Developer links
HolaOS
With over 6,500 GitHub stars, HolaOS bills itself as an "open agent computer" that reimagines the traditional operating system as a shared workspace where humans and AI agents collaborate across files, browsers, and 100+ integrated tools simultaneously. Unlike chat-only interfaces, HolaOS places live application UIs—Notion-style editors, browsers, custom workspace apps—side by side with the agent conversation, so operators always see what agents are doing and can intervene at any moment. The persistent memory system stores workspace knowledge locally as Markdown files and embedded vectors via SQLite vec, enabling RAG-powered recall that survives session boundaries without the typical context window bloat. Safe Session Compaction reserves roughly 70% of the model context window for fresh reasoning while folding older history into structured checkpoints that retain goals, constraints, progress, and decisions. Agents connect to Linear, GitHub, Slack, Jira, HubSpot, Gmail, and dozens more through one-click OAuth, automatically fetching relevant signals and converting scattered app data into working memory. BYOK support for Claude, GPT, and Gemini models lets operators use their own API keys at zero markup, while built-in Kimi K3 and GLM-5.2 models provide ready-to-use alternatives. Skills package reusable workflows that any agent can invoke on demand, and scheduled triggers enable autonomous digests, monitors, and reports. The runtime supports independent server deployment alongside the desktop client. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Modified Apache 2.0 licensed.
Benefits
- Persistent Agent Memory System
- Agents retain working context across sessions with local-first Markdown and SQLite vec storage, enabling RAG-powered recall without losing goals, constraints, or project decisions.
- 100+ One-Click Integrations
- Connect to GitHub, Slack, Linear, Jira, HubSpot, Gmail, Notion, and more via OAuth, automatically fetching signals and converting tool data into actionable working memory.
- Side-by-Side App Interface
- Live workspace apps run alongside agent conversations, letting operators inspect results, edit files, and take control at any moment without switching tabs or contexts.
- Bring Your Own Keys
- Use your own Claude, GPT, or Gemini API keys at zero markup, or leverage built-in Kimi K3 and GLM-5.2 models with no provider setup required.
Features
- Session Context Compression
- Safe Session Compaction reserves 70% of the model window for fresh reasoning while folding older history into structured checkpoints retaining goals, constraints, and progress.
- Reusable Agent Skills
- Package workflows into skills that any agent invokes on demand, with combos bundling multiple skills and integrations into single-install capability sets.
- Agent-Driven Browsers
- Create and manage signed-in browser profiles that agents control for browsing, clicking, extracting, and completing web-based tasks under operator oversight.
- Multi-Agent Orchestration
- Hidden sub-agents work in parallel on complex tasks while the orchestrating agent consolidates progress into one easy-to-review result for the operator.
- Scheduled Autonomous Tasks
- Run agents on schedules or triggers to produce digests, monitors, and reports that complete and file results without operator intervention.