English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

holaOS: A Shared-Memory Workspace for Claude Code, Codex, and Other AI Agents

Forum topic · ✨步子哥 · 2026-08-13

Summary

holaOS is an open-source AI desktop workspace that lets multiple agents—Claude Code, Codex, and its own holaOS agent—share a single working environment with a unified, locally stored memory. Instead of replacing agents, it addresses the "agent memory silo" problem: each agent today maintains its own context, history, and tool config, forcing users to retell context when switching. holaOS keeps context, preferences, and project history as plain local files that users can read and edit, enabling debuggability, portability, and transparency. It supports MCP, offering 100+ tool integrations that any compatible agent can invoke. The project ships a BYOK mode and a bundled-model mode covering Kimi K3, GLM 5.2, GPT 5.6, Claude Opus 5, and Fable 5. Built on TypeScript and Electron under a Modified Apache 2.0 license, holaOS positions itself as agent-neutral infrastructure rather than another locked-in IDE like Cursor or Windsurf.

A Confusing Opening

If you see holaOS's GitHub description, your first reaction might be "yet another AI desktop":

> Run any agent — Claude Code, Codex — across your tools (100+ integrations + MCP), apps, browser, and files, with shared memory.

But reading carefully reveals an unusual positioning: it doesn't replace any agent; it lets multiple agents share one working environment.

This is a completely different direction from editors like Cursor or Windsurf that ship their own built-in agent.

The Core Problem: Agent Memory Silos

If you use both Claude Code and Codex daily, have you hit this:

  • Claude Code helps you refactor a module, with the full project structure in its context
  • You switch to Codex to write another feature, and it knows nothing about that refactor
  • You have to manually tell Codex what Claude Code did, or have it re-read the code
  • This is the agent memory silo problem. Each agent has its own context window, conversation history, and tool configuration. Switching agents means swapping in an "amnesic colleague."

    holaOS aims to solve exactly this. Its core promise:

    > Context, preferences, and project history live in a single shared memory — stored locally, as plain files you can read and edit.

    The keywords are shared and locally. Shared means cross-agent availability; locally means nothing is locked inside a cloud service.

    Three Design Decisions Worth Examining

    1. Agent-Neutral — No Vendor Lock-In

    holaOS does not build its own agent. Instead, Claude Code, Codex, and holaOS's bundled agent run side by side. The README states it plainly:

    > No lock-in — bring the agent you already trust.

    This aligns with the principle that "division of labor beats unification"—holaOS provides workspace infrastructure; agents do the reasoning. You won't have to rebuild your entire workflow just because you switched agents.

    2. Memory as Files, Not a Database

    holaOS stores its shared memory in local files that users can open and edit directly. This design choice is critical:

  • Debuggable: When an agent behaves oddly, you can inspect its memory files to find the cause.
  • Portable: Switching tools doesn't strand your memory.
  • Trustworthy: Users get full visibility into what the AI "remembers."
  • This contrasts with OpenAI's Memory feature, which lives in the cloud and only exposes summaries to users—never the raw data.

    3. BYOK Plus Bundled Models

    holaOS offers two modes:

  • Bundled models: One account unlocks SOTA models (Kimi K3, GLM 5.2, GPT 5.6, Claude Opus 5, Fable 5) with no API key management.
  • BYOK: Bring your own OpenAI or Anthropic key, billed to your own account.
  • This dual-track design is pragmatic—zero-friction onboarding for newcomers, full control for power users.

    Relationship with MCP

    The README mentions "100+ integrations + MCP." MCP (Model Context Protocol) is Anthropic's standardized agent-to-tool interface. holaOS's MCP support means:

  • Any MCP-compatible tool can be invoked by agents inside holaOS.
  • An MCP server you write can be used simultaneously by Claude Code, Codex, and the holaOS agent.
  • Back to the division-of-labor principle—holaOS doesn't reinvent tool protocols; it uses MCP, an emerging standard, to connect existing tools.

    A Question Worth Asking

    holaOS's positioning is clear, but one question is worth probing: what is the format of the shared memory?

    The README says "stored locally, as plain files you can read and edit" but doesn't specify the format. If it's a custom JSON, cross-tool migration still requires conversion. If it uses a standard format (for example, Markdown with frontmatter), portability is much stronger.

    The answer determines whether holaOS is "a product" or "an ecosystem." In the former case, users are locked into holaOS; in the latter, holaOS could become a de facto standard for agent workspaces.

    Comparison with macro-inc/macro

    Trending the same day was macro-inc/macro (+1,180 stars), positioned as a "unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM." Both pursue "unified workspace" but in different directions:

  • macro: Team-oriented—integrates communication, documents, CRM, and other business tools.
  • holaOS: Developer-oriented—integrates agents, MCP tools, and local files.
  • macro wants to replace Notion + Slack + Salesforce; holaOS wants to replace Cursor + Claude Desktop + various MCP hosts. Different markets, but both point to the same trend: tool fragmentation has reached the point where users can no longer tolerate it.

    Project Data

  • Repository: holaboss-ai/holaOS
  • Stars today: +380
  • Platforms: macOS, Windows, Linux
  • Tech stack: TypeScript + Electron
  • License: Modified Apache 2.0
  • Website: holaos.ai
---

*holaOS's core bet: users are tired of rebuilding their working environment for every new agent. If the bet pays off, "agent-neutral + shared memory" may become the foundational design pattern for AI workspaces.*

Tags

#ai-agents#shared-memory#claude-code#codex#model-context-protocol#developer-tools#electron#workspace

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633437