beever-atlas
Reduces onboarding friction and documentation debt by converting unstructured knowledge into queryable conversation-based contexts, lowering ramp time for en…
Self-hosted knowledge base that turns your team's Slack, Discord, Microsoft Teams, and Mattermost chats into a self-maintaining wiki. It extracts atomic facts from messages, deduplicates them, clusters them into topic pages with citations, and links people, decisions, and projects in a graph store. Ask questions in natural language through the dashboard, or connect Claude Code or Cursor via its MCP server (28 tools). Ships as a Docker Compose stack: backend, bot, and web services plus Weaviate, Neo4j, MongoDB, and Redis.
- Ask Claude to search your team's internal documentation wiki for deployment best practices
- Generate answers to common engineering questions by querying your organization's knowledge base
- Find relevant code examples and architectural patterns from your company's documentation library
Reduces onboarding friction and documentation debt by converting unstructured knowledge into queryable conversation-based contexts, lowering ramp time for engineers and support costs for distributed teams.
Engineering teams with fragmented documentation seeking searchable, conversational access to institutional knowledge without wiki maintenance overhead.
https://github.com/Beever-AI/beever-atlas
By Beever-AI
How to Get It
git clone https://github.com/beever-ai/beever-atlas.git && cd beever-atlas && ./atlas
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Search my team's internal documentation wiki for deployment best practices
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 441 GitHub stars; 7 contributors; last commit 6d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 441 GitHub stars; 7 contributors; last commit 6d ago; license Apache-2.0.