tdai-memory-suiteComplete local memory system for OpenClaw: 4-layer memory pipeline (L0→L1→L2→L3) + local vector search (nomic-embed-text) + ontology knowledge graph + Nomic...
Install via ClawdBot CLI:
clawdbot install paudyyin/tdai-memory-suiteGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"ignore all previous instructions"Potentially destructive shell commands in tool definitions
exec(Accesses system directories or attempts privilege escalation
/proc/Calls external URL not in known-safe list
https://clawhub.ai/user/paudyyinGenerated Sep 5, 2026
A support chatbot that remembers user preferences, past issues, and resolutions, offering personalized assistance. It uses the 4-layer memory pipeline to store interaction history and recall relevant context.
An assistant that helps with project management, note-taking, and scheduling, using the ontology graph to link tasks, people, and documents. L3 persona modeling enables it to adapt to the user’s working style.
An educational bot that tracks a student's learning progress, knowledge gaps, and preferences. It uses memory to tailor content and revision, and the ontology graph to map topics and skills.
A virtual health assistant that remembers patient history, symptoms, and treatment plans, providing timely reminders and support. The local memory ensures privacy and compliance.
An assistant that stores case details, legal precedents, and client preferences. The ontology graph links cases, statutes, and attorneys, enabling efficient retrieval and context-aware drafting.
Offer the memory suite as a premium feature in a conversational AI platform, charging per user or API usage. Provide tiered plans based on storage and memory extraction capacity.
License the full memory suite to enterprises that require data sovereignty and full control. Includes installation, customization, and support services.
Deploy the memory suite as part of tailored AI assistant solutions for clients, combining consulting, integration, and training. Revenue from project-based fees and ongoing support.
💬 Integration Tip
Start with the core tdai-core pipeline and local SQLite backend, then add ontology and Atlas as needed. Ensure you have the required nomic-embed-text model downloaded and configured correctly for local vector search.
Scored Sep 5, 2026
Uses known external API (expected, informational)
api.openai.comAudited Sep 5, 2026 · audit v1.0
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