Back to browse
GitHub Repository

the agent that never starts from zero

42 starsPython

Open-source desktop agent that uses a local folder as its memory

by 10keane·Jul 7, 2026·2 points·0 comments

AI Analysis

●●SolidBig BrainShip ItSolve My Problem

Agent memory stored as editable markdown files instead of hidden vector databases.

Strengths
  • Explicit memory files let users audit and edit agent knowledge directly.
  • Local-first folder structure avoids vendor lock-in and hidden context storage.
  • Approval presets and sandboxing add safety to autonomous file modifications.
Weaknesses
  • Alpha status with few stars suggests unproven stability and edge cases.
  • Relies on external LLM APIs despite local storage, limiting offline capabilities.
Target Audience

Developers building with AI agents, local-first productivity users

Similar To

Cursor · Claude Desktop · OpenInterpreter

Post Description

Orbital is an open-source desktop agent runtime that lives in a local folder on your desktop, with sandbox, approval presets and sub-agent support.

Think of it as Obsidian + Hermes in one native app, with extra features.

The key is that it uses the folder as its own wiki to keep track of your work and artifacts, so it stays at the tip of your work without needing you to explain twice.

Some important features:

1. Long-term memory: Orbital stores all memory as .md files locally. It uses a two-tier approach. Tier 1 is a few files injected directly into the system prompt. Among them is an index.md, which is how the agent remembers what the tier 2 files are and when/how to use them. You can open the folder and read everything it knows.

2. Project as sandbox: You set up a "project" in a local folder — same idea as a Claude/ChatGPT project. But the agent can create, update and delete project files when needed (you can set it to ask for your approval first). The agent's shell commands are restricted to a sandbox. Seatbelt on macOS, a separate user account on Windows

3. Sub-agent support: It can directly dispatch Claude Code (official Agent SDK) and Codex (App Server protocol) as sub-agents, using your existing subscription. Parallel agent fan-out is also supported.

Other basic features include cron jobs, task queue, budget control, etc.

Solo builder. Built in 1 month. But it took me 3 months to dogfood and stabilize. Now I can proudly say I use it every day and it has replaced my original Claude workflow.

One example I can share is orbital-marketing. I set up this project with all my architecture and product design files, plus a cron job that monitors competitor features daily, and I use the artifacts to adjust my product roadmap. It's also my central hub for content creation like video scripts as the agent needs to understand the nuances between Orbital and other products. Another project is orbital-feature-log, which helps me write specs against the repo, dispatch Claude Code to investigate the implementation plan and Codex to implement. Orbital does the final check.

It comes with a UI. You can download it and set it up within 3 minutes.

release link: mac:https://github.com/zqiren/Orbital/releases/download/v0.7.1/O... windows:https://github.com/zqiren/Orbital/releases/download/v0.7.1/O...

Similar Projects