CMEM Pro
claudeCMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 1 MCP server · hooks
Auto-/clear when a prompt starts an unrelated task: a local ONNX classifier (no API calls) scores each prompt and splits it into a fresh session.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin new-task-split in danielrosehill/New-Task-Split. Commands read from the repo's manifest — 19 days 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.
installInstall the new-task-split hook's local model (venv + int8 ONNX from Hugging Face) and enable it. Use for "install new-task-split", "set up the split hook".
removeRemove the new-task-split hook's venv, model, config and logs. Use for "uninstall new-task-split", "remove the split hook".
toggleEnable, disable, switch shadow/split mode, set the threshold or context turns or show status of the new-task-split hook. Use for "turn off auto split", "enable split hook", "shadow mode", "split status".
trialSet up the `claudehook` test launcher, which starts one Claude Code session with new-task-split on while plain `claude` stays off. Use for "try new-task-split", "set up the test CLI", "test the split hook".
update-modelUpdate the new-task-split classifier to the newest (or a pinned) Hugging Face revision. Use for "update the split model", "new model version".
${CLAUDE_PLUGIN_ROOT}/scripts/run-hook.sh
${CLAUDE_PLUGIN_ROOT}/scripts/run-hook.sh
CMEM Pro for the Claude app - hooks stream tool use to cmem.ai and inject observations into new sessions and agents
3 skills · 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
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
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
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 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.