beever-atlas

Overview

Beever Atlas extracts atomic facts from Slack, Discord, Teams, and Mattermost conversations, deduplicates and clusters them into topic pages with citations. It features a 3-tier semantic store and graph memory system that fuels both an auto-generated LLM wiki and a QA agent accessible through the dashboard or MCP integration. The system supports 16 MCP tools for querying knowledge bases with per-agent authentication capabilities.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• ask_knowledge_base

  Ask questions about the knowledge base and get cited answers.

  Try:What are the main decisions made about the new project?Try:Who worked on feature X and when?
• get_channel_wiki

  Retrieve the auto-generated wiki for a specific channel.

  Try:Show me the wiki for the #product-design channelTry:Get the distilled knowledge from the marketing team's channel
• search_messages

  Search for specific messages or conversations across all connected platforms.

  Try:Find all messages mentioning the deadlineTry:Search for discussions about the API integration
• get_entity_graph

  Retrieve the entity graph showing relationships between people, projects, and decisions.

  Try:Show me who worked on project Y with ZTry:What decisions is person X associated with?
• list_topics

  List all identified topics in a channel's knowledge base.

  Try:What topics are covered in the engineering channel?Try:Show me all main discussion topics
• get_topic_details

  Get detailed information about a specific topic including citations.

  Try:Tell me about the topic 'user authentication'Try:What do we know about the 'budget planning' topic?
• get_citations

  Retrieve source citations for a specific fact or answer.

  Try:Show me the source for the decision to move to cloud infrastructureTry:Where did we discuss the new UI design?
• get_people_mentions

  Find all mentions of specific people across conversations.

  Try:What has been said about John's contributions?Try:Find all mentions of Sarah in the team discussions
• get_project_timeline

  Retrieve the timeline of events and decisions for a specific project.

  Try:Show me the timeline for the product launchTry:What key events happened with project X?
• get_channel_overview

  Get a high-level overview of a channel's activity and key topics.

  Try:Give me an overview of what happened in the sales channel last monthTry:Summarize the main activities in the #design channel
• get_faq

  Retrieve frequently asked questions and answers for a channel.

  Try:What are the common questions about onboarding?Try:Show me the FAQ for the customer support channel
• get_glossary

  Access the glossary of terms and their definitions from a channel.

  Try:What does 'MVP' mean in our context?Try:Show me the glossary terms from the engineering channel

Note: Inferred from the MCP server feature description and architecture diagram, which mentions '16 tools' but doesn't list them explicitly. Tool names and descriptions are based on the functionality described in the README about the knowledge ba

Comparable tools

Installation

git clone https://github.com/beever-ai/beever-atlas.git
cd beever-atlas

make demo

./atlas

{
  "mcpServers": {
    "beever-atlas": {
      "command": "npx",
      "args": ["beever-atlas-mcp"]
    }
  }
}

FAQ

What platforms does Beever Atlas support?

Beever Atlas supports Slack, Discord, Microsoft Teams, and Mattermost conversations. It can also import from files.

How many MCP tools does Beever Atlas provide?

Beever Atlas provides 16 MCP tools for querying the knowledge base with per-agent authentication capabilities.

Compare beever-atlas with