claude-mem

claude-mem is an agent for coding agents from giggsoinc/raven. It costs 66 tokens per session (575 once invoked), scanned A, original, MIT.

A local session-memory system that stores project notes in Markdown files. It loads a small memory card at the start of a session and records useful information when the session ends.

In plain words
What is it for?
It is for maintaining project notes, recording sessions, extracting knowledge, and keeping a human-readable vault of ongoing work.
Why use it?
It helps an agent continue with open questions and recent project context without loading large history files or exposing secrets.

Agent

Part of the raven plugin — 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/giggsoinc/raven/claude-mem
Clone the repo
git clone --depth 1 https://github.com/giggsoinc/raven

Or install raven, the plugin that ships this one along with the rest of its 63 skills, 13 commands, 10 agents, 5 hooks, 1 MCP server.

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 claude-mem

README.md
[![agentmods](https://agentmods.dev/badge/agents/giggsoinc/raven/claude-mem.svg)](https://agentmods.dev/agents/giggsoinc/raven/claude-mem)
Your own site
<a href="https://agentmods.dev/agents/giggsoinc/raven/claude-mem"><img src="https://agentmods.dev/badge/agents/giggsoinc/raven/claude-mem.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00066 $0.00575
Opus 5 $0.00033 $0.00287
Sonnet 5 $0.00013 $0.00115
Haiku 4.5 $0.00007 $0.00057

Measured 5d ago against content hash 715fd40f442a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-mem 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 5d 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.

agents/claude-mem.md · 73 lines

What it actually says

Claude Mem — Session Memory Agent v3.0 (RavenVault)

Canonical vault: ~/RavenVault
Deprecated: AndieVault — do not write there.
Agent start: .raven/memory/CARD.md via ide-boot.py (load=1).

No secrets. No network. Local markdown only.


On Session START

  1. Ensure hub exists (writer does this too):
python3 "${CLAUDE_PROJECT_DIR:-.}/scripts/memory/ide-boot.py" 2>/dev/null \
  || python3 scripts/memory/ide-boot.py 2>/dev/null \
  || true
  1. If load=1, Read only the memory= path. Surface open questions from the card, not a vault dump.

  2. Do not load full session files or multi‑MB vault dumps.


On Session END

  1. Prefer Stop hooks (obsidian-log.py, knowledge-extract.py). If hooks did not run:
python3 scripts/obsidian-log.py </dev/null 2>/dev/null || true
python3 scripts/knowledge-extract.py --quiet 2>/dev/null || true
python3 scripts/knowledge_graph.py 2>/dev/null || true
  1. Hub rules

    • ~/RavenVault/projects/{name}.md must exist before any [[projects/{name}]] link.
    • Update Current state, Open questions, Recent sessions.
  2. Index hygiene

    • Active Projects = every file in projects/*.md.
    • Strip corrupted placeholder lines (ere_, broken fragments).
    • Prefer vault_common.rebuild_index() via obsidian-log.
  3. Optional thin local cache:

mkdir -p .raven/memory
python3 scripts/memory/ide-boot.py 2>/dev/null || true

  • Every session → [[projects/{name}]]
  • Every decision → [[projects/{name}]] + related [[concepts/…]]
  • Frontmatter type: on all notes

claude-mem v3.0 — RavenVault-only, digest-first, index hygiene.

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. 5d ago First seen · 73 lines · 66 tokens per session scan A 715fd40f442a

Subscribe to this mod's changes

claude-mem is an agent published in the GitHub repository giggsoinc/raven (5 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 575 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

context-manager

Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…

czlonkowski/n8n-mcp · 0 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

adapter_grok

Grok is an eagerly registered stock-TUI adapter. RimZ launches grok, installs passive global hooks in ${GROKHOME:-/.grok}/hooks/rimz.json, and enriches each session from its durable updates.jsonl, summary.json, signals.json, and optional events.jsonl files. ACP and provider-private billing APIs stay outside this…

rimio-ai/rimz · 0 tokens

starlight-repos-extractor

Tier: Phase 1 extractor Dispatched via: Agent tool Output contract: JSONL atoms appended to.

frankxai/Starlight-Intelligence-System · 7 tokens

portable-memory-parent-orchestrator

Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens