engram-brainPersistent long-term memory powered by knowledge graphs, ACT-R activation, and 15-phase consolidation. Remember conversations across sessions, recall relevan...
Install via ClawdBot CLI:
clawdbot install moshik21/engram-brainGrade 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:8100/api/knowledge/bootstrapCalls external URL not in known-safe list
https://github.com/Moshik21/engramUses known external API (expected, informational)
raw.githubusercontent.comAI Analysis
The skill communicates only with localhost endpoints (127.0.0.1:8100) for its memory functions, which is consistent with its purpose as a local memory system. The external GitHub references are for installation/updates only, not data transmission. No credential harvesting, hidden instructions, or obfuscation patterns were detected.
Generated May 6, 2026
Equip an AI assistant with long-term memory to remember user preferences, past conversations, and important facts across sessions. The assistant can recall context automatically, providing coherent and personalized interactions without repeated setup.
Integrate Engram into a customer support chatbot to retain conversation history and resolved issues. The system gradually builds a knowledge graph of common problems and solutions, enabling faster and more accurate responses over time.
Help researchers and analysts by storing findings, references, and insights in a temporal knowledge graph. Engram can recall relevant information from past sessions, making it easier to build upon previous work and avoid duplication.
Build an adaptive tutoring system that remembers each student's learning progress, strengths, and weaknesses. Engram's consolidation mechanism helps prioritize review of forgotten topics, personalizing the learning experience.
Use Engram to maintain context across project meetings and decisions. The assistant can recall past discussions, deadlines, and stakeholder preferences, improving consistency and decision-making in agile environments.
Offer Engram as a premium memory backend for AI assistant platforms. Charge per active user or per memory storage tier, providing persistent memory capabilities that enhance user retention.
License Engram to companies building custom AI agents or chatbots. Integrate the memory system into their product, charging a one-time integration fee plus ongoing support and updates.
Keep Engram open source to drive adoption, while offering paid support, consulting, and managed hosting for enterprises. Generate revenue through commercial licenses for proprietary modifications.
💬 Integration Tip
Start with the local SQLite backend for testing; the API endpoints are straightforward REST calls. Use 'uv tool install engram' for the quickest setup.
Scored Jun 29, 2026
Audited Apr 16, 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...
Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context duri...
Turn scattered local sources into a source-constrained evidence notebook for incident, release, and maintainer decisions.
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