AIAny
GitHub

Ever Gauzy

Provides a full‑stack business management suite (ERP/CRM/HRM) with project and time tracking — organized as a TypeScript monorepo with web UI, Electron desktop clients, and optional self‑hosted API/server.

Introduction

Most business management platforms split UI, backend, and integrations across separate projects; this codebase intentionally bundles them into a single TypeScript monorepo and extends the stack with an MCP server so AI assistants can act on business data.

What Sets It Apart
  • Monorepo-first architecture: frontend (Angular), backend (NestJS), desktop clients (Electron) and auxiliary apps (timer, server, agent) live in one repository, reducing integration drift and easing cross-app refactors.
  • Built-in AI integration: an MCP (Model Context Protocol) server and auth service enable AI assistants to invoke 300+ tools and interact with the platform via OAuth, WebSocket/REST or stdio transports — designed for both remote and self‑hosted deployments.
  • Full business coverage: includes ERP/CRM/HRM/ATS/PM features plus time/activity tracking and billing workflows, making it a single codebase for many operational needs.
  • Deployment flexibility: supports SQLite for quick local setups or PostgreSQL/Redis for production, and offers both server and desktop packaged modes.
Who It's For & Trade-offs

Great fit if you maintain or self‑host business software for small-to-medium organizations and want a single, TypeScript‑centric stack that already integrates AI tooling. It’s also useful for teams that need both desktop time-tracking agents and a server-side API. Look elsewhere if you need a permissive license for embedding in proprietary products (this project is AGPL-3.0), or if you prefer a narrow SaaS product rather than a broad, self‑hostable platform — the codebase’s scope and modularity add complexity and operational overhead compared with single-purpose apps.

Additional notes: active monorepo with thousands of releases and many contributors; primary language TypeScript; started in 2019. The MCP components are a key differentiator for teams exploring AI-driven automation of business workflows.

Information

  • Websitegithub.com
  • Organizationsever-co
  • Authorsrahul-rocket, evereq, adkif, AlexTasev, ckhandla94, samuelmbabhazi, YavorGrancharov, syns2191, rmagon, GloireMutaliko21
  • Published date2019/06/02

Categories

More Items

GitHub
AI Infra2026

Compresses tool outputs, logs, files and RAG chunks locally before they reach the LLM to reduce token usage while caching originals for on-demand retrieval. Provides proxy/library/wrap modes, JSON- and code-aware compressors, and reversible compression.

GitHub

Connects Blender to any LLM so models can inspect, create, and modify 3D scenes via a socket-based Model Context Protocol (MCP) server; supports object manipulation, materials, renders, asset import, and executing Blender Python.

GitHub
AI Infra2026

Indexes mixed-format folders locally into a zero-config, Elasticsearch-compatible search engine offering keyword, semantic, vector and hybrid retrieval. Embeds on ingest, provides per-agent namespaced memory and AST-aware code indexing in a single static binary with no external embedding key.