EthosPowerAIApproach
The open-source stack
Every platform below is open-source and runs on your own infrastructure, and that is a governance decision rather than a preference: your compliance team can read the code, trace where the data goes and sign off without taking a vendor's word for it, and you can leave at any time with the code in hand. Technology is the third and minor step of the work. The method that decides whether any of this gets deployed at all is on the approach page; this page exists so that the third step, when it comes, is built from parts nobody can withdraw.
On this page
AnythingLLM
Private AI Document Intelligence
An all-in-one AI application for private document chat, RAG, and AI agents. Run locally or self-hosted with complete data control.
Explore AnythingLLM
Click on any capability to discover how AnythingLLM can transform your document workflows with private AI.
All capabilities work together — embed documents, chat with local or cloud LLMs, and let AI agents automate your workflows.
Ollama
Run LLMs Locally
The simplest way to run open-source large language models on your own hardware with complete privacy. 100+ models available.
Click on any feature node to explore Ollama's capabilities
n8n
Fair-Code Workflow Automation
A powerful workflow automation platform with 400+ integrations, native AI capabilities, and full self-hosting options.
Click on any feature node to explore n8n's capabilities
Nextcloud
Self-Hosted Collaboration Platform
Privacy-focused file sharing and collaboration with AI assistant capabilities. End-to-end encryption and full data sovereignty.
Click on any app node to explore Nextcloud's capabilities
ERPNext
Open Source ERP System
Comprehensive business management platform for accounting, inventory, HR, CRM, and manufacturing. No per-user licensing fees.
Explore ERPNext Modules
Click on any module in the diagram to see detailed information about its features and business value.
All modules work together seamlessly — changes in one automatically update others in real-time.
OpenProject
Open Source Project Management
Leading open source project management software with Gantt charts, agile boards, time tracking, and team collaboration features.
Click on any feature node to explore OpenProject's capabilities
Qdrant
High-Performance Vector Database
Open-source, Rust-based vector database optimized for semantic search, RAG applications, and AI memory systems.
Click on any feature node to explore Qdrant's capabilities
Neo4j
Native Graph Database
Leading graph database for knowledge graphs, AI memory systems, and relationship-rich connected data.
Click on any feature node to explore Neo4j's capabilities
ChromaDB
AI-Native Embedding Database
Open-source vector database for embeddings with simple API, local development, and seamless LLM integration.
Click on any feature node to explore ChromaDB's capabilities
Playwright
AI-Powered Browser Automation
Microsoft's browser automation framework with AI-powered test generation, MCP integration, and cross-browser testing.
Click on any feature node to explore Playwright's capabilities
Firecrawl
LLM-Ready Web Scraping
Turn any website into clean, structured markdown for LLM consumption with JavaScript rendering and semantic chunking.
Click on any feature node to explore Firecrawl's capabilities
Postiz
Social Media Management
Self-hosted social media scheduling with AI content generation. Open-source alternative to Buffer and Hootsuite.
Click on any feature node to explore Postiz's capabilities
Plane
Modern Project Tracking
Open-source project management with GitHub-style issues, sprints, and cycles. Self-hosted Jira alternative.
Click on any feature node to explore Plane's capabilities
Task Master AI
PRD-to-Tasks Decomposition
AI-powered task management that converts PRDs into structured, actionable task hierarchies with MCP integration.
Click on any feature node to explore Task Master's capabilities
Msty
Local AI Interface
Beautiful desktop app for running local LLMs with GPU acceleration, Shadow Personas, and MCP integration.
Click on any feature node to explore Msty's capabilities
SmythOS
No-Code AI Agents
Visual workflow builder for creating intelligent AI agents with drag-and-drop development and enterprise integration.
Click on any feature node to explore SmythOS's capabilities
LibreChat
Open Source ChatGPT Alternative
Self-hosted AI chat with multi-LLM support, agents, memory, and MCP integration.
Click on any feature node to explore LibreChat's capabilities
Open WebUI
Self-Hosted LLM Interface
Privacy-focused web interface for local and cloud LLMs with seamless Ollama integration.
Click on any feature node to explore Open WebUI's capabilities
Matrix/Element
Federated Secure Communication
Open protocol for decentralized, end-to-end encrypted chat and video conferencing.
Click on any feature node to explore Matrix/Element's capabilities
Weaviate
AI-Native Vector Database
Open-source vector database with hybrid search, built-in vectorization, and AI agents.
Click on any feature node to explore Weaviate's capabilities
Windmill
Code-First Workflow Engine
Open-source serverless runtime for scripts, flows, and apps in TypeScript, Python, Go, Bash, and SQL. The orchestrator I reach for when n8n's no-code surface starts fighting me.
Click on any feature node to explore Windmill's capabilities
Second Brain Pattern
Voice → Graph, Vectors, CRM → Human Gates
A pattern I run for my own two brands and adapt for clients: capture a voice note in Telegram, transcribe it with Whisper on a local GPU, extract entities with a local model, and write the result to a Neo4j graph, a Qdrant vector store and Frappe CRM with cross-references in each direction. Two crawlers prospect for leads but cannot write to the CRM; a person approves every prospect, every outbound email and every published episode. Windmill runs the cron and the gates, Listmonk sends what a thumb has approved.
Click on any feature node to explore Second Brain's capabilities
DBOS
Durable Execution on Postgres
A lightweight library that turns ordinary Python or TypeScript functions into crash-safe, replayable workflows backed by Postgres. Step outputs are checkpointed; a process restart resumes from the last completed step instead of re-running side effects. The foundation under the Dark Software Factory.
Click on any feature node to explore DBOS's capabilities
Milvus
Scalable Vector Database
Open-source vector database for trillion-scale similarity search with hybrid queries.
Click on any feature node to explore Milvus's capabilities
Frappe Learning
Open-Source Learning Management System
A self-hostable LMS built on the Frappe Framework — structured courses with chapters and lessons, auto-graded quizzes, manual-review assignments, embedded programming exercises, learner batches with Zoom live classes, completion certificates and a built-in job board. I provide setup, configuration and integration so you keep full control of your learners' data.
Click on any feature node to explore Frappe Learning's capabilities
DeerFlow
Long-Horizon Research and Coding Agent Harness
DeerFlow is ByteDance's MIT-licensed agent harness for research and coding tasks that run for minutes or hours, built on LangGraph with sub-agents, skills, long-term memory and pluggable sandboxes. I self-host it with Docker Compose as a gateway, a frontend and Redis, and connect it to my own models and tools. I provide setup, configuration and integration.
Click on any feature node to explore DeerFlow's capabilities
Honcho
Memory Infrastructure for Stateful Agents
Honcho, from Plastic Labs, is AGPL-3.0 memory infrastructure: an API server stores workspaces, peers, sessions and messages, and a background deriver reasons over them to build representations an agent can query. I self-host it on PostgreSQL with pgvector and wire it in through the Python or TypeScript SDK. I provide setup, configuration and integration.
Click on any feature node to explore Honcho's capabilities
Hermes Agent
Self-Improving Agent with Skills and Persistent Memory
Hermes Agent, from Nous Research, is an MIT-licensed agent that runs as a terminal UI, a CLI or a messaging gateway, writes its own procedural skills after complex tasks and keeps memory across sessions. I run it on my own hardware with the model provider of my choice, behind a LiteLLM proxy where that helps. I provide setup, configuration and integration.
Click on any feature node to explore Hermes Agent's capabilities
Graphiti
Temporal Knowledge Graphs for Agent Memory
Graphiti, from Zep, is an Apache-2.0 Python framework that turns a stream of episodes into a bi-temporal knowledge graph, recording when each fact became true and when it was superseded, and retrieves with a mix of embeddings, BM25 and graph traversal. I self-host it against my own Neo4j (FalkorDB and Neptune are also supported) and expose it to agents through its optional MCP server. I provide setup, configuration and integration.
Click on any feature node to explore Graphiti's capabilities
LiteLLM
OpenAI-Compatible Gateway to 100+ Model Providers
LiteLLM is a proxy and Python SDK that gives one OpenAI-compatible endpoint across more than a hundred providers, with routing, fallbacks, virtual keys, spend tracking and logging callbacks. The core is MIT-licensed (the repository's enterprise directory carries a separate licence), and I self-host the proxy with Docker and PostgreSQL as the routing layer in front of local and hosted models. I provide setup, configuration and integration.
Click on any feature node to explore LiteLLM's capabilities
Listmonk
Self-Hosted Newsletter and Mailing List Manager
Listmonk is an AGPL-3.0 newsletter and mailing-list manager shipped as a single Go binary over PostgreSQL, with lists, campaigns, templates, bounce processing and a transactional email API. I run it on my own VPS as the email layer behind my lead-capture forms and this site's blog subscriptions. I provide setup, configuration and integration.
Click on any feature node to explore Listmonk's capabilities
OpenCode
Open-Source AI Coding Agent for the Terminal
OpenCode is an MIT-licensed coding agent with a terminal UI, a plan agent that only reads and a build agent that edits, language-server support and a client/server split that also runs headless as an HTTP server. I self-host it as a service on my own machines, pointed at the model provider of my choice, with optional MCP servers for extra tools. I provide setup, configuration and integration.
Click on any feature node to explore OpenCode's capabilities
Ready to deploy this on your infrastructure?
I'll help you evaluate, deploy, and configure the right tools for your organisation's business logic — not the other way round.