Sign InOpen Brain
GitHubGitHub RepoNeeds Review

holaboss-ai/holaOS

holaOS is a local-first workspace where Claude Code, Codex, and a built-in agent share memory, tools, skills, and apps. It reduces setup duplication, but its modified Apache license adds distribution conditions.

GitHub
Open Source Open MarkdownOpen JSON
Source Summary

holaOS runs Claude Code, Codex, and its own agent in one local-first workspace with shared memory, tools, skills, and apps. The repository claims **100+ integrations and MCP**, supports BYOK, and stores memory as locally editable files.

Practical Implication

Builders switching between agents could centralize project history and reusable workflows instead of recreating context per client. The workspace also exposes browser control, scheduled automation, live app surfaces, and deliverables such as spreadsheets and slides.

Agent-Ready Context
holaOS runs Claude Code, Codex, and its own agent in one local-first workspace with shared memory, tools, skills, and apps. The repository claims **100+ integrations and MCP**, supports BYOK, and stores memory as locally editable files.

Builders switching between agents could centralize project history and reusable workflows instead of recreating context per client. The workspace also exposes browser control, scheduled automation, live app surfaces, and deliverables such as spreadsheets and slides.

The project had **769 stars** in the supplied snapshot, so maturity is not established by the material. Its **modified Apache 2.0** license adds commercial-distribution and branding conditions, and the one-line installer executes a remote shell script that merits inspection first.
Connected Context · Feed7 Judgment

This shifts portability from sharing individual skills or model endpoints toward a single local workspace where several agents inherit the same memory, tools, and apps. It could reduce repeated context setup, but the supplied evidence does not establish maturity; its broad integration surface, installer, and modified license add governance, security, and distribution questions.

Introducing Agent PluginsAgent Plugins standardizes portable components, while holaOS attempts to supply the broader shared runtime—memory, apps, automation, and UI—that the packaging contract explicitly leaves to clients.Effective harnesses for long-running agentsholaOS generalizes persistent context across agents, whereas Anthropic’s pattern grounds continuity in explicit progress files, feature state, verification, and git commits.stablyai/orcaBoth consolidate multiple coding agents into one workspace, but Orca emphasizes worktree isolation and supervision while holaOS emphasizes shared memory, integrations, and reusable capabilities.Alishahryar1/free-claude-codeFree Claude Code broadens model choice through a proxy; holaOS instead broadens agent-client coordination, shifting the centralization point from model routing to workspace context and tools.
Context Map
toolscoding#coding-agents#agent-memory#mcp
Uncertainty
The project had **769 stars** in the supplied snapshot, so maturity is not established by the material. Its **modified Apache 2.0** license adds commercial-distribution and branding conditions, and the one-line installer executes a remote shell script that merits inspection first.