claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Compressed memory format for Claude Code. Up to 75% token compression at 100% decode accuracy.
Plugin sigil from marketplace sigil in khaosdoctor/sigil. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
decodeDecode a Sigil-compressed snippet back into plain prose. Use when the user wants to verify what a Sigil entry means, or when reading memory entries that need human-readable explanation.
doctorDiagnose the health of Sigil memories. Checks format validity, duplicates, stale entries, and compression opportunities.
encodeEncode plain prose into Sigil compressed format without saving. Use when the user wants to preview how something would look in Sigil, or to test compression before committing.
initMigrate all existing memory files to Sigil compressed format. Discovers, inventories, compresses, and cleans up memory across all scopes.
purgeRemove invalid and duplicate entries from Sigil memory. Shows a dry run first, then asks for confirmation before writing.
recallSilently load and internalize memories at session start. TRIGGER: beginning of a new conversation, or when the user says /recall, 'what do you remember', 'recall memories', or 'load context'. Invoke this ONCE at the very start of each session, before doing any work.
rememberSave a memory in Sigil compressed format. TRIGGER: user says /remember, 'remember this', 'keep this in mind', 'note that', 'don't forget', or similar. Also invoke proactively when you notice something worth remembering long-term (feedback, corrections, project context, references).
statsShow compression statistics for all Sigil memory files. Reports total entries, tokens, domain breakdown, and estimated savings vs prose.
wrap-upReview the current session and save anything worth remembering long-term. Run at session end to capture feedback, decisions, project context, and references.
bash ${SIGIL_ROOT:-${CLAUDE_PLUGIN_ROOT}}/bin/session-start.sh
bash ${SIGIL_ROOT:-${CLAUDE_PLUGIN_ROOT}}/bin/recall.sh
bash ${SIGIL_ROOT:-${CLAUDE_PLUGIN_ROOT}}/hooks/precompact.sh
bash ${SIGIL_ROOT:-${CLAUDE_PLUGIN_ROOT}}/hooks/sigil-checkpoint.sh
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.