brainxVector memory engine with PostgreSQL + pgvector + OpenAI embeddings. Stores, searches, and injects contextual memories into LLM prompts. Includes auto-inject...
Install via ClawdBot CLI:
clawdbot install mdx2025/brainxGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
process.env.OPENAIHardcoded API key or token pattern found in skill definition
AKIAIOSFODNN...Potentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
https://github.com/Mdx2025/brainx-v5Generated Mar 20, 2026
BrainX enables AI support agents to recall past customer interactions, preferences, and resolved issues across sessions. It automatically injects relevant context at startup, allowing agents to provide personalized, consistent support without manual briefing. This reduces repetition and improves resolution times by leveraging shared learnings from all agents.
In project management, BrainX stores decisions, learnings, and gotchas from past projects as vectorized memories. It semantically searches and injects this context into LLM prompts to guide new projects, avoiding past mistakes and promoting best practices. The system automatically deduplicates and prioritizes memories based on usage for efficient retrieval.
BrainX helps AI agents in healthcare remember regulatory updates, compliance protocols, and patient interaction guidelines across sessions. It detects contradictions in memories and supersedes outdated information, ensuring agents provide accurate, up-to-date advice while automatically scrubbing PII for data security.
For AI tutoring systems, BrainX maintains persistent memories of student progress, learning patterns, and effective teaching strategies. It uses semantic search to retrieve relevant past interactions and injects them into prompts, enabling personalized lesson plans and adaptive feedback without manual context setup.
BrainX supports AI agents in finance by storing market insights, investment decisions, and risk assessments as vector embeddings. It automatically injects context at session start, allowing agents to analyze trends and make informed recommendations based on historical data, with anti-contradiction features to keep information accurate.
Offer BrainX as a cloud-based service with tiered pricing based on memory storage, agent count, and features like auto-injection hooks. Revenue comes from monthly subscriptions, targeting businesses needing persistent AI memory without infrastructure management. Upsell options include premium support and custom integrations.
Sell perpetual licenses for on-premise deployment, including customization, training, and support services. Revenue is generated through one-time license fees and ongoing maintenance contracts, ideal for large organizations with strict data privacy requirements or existing PostgreSQL setups.
Provide a free tier with basic memory storage and search, monetizing through paid upgrades for advanced features like cross-agent learning, disaster recovery, and higher usage limits. Revenue streams include subscription upgrades and pay-as-you-go options for additional capacity.
💬 Integration Tip
Ensure PostgreSQL with pgvector is set up and DATABASE_URL is configured; test the auto-injection hook in a staging environment before production to verify context injection works as expected.
Scored Apr 19, 2026
Uses known external API (expected, informational)
api.openai.comAI Analysis
The skill's external API usage (OpenAI) is consistent with its stated purpose of generating embeddings for a memory system, and the credential pattern found appears to be a placeholder example. No evidence of hidden instructions, credential harvesting, or data exfiltration to unauthorized servers was found in the provided definition.
Audited Apr 17, 2026 · audit v1.0
Work with Obsidian vaults (plain Markdown notes) and automate via notesmd-cli.
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
LinkHut bookmark management API integration with managed OAuth. Save, organize, search, and manage bookmarks with tags, notes, and privacy settings. Use this...
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...
把一本书里沉淀的方法论蒸馏成一组原子化、可被Agent调用的skills,同时产出给人看的笔记和话术库。触发:用户说'帮我拆《XX》''把XX蒸馏成skill''distill this book into skills'时。不做书摘/读后感/作者人设角色扮演。