Resume work using the latest recorded session matching the current project directory. The skill surfaces unanswered questions first, summarizes relevant decisions and files, and provides a concrete next step while checking that records belong to the selected project.
Resume the most recent agent session for the current working directory, leading with any unanswered question. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.
Review the instructions the agent will receive before you install.
The user wants to resume work. Optional cwd override: $ARGUMENTS
memory_sessions { "project": "<current-project-id>", "limit": 20 }
Pick the most recent session whose cwd matches this project, then:
memory_recall { "query": "<session top concepts>", "project": "<current-project-id>", "limit": 10 }.
When an agent is requested, pass the same agentId to both calls.
Expected output:
Resuming 7f3a9c2 "Auth refresh rework".
Open question: should logout revoke all device tokens or just the current one?
Next step: decide revoke scope, then update auth/logout.ts.
Match the session by directory boundary, not raw prefix, so a sibling repo never gets mistaken for this one. Never invent observations for an empty session.
$ARGUMENTS is given, normalize it to absolute
(path.resolve(process.cwd(), $ARGUMENTS)); else use the cwd.memory_sessions with the exact project identifier when known, and
agentId when requested. Otherwise follow nextCursor until the matching
directory is found or pagination ends. Preserve filters between pages.
Pick the most recent session whose normalized cwd
matches by directory boundary: equality, OR cwd.startsWith(projectPath + sep),
OR projectPath.startsWith(cwd + sep). Prefer completed over abandoned.
No match: report that this project has no matching session and stop. Do not
substitute a different project's session.summary or recent conversation observations whose narrative
ends in ?.memory_recall on the top concepts, limit 10, preserving the chosen project
and agent scope. Check each result's session or
project provenance before including it; a query alone does not enforce scope.WRONG: session.cwd.startsWith(projectPath) matches /repo-a-staging when the
project is /repo-a, resuming the wrong repo's session.
RIGHT: session.cwd === projectPath || session.cwd.startsWith(projectPath + sep),
a directory-boundary check that cannot cross sibling repos.
recap, session-history, recall: same session data, broader views.See TROUBLESHOOTING.md if memory_sessions or memory_recall is not available.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Connect agentmemory to coding agents such as Claude Code and Codex while preserving existing server settings. It guides configuration, host restarts, and checks that memory tools are available and can save and retrieve information.
Explain how agentmemory stores and retrieves coding agents’ memories, including its engine, search methods, memory lifecycle, ports, and web viewer. Useful for understanding the system or planning extensions to its functions.
Set up and troubleshoot a local agentmemory server by checking MCP connections, authentication, ports, and environment settings. Understand which optional memory features require additional configuration, model downloads, or token usage before enabling them.
Understand how agentmemory automatically records tool activity, prompts, and session boundaries through hooks, actions triggered by session events. Use it to check integration setup, investigate missing records, and distinguish capture from optional summaries and context injection.
Helps agents choose the right agentmemory tool through MCP, a protocol for connecting agents to tools. It explains tool roles and points to parameter references for saving, retrieving, organizing, and maintaining stored knowledge.
Guides HTTP integration with the agentmemory server for saving and searching knowledge. It explains authentication, request conventions, and endpoint references, including how to connect systems that do not support MCP, the agent tool connection protocol.