agentmemory-history
Skill9 starsChanged 22 days agoMITView on GitHub
Read past work: resume the last session, recap recent sessions, list agent-linked commits, trace a line back to the session that wrote it, or compact the current conversation for handoff. Use when the user says "where were we", "resume", "recap", "session history", "what did we do", "why is this code here", "who wrote this", or "handoff".
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- agentmemory-agentsAGENTS.md
- agentmemory-opsSkill
- agentmemorySkill
- caveman-commitSkill
- caveman-compressSkill
- caveman-reviewSkill
- cavemanSkill
- caveman-statsSkill
- codebase-designSkill
- code-reviewSkill
- delegationSkill
- documentationSkill
- git-commitSkill
- graphifySkill
- grillingSkill
- i-have-adhdSkill
- jev-decisionSkill
- megacaveSkill
- orchestrationSkill
- plansSkill
- resolving-merge-conflictsSkill
- ultracaveSkill
The file
Files
agentmemory history
Session archaeology over agentmemory. Every workflow reads memory_sessions,
memory_recall, or memory_commits; pick the row that matches the question.
In AGENTMEMORY_TOOLS=core mode, memory_commits and memory_commit_lookup
are hidden. Use the REST fallback in ../_shared/TROUBLESHOOTING.md.
Route
| Question | Workflow |
| "where were we" / resume / handoff | references/handoff.md |
| "what have we been doing" / recap window | references/recap.md |
| "past sessions" / timeline overview | references/session-history.md |
| "why is this code here" / blame to session | references/commit-context.md |
| "what has the agent shipped" / linked commits | references/commit-history.md |
| compact this conversation for another agent | references/handoff-compact.md |
Core rules
- Match sessions to the project by directory boundary, not raw string prefix. A sibling repo is never "this project".
- A
commit: nulllookup means the commit predates session linking. Say so; do not invent intent from the diff. - Empty results are a real answer. Never narrate activity the tools did not return.
- Surface an unanswered user question first when resuming.
- Handoff documents go to the OS temp directory, never the workspace, and redact secrets.
- Cite short session ids (first 8 chars) and observation counts so the user can verify.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.