Open-source TypeScript framework for rapid application development. Production-ready foundation with zero vendor lock-in and complete control over your code.

Stack: Vue 3 + Vite frontend, Express + Prisma backend, Redis for queues and caching, Docker for one-command deployment.

What comes out of the box: authentication (JWT, OAuth, Sessions, 2FA), role-based access control (RBAC with CASL), background jobs (Redis queues, Cron, Events), CMS module (content, pages, HTML cache), communications (email, WebSocket), 50+ Vue UI components.

Plugin-based architecture keeps your code isolated from the core. Core updates don’t break your customizations. Each feature lives in its own plugin module, enable or disable via config.

Built for pairing with AI coding assistants. Structured prompts generated from models and routes, strict guardrails via generated types and validators, context capsules for ChatGPT/Cursor/Claude Code, review trail with lint and tests on generated code.

Running in production for multiple projects. Self-hosted only, deploy to any VPS, cloud, or Kubernetes.

Site: https://typus.dev
Demo:

Self-hosted semantic memory system that gives AI agents persistent, searchable memory with automatic tagging. Agents store and retrieve documents by meaning, not keywords.

Built on PostgreSQL with pgvector for embedding-based search. Documents get date and source tags automatically on save. Type, project, and topic tags are inferred from similar existing documents after indexing.

Multi-workspace support for separating different projects or teams. Full document version history. CLI tool and MCP server for direct integration with Claude Code or any MCP-compatible client.

Used in production as a shared knowledge layer between 5+ AI agents working on the same projects. Agents write findings, decisions, and worklogs. Other agents search and build on that context across sessions.

Works fully offline with local ONNX embeddings. No external API calls needed for search.

GitHub: https://www.twine.net/signin

Self-hosted knowledge base platform where teams upload documents and get answers through a chat interface. Users ask questions in natural language and get responses grounded in their actual documentation, not generic AI answers.

Supports PDF, Markdown, and text documents. Semantic search finds relevant content across the entire knowledge base. Chat interface provides sourced answers with references to specific documents.

Self-hosted on Docker, all data stays on the client’s infrastructure. No external API dependencies for document storage or search. Works with Claude and other LLM providers for the chat layer.

Built for teams that need internal documentation accessible through conversation without sending sensitive content to third-party SaaS platforms.

Site: https://www.twine.net/signin

Self-hosted platform that gives each AI agent its own isolated Linux desktop with a real Chromium browser. Agents see the screen, click, type, navigate tabs. You watch them work in real time via built-in dashboard and take control when needed.

Docker-based, MCP-native. Works with Claude Code, Claude Desktop, Cursor, or any MCP-compatible client. Each desktop is a container with full isolation, no bind mounts or host access.

Features: live screenshot streaming, Chrome DevTools Protocol semantics for faster element interaction, snapshot and restore of desktop state, knowledge compilation from past sessions, human-in-the-loop control.

Around 2GB RAM per desktop, no GPU required. Runs on any Linux server or Windows with WSL2.

Site: https://screenbox.dev
GitHub: https://github.com/dklymentiev/screenbox
Demo:

Open-source workflow orchestrator for AI agents. Define multi-step processes in YAML, assign each step to a specialist agent, and run with automatic crash recovery via SQLite.

Each block in a workflow can be an LLM call (Claude, GPT, Ollama, OpenRouter) or any executable script. The orchestrator handles dependencies, data flow between blocks, and error handling. Parallel execution, conditional branching, revision loops, and tag-based routing supported.

Three execution modes: sync (CLI, wait for result), async (daemon, poll for progress), step mode (run N blocks per invocation, save state, exit).

Built-in MCP server lets you trigger workflows directly from Claude Desktop, Cursor, or Claude Code. Optional daemon mode with WebSocket for live updates.

MIT licensed. Five working examples in the repo.

GitHub: https://github.com/dklymentiev/rein-orchestrator
Demo:

Typus - https://www.twine.net/signin

Is a full-stack framework that builds complete systems from structured modules — authentication, data and content management, routing, and more - with zero boilerplate. Define your intent, and Typus scaffolds your app in minutes so you can focus on what truly matters.
Handcrafted from scratch by one developer and an AI companion - built to help others move fast and think big.

Highlights:
Plug & play modules - drop in and go.
AI-coding ready - detailed instructions for every system component.
Type-safe architecture - strong typing with predictable behavior.

Core modules included:

Backend Core - REST API, routing, middlewares (Express, TypeScript, Zod)
Frontend UI - layouts, theming, base pages (Vue 3, Vite, Tailwind)
UI Library - core components (Vue 3, Tailwind)
Database ORM - models, migrations, CRUD (Prisma, MySQL)
Queue & Tasks - background jobs, cron, multi-level tasks (Redis)
Notification System - events, websockets, email/messenger integration
2FA Auth - JWT login + TOTP 2FA
Access Control - roles, permissions, rules (CASL)
Content Manager - CMS with typed DSL
Dynamic Routing - data-driven routes (Vue Router + Express Router)
Domain Models - DSL for Database/API/UI generation
Renderer Engine - dynamic UI with DSX page renderer

My role: Full Stack Developer - from architecture design to frontend and backend implementation.