Home | Chaos Cypher

Core Intelligence

GraphRAG Search

Find answers that span multiple documents. Fuses knowledge graph traversal with vector search using Personalized PageRank and Reciprocal Rank Fusion — plus keyword, semantic, and hybrid search modes.

Knowledge Graph

Extract entities and relationships from your documents. Explore connections through an interactive graph canvas with search, filtering, and templates.

AI Chat with RAG

Ask questions about your documents with retrieval-augmented generation. Get cited answers grounded in your actual content, scoped to specific sources or the full database.

Data Foundation

Quality Analysis

Score the richness and completeness of your knowledge graph on a 0-100 scale. Detailed breakdowns by entity quality, relationship density, connectivity, and coverage — identify weak sources and guide improvement.

Document Processing

Upload PDFs, Word documents, web pages, and more. Automatic chunking, embedding, and RAG-ready indexing in seconds.

Multi-LLM Support

Connect to Ollama, OpenAI, Anthropic, or Gemini. Run fully local with Ollama or use cloud providers — switch between them with a single config change. Embeddings run locally on the CPU with no API keys needed.

Automation & Integration

Automations

Build multi-step workflows with triggers, conditional logic, and a visual workflow builder. Execute automated knowledge extraction pipelines.

MCP Server

Connect Claude Desktop, Cursor, ChatGPT, and other AI assistants directly to your knowledge graph via the Model Context Protocol. 30 tools for search, traversal, and graph building.

Plugin System

Extend Chaos Cypher with custom document loaders, extraction domains, and workflow tools. Drop a Python file into the plugins directory — no registration needed.

Lexicon Hub

Share, discover, and reuse knowledge packages from the community

Pull

Download templates, entities, and workflows published by others. Jumpstart your project with community-built knowledge graphs.

chaoscypher pull john/medical-ontology

Community Registry

Browse packages by keyword, author, or domain. Templates, knowledge graphs, and workflows — shared by the community, ready to import.

Browse Packages

Publish

Export your extracted knowledge as a CCX package and share it with the community. Public or private — your choice.

chaoscypher push my-knowledge.ccx

Ecosystem

Integrations

MCPREST APIPython SDKCLI

LLM Providers

OllamaAnthropicGeminiOpenAI

Supported Formats

Text

PDFDOCXCSVJSONHTMLMD+8 more

Audio

MP3WAVFLACOGGM4A+2 more

Video

MP4MKVMOVWebMAVI+2 more

Images

JPGPNGWebPGIFTIFFBMP

Archives

ZIPTAR.GZany content

Get Started

Pick the path that fits how you work:

Docker

Full web UI — upload, search, chat, explore the graph

docker pull ghcr.io/chaoscypherinc/chaoscypher:latest
docker run --rm -p 80:80 ghcr.io/chaoscypherinc/chaoscypher:latest

Web UI with graph canvas
REST API + queue monitor
Background workers
Hot reload for development

Full installation guide

CLI

Terminal-first — process documents and query your graph from the shell

pip install chaoscypher
chaoscypher setup
chaoscypher source add paper.pdf

Setup wizard for LLM config
Add, search, and manage sources
Graph and template operations
Interactive chat sessions

CLI reference

Python Package

Integrate into your own code — extract, search, build graphs programmatically

from chaoscypher_core import ChaosCypher

result = ChaosCypher.extract_sync("paper.pdf")
print(result.model_dump_json(indent=2))

Zero boilerplate, one-liner API
Pydantic models throughout
Sync and async interfaces
Embeddable Engine class

Developer quickstart

Architecture

Modular monorepo — each package owns a single concern and communicates through typed interfaces. The Core library is framework-agnostic, so it runs identically behind the API, inside workers, or embedded in your own scripts.

Learn more about the architecture

Start Building

Open source. Run locally or in the cloud. No API keys needed to get started.

Get Started Join Discussions