See the difference.
$ mindex context "How does the production deploy process work?" --compare
Vector similarity only: finds text, misses context
Continuous Delivery Pipeline builds, tests, and promotes every merge...
Container orchestration platform operates all production workloads...
3 documents found (flat list, no relationships)
Finds keywords but can't connect the dots between systems.
Similarity + Knowledge Graph + Document Connections
◆ Direct matches (semantic search)
◇ Discovered via knowledge graph
◈ Document relationships
CI pipeline triggers Kubernetes deploy via ArgoCD sync
Deploy emits canary metrics consumed by monitoring stack
Alert thresholds trigger incident runbook and auto-rollback
5 chunks · 3 connections · 5 documents read
Finds HOW systems connect, not just similar words.
Ready in 5 commands.
From zero to AI-powered knowledge base in under a minute.
$ curl -fsSL https://raw.githubusercontent.com/usemindex/cli/main/install.sh | sh$ mindex auth$ mindex mcp install claude-code$ mindex init claude-code$ mindex upload ./docs --recursive -n docsWorks with Claude Code, Cursor, Windsurf, Claude Desktop, and any MCP-compatible tool. Accepts .md, .txt, .pdf, .docx, .pptx, .xlsx, .html, .csv, .json, .xml files.
Your AI guesses instead of connecting the dots.
Your brain doesn't search by similarity. It connects ideas. Mindex works the same way: a memory layer that understands relationships, not just keywords.
Differentials
Works with Claude
Native support for Anthropic models.
Works with OpenAI
Compatible with GPT and the OpenAI API.
Pluggable via API
Simple REST API. MCP support included.
Ready in minutes
No infra to manage. Just plug and go.