claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Memory that outlives the session, backed by a Taisce deployment you run.
Plugin taisce-memory from marketplace taisce in ensera-ai/taisce. Commands read from the repo's manifest — yesterday.
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.
taisce-contextAssemble one person's conversation history under a character budget, for a handover, a summary of what somebody has said, or when a long history has to be compacted into what a model can read. Calls the context tool on the taisce MCP server. Reads only, and needs a data subject.
taisce-freshnessCheck how far behind memory is before trusting an absence, after recording something, or when the user asks whether memory is current or whether anything is stuck. Calls the freshness tool on the taisce MCP server. Reads only.
taisce-memoryUse when the user refers to a past decision, asks "what did we decide", "why is it like this", "did we already try", treats a name as known, or when you are about to make a choice the team may already have made. Also use after a decision is reached, to record it. Backed by a Taisce deployment over M
taisce-observeRecord what was said, in the speaker's own words, when a decision is reached, a constraint is discovered the hard way, or the user corrects your understanding. Calls the observe tool on the taisce MCP server. This one writes.
taisce-recallAsk memory a question before answering one that turns on a past decision — "why is X like this", "what did we decide about Y", "did we already try Z" — or before making a choice the team may have made already, or when a name is treated as known and you do not recognise it. Calls the recall tool on t
taisce-report-feedbackReport that a recalled record looks wrong — stale, misattributed, contradicted by what the user just said — without changing what memory holds. Use when the user says memory has something wrong, or when a recall contradicts the person it is about. Calls the report_feedback tool on the taisce MCP ser
taisce-resolve-citationTurn a fact_id from a recall into the record behind it — its validity, whether it was superseded or retracted, and all of its evidence — before relying on a recalled fact for anything that matters, or when the user asks where a claim came from or whether it is still true. Calls the resolve_citation
/taisce-memory:memory-statusHow far behind is the memory, and is anything parked?
/taisce-memory:recallAsk Taisce memory what it knows, before deciding something it may already have decided.
/taisce-memory:rememberRecord something worth keeping in Taisce memory, in the user's own words.
taisceconnects to: ${user_config.endpoint}/mcp
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/session_start.py"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/capture_turn.py"
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
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
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · 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.