alex-clawmemorySovereign agent memory engine — self-hosted, privacy-first SQLite store with LLM-based fact extraction (GLM-4.7), hybrid BM25+vector search, contradiction re...
Install via ClawdBot CLI:
clawdbot install bowen31337/alex-clawmemoryGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:7437/factsCalls external URL not in known-safe list
https://github.com/clawinfra/clawmemoryAI Analysis
The skill operates a local server on localhost:7437 and stores data in a local SQLite file, with all documented endpoints serving this stated purpose. The external GitHub URL is for source code reference, not a runtime data sink. No evidence of credential harvesting, hidden instructions, or obfuscation.
Audited Apr 17, 2026 · audit v1.0
Generated Apr 18, 2026
Developers building personal AI assistants can use ClawMemory to store user preferences, habits, and facts locally, enabling personalized responses without cloud dependency. It integrates with OpenClaw for automatic memory capture and recall during conversations, enhancing user experience with persistent context.
Healthcare providers can deploy ClawMemory in on-premise servers to securely store patient preferences, medical history snippets, and treatment plans in a privacy-first manner. The hybrid search allows quick retrieval of relevant information during consultations, while contradiction resolution ensures data consistency.
Companies can integrate ClawMemory into customer support bots to remember past interactions, user issues, and preferences across sessions. The self-hosted SQLite store ensures data sovereignty, and the OpenClaw plugin auto-injects context to improve response accuracy without external APIs.
Educational platforms can use ClawMemory to track student learning progress, preferences for subjects, and skill levels in a structured way. Tutors or AI systems can query memory to adapt lessons, and the decay settings help prioritize recent learning data for dynamic curriculum adjustments.
Law firms or compliance teams can utilize ClawMemory to store and search through structured facts from case notes, client preferences, and regulatory requirements. The local storage ensures confidentiality, and the fact extraction from conversations aids in automating documentation processes.
Offer paid consulting, customization, and support services for organizations deploying ClawMemory in their AI systems. Revenue comes from setup fees, ongoing maintenance contracts, and training sessions for integrating the skill into existing workflows.
Provide a hosted version of ClawMemory with additional features like advanced analytics, multi-user support, and cloud sync options (e.g., Turso integration). Charge based on usage tiers, storage limits, or number of API calls, targeting businesses needing scalable memory solutions.
Develop and sell premium plugins or integrations for ClawMemory with popular platforms like Slack, Discord, or CRM systems. Revenue is generated through one-time purchases or licensing fees, focusing on extending functionality for specific industry needs.
💬 Integration Tip
Ensure Ollama is running for optimal vector search; start with default config and adjust decay settings based on use case longevity to balance memory relevance and storage.
Scored Apr 19, 2026
Structured reasoning through sequential thinking — break complex problems into steps, solve each independently, verify consistency, synthesize conclusions wi...
LLM-driven epistemic reasoning engine. Evaluates claims against evidence, outputs calibrated confidence and structured belief state (VERIFIED/CONTESTED/UNCER...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括:(1) 滑动窗口式短期记忆,(2) 自动摘要生成中期记忆,(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
Store secrets, long-term memory, daily logs, and anything custom in your Convex backend instead of local files