claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Structured, decision-focused memory for Claude Code sessions. Four slash commands — /opening, /closing, /report, /reopen — implement a surgical shift-handoff model so every session starts oriented instead of cold, plus a paired claude-reopen shell tool to jump back into an exact past session. Captures what was decided and why, what was rejected, implicit assumptions, where the agent struggled, and what's still open — and verifies its own claims before saving: file changes checked against git, narrative claims independently audited against the raw session transcript, and stale Do Not constraints flagged in /report.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin simple-context-memory in revans/simple-context-memory. Commands read from the repo's manifest — 1 month ago.
/simple-context-memory:closingEnd-of-session archaeology document. Captures a summary, what was built and why, alternatives rejected with forward Do-Not constraints, key discoveries as Q→A pairs, implicit assumptions made, where the agent struggled, and open questions with next steps. Saved to docs/sessions/ with a timestamp fil
/simple-context-memory:openingStart-of-session context loader. Reads session archaeology documents from docs/sessions/ to orient the agent for the current session, including pulling every checkpoint for a specific session_id in order.
/simple-context-memory:reopenFind a past Claude Code session by description or slug across docs/sessions/*.md and surface the `claude --resume <id>` command to jump back into that exact conversation.
/simple-context-memory:reportReads session documents and produces a project state report — consolidated open deferrals, Do Not constraints, standing assumptions, and fragile areas, each linked back to their source session. Always writes to docs/reports/report.md (single file, overwritten each run). Incremental by default — only
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.