Ross ROSS = Recommend OSS · open-source software intelligence for agents

holaboss-ai/holaOS

Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps, browser, local files — with shared memory. Any agent (Claude Code, Codex), any model, or BYOK. Set up in clicks, not months. Local-first: your data never leaves your machines. observed · 2026-08-28

github.com/holaboss-ai/holaOS · homepage · TypeScript · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

69/100

  • Activity 98
  • Release rhythm 64
  • Longevity 11

Flags: young no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 164
  • days_rel: 27
  • days_push: 12
  • n_releases_24m: 1

Full methodology

Adoption not part of the score

10925 stars · 714 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

holaOS is an open-source, local-first agentic desktop workspace built with Electron and TypeScript that lets enterprises assemble their own agent-native environment. It connects existing systems via 100+ integrations and MCP, supports any agent (Claude Code, Codex) or model with BYOK, and provides shared memory across agents while keeping data on local machines.

Use cases

  • run AI agents against my company's existing tools and integrations
  • set up an agentic workspace without months of engineering
  • connect Claude Code or Codex to my local files and chat tools
  • give multiple agents shared memory across my systems
  • keep agent workflows local so data never leaves my machines
  • build a customizable agent runtime with MCP support
  • use my own API keys with an agent desktop app

When to choose

  • you want a local-first, privacy-conscious agent workspace where data stays on your machines
  • you need to connect many existing systems (100+ integrations, MCP) to AI agents quickly
  • you want model and agent flexibility, including BYOK and Claude Code/Codex support
  • you're an enterprise that wants to customize and self-host an agentic platform

When to avoid

  • you need a fully managed cloud SaaS with zero local setup
  • you require a permissively licensed codebase for commercial redistribution (license is Modified Apache 2.0, not standard)
  • you only need a simple chatbot without integrations or workspace features
  • you need a lightweight CLI-only agent harness rather than a desktop application

Facets

application · maturity active

agent-framework mcp chat-interface workflow-automation plugin-system developer-tools large-language-models developer-tools self-hosted windows agentic-workspace agent-os local-first byok integrations shared-memory claude-code codex mcp-runtime enterprise-agents ai-agents automation macos linux electron desktop typescript

10 sources

Member repositories

RepositoryRoleHealth v2
holaboss-ai/holaOSmain69

For agents

markdown · JSON · MCP: product_card(name="holaboss-ai/holaOS")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem