claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Operational memory for long-running AI-assisted projects: a git-tracked record store, a session-start hook that loads it, and the skills that read and write it.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin atlas in HuanCheng65/atlas. 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.
atlas-bootstrapSet a project up on atlas — one starting today, or one already running for months, with or without other frameworks like Superpowers / GSD. Use ONCE per project. Use WHEN the user says "set up atlas here", "start a new project with atlas", "migrate this to atlas", or "bootstrap atlas". Creates the s
atlas-compactPeriodic maintenance pass. Three jobs — consolidating the memory records, whose one-line titles are loaded into every session and therefore have a budget; reviewing the store for records that have quietly stopped being true; and reading the scope of recent changes in the repository, which is where a
atlas-entityOperations on the record store under docs/atlas/records/ — listing, searching and auditing records, renaming one, running validate and reindex, and the one-time migration from the old D/E/Q layout. Writing a single record needs no skill; the trigger conditions and the new.py call live in using-atlas
grill-meInterview the user before non-trivial work until you reach shared understanding, then write down what was settled. Use WHENEVER the user describes a feature, task, design, refactor or experiment — seeming clarity is not a skip reason, underspecified edges are — and ALSO mid-work, when the change rea
using-atlasAuto-loaded at the start of every conversation on an atlas-enabled project (docs/atlas/ exists). Invoke IMMEDIATELY at session start, before responding to the user's first message. The session-start hook has already injected the project's state; this skill carries the rules for reading and writing t
[ -d docs/atlas/records ] || exit 0; exec python3 "${CLAUDE_PLUGIN_ROOT}/hooks/store_guard.py"
[ -d docs/atlas ] && python3 "${CLAUDE_PLUGIN_ROOT}/skills/using-atlas/scripts/session_start.py" || true
[ -d docs/atlas ] && python3 "${CLAUDE_PLUGIN_ROOT}/skills/using-atlas/scripts/session_start.py" --resume || true
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
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
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.