engramLocal associative memory graph for an OpenClaw workspace, shipped as a set of CLI scripts: engram.py (store/recall/msgctx/task ledger over SQLite+FTS+embeddings), engram-migrate.py (markdown to nodes), engram-serve.py and bq.py (optional warm daemon over a Unix socket), embeddings.py (ONNX e5 vectors), engram-backup.py (nightly SQLite backup with retention), engram-sleep.py (nightly consolidation, optional local-Ollama distillation), engram-maintenance.py and engram-hygiene.py (dedupe/orphan/archive tiering), engram-aliases.py (alias curation), engram-rewire.py (opt-in: slims MEMORY.md, adds marked cron lines, asks first), engram-uninstall.py (full revert). Task evidence strings run through the shell. No network calls except to localhost Ollama, and only if you enable it.
Install via ClawdBot CLI:
clawdbot install dannydvm/engramGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:3400/api/memoriesPotentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
http://localhost:3400/api/memoriesAI Analysis
The skill interacts with a local server (localhost:3400) for its stated purpose of persistent memory storage, which is consistent with its design and does not constitute unauthorized external data exfiltration. The 'UNSAFE_SHELL' signal appears to be a misinterpretation of example setup commands, not actual skill execution. The primary risk is local data persistence, not external transmission.
Generated Mar 22, 2026
Track client interactions, preferences, and churn risks across sessions. Store facts like contract terms, decisions on support strategies, and events such as onboarding milestones. Use semantic search to quickly recall client history before meetings.
Maintain a persistent memory of technical decisions, codebase facts, and team preferences. Store events like deployment dates and relationships between team members. Recall context-aware memories to avoid re-discussing past decisions during sprint planning.
Securely store patient preferences, treatment decisions, and appointment events in a local-first setup. Use agent scoping to isolate memories per healthcare provider while allowing global access to critical facts. Semantic search helps retrieve patient history efficiently.
Document case facts, legal decisions, and client relationships across long-term engagements. Apply memory decay to prioritize recent developments while archiving older details. Auto-extract memories from legal documents to streamline data entry.
Store research findings, hypotheses, and literature references as typed memories. Use memory relationships to link supporting or contradictory evidence. Semantic search aids in recalling relevant studies during paper writing or team discussions.
Offer tiered subscriptions for teams, with features like advanced memory relationships, higher storage limits, and priority support. Target businesses needing persistent memory for customer-facing agents or internal knowledge bases.
Provide custom setup, training, and integration with existing AI agent workflows or MCP protocols. Help clients optimize memory types and decay settings for specific use cases like healthcare or legal.
Distribute the core tool as open source (e.g., via npm) to build a community. Monetize through premium extensions like cloud sync, advanced analytics dashboards, or specialized embedding models.
💬 Integration Tip
Start by integrating the boot sequence command into agent startup scripts to load relevant memories automatically, and use the REST API for seamless embedding into existing applications.
Scored Apr 19, 2026
Audited Apr 17, 2026 · audit v1.0
Manage a personal knowledge base by adding, searching, organizing, and reviewing articles, links, and notes with tags and natural language queries.
Generate a daily work report by automatically discovering all git repositories the user worked on, collecting commit logs across all branches, and summarizin...
日记引导助手。每日写作引导、感恩日记、反思日记、晨间日记、晚间总结、周总结模板。Journal prompts for daily writing, gratitude, reflection, morning pages, evening review, weekly summary. 日记、写作、反思、感恩。
Use when maintaining RDR2 (Red Dead Redemption 2) playthrough notes — logging an acquisition ("acquired X", "got N gold bars", "finished X"), answering in-game location/crafting questions, or reviewing the notes for duplicate or stale info. Triggers on RDR2, Red Dead Redemption, playthrough, legendary animal, talisman, trinket, valerian root, gold bar, horse, weapon, berry.
Use when a sales rep already has a customer who has expressed some need (from outreach follow-up, account-landing research, customer-initiated contact, or meeting notes) and needs to structurally validate whether that need is real, urgent, whose pain it actually is, and whether it matches the team's capability — before pushing to ROI proofing or buying-intent assessment. Triggers: '验证一下这个需求是不是真的', '需求真不真', '客户说痛但我不确定', '这个客户值不值得跟', '客户说会考虑但是真的吗', '谁拍板', '现有方案是什么', '切换成本', 'need validation', 'pain point validation', 'is this a real need', 'verify customer need'. Do NOT use for: scoring leads at line-item level, building target-customer profiles, calculating ROI, overall buying-intent scoring, opportunity-stage assessment, or writing outreach/cold messages.
Microsoft OneNote integration. Manage Notebooks. Use when the user wants to interact with Microsoft OneNote data.