":"The user prefers daily planning summaries with decisions, blockers, and next actions.","domain":"personal","sensitivity":"private","confidence":0.84}

Good explicit commit, the user said to remember it:

{"agent_id":"hermes","agent_type":"personal_assistant","permission_profile":"trusted_local_agent","title":"Preferred daily planning format","canonical_text":"The user prefers daily planning summaries with decisions, blockers, and next actions.","domain":"personal","sensitivity":"private","confidence":0.93,"source_type":"direct_user_instruction"}

title and canonical_text are the only required fields. Everything else is optional, and any field not in the server's tools/list schema is rejected outright rather than ignored.

If Alice returns confirmation_required, show the proposed text and, only after the user confirms, call alice_memory_manage with action: "confirm" and the confirmation_id Alice returned (full-surface). If Alice returns review_required, do not tell the user to clear a review queue.

Bad commit, too low confidence to be worth storing:

{"title":"Possible reporting preference","canonical_text":"The user might dislike long reports.","confidence":0.31}

See docs/alpha/hermes-skill.md for full recipes.

Changes

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.

  1. 8d ago First seen · 65 lines · 28 tokens per session scan A 9bab37724a80

Subscribe to this mod's changes

alice-memory is a skill published in the GitHub repository samrusani/AliceMemory (3 stars, last pushed 12d ago), licensed MIT. It adds 28 tokens to every session and 739 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.