1,000
stars
66
forks
4
watchers
53
prs
24
issues
63
releases
README
English · 简体中文 Codex hits its usage limit mid-task. Claude Code picks up in the same conversation. Codex stops at its usage limit. One switch in the picker, and Claude Code continues the answer from the project's context. Orbital The project agent Every agent owns a session. Orbital owns the project. Orbital is the context steward for your agents. It maintains your project's context so every agent works from the same one. Whatever any agent produces or learns, Orbital keeps for all the others to reuse. Your agents evolve together on the same project. Context is yours. Agents are interchangeable. Set up in under 5 minutes. No Python or Node required. Bring your own API key. New here? Read the user guide. One-minute demo: one task, two agents, nothing re-explained https://github.com/user-attachments/assets/5f1373bc-2c3e-440b-af52-77ecbd80c27f !Platform: Windows !Platform: macOS --- Why a project agent? Is your context actually yours? You're three rounds into a design discussion with Claude Code when it stops with "You're out of usage credits." Your Codex quota is sitting right there, but Codex knows nothing about this project: the goal, the two decisions you just made, the half-edited files. You'd have to explain all of it again. Every agent's remaining quota sits in the picker. Pick another one and it continues from the same project context. It isn't only usage limits. People already use several capable agents at work: for the newest model, the leftover quota, or because a particular tool is better at the job. But the plan you settled with Claude Code, the file Codex left half-edited, the trade-off you decided in Cursor: each one is locked inside its own session. Close the session or switch tools, and that context is out of reach. So you carry the project between them: restating goals, explaining previous decisions, locating artifacts, and checking what was left unfinished. You are the agent's intern: copying and pasting, ferrying context, remembering where all the odd files live, while the agent gets the thinking. Orbital takes the context out of the session and puts it back in your local folder, and changes the unit of work from the session to the project. The project agent records every agent's progress on the project, so the next agent picks up the task with the full context. Whatever one agent produces or learns is kept for every other agent to draw on and reuse. No wheel gets reinvented: all your agents evolve together on the same project. Individual agents complete tasks. Orbital moves the whole project forward. --- What it means to own the project Orbital maintains five things that normally disappear or fragment between agent sessions — all of them as plain files in your project folder: - State — what is true about the project now (PROJECT_STATE.md) - Decisions — what was decided and why (DECISIONS.md) - Lessons — what the project has learned (LESSONS.md) - Work — what is running,
Top issues
#58[Windows] W3 deny ACE on .git\config / .git\hooks also denies SYNCHRONIZE, so the worker cannot run git at all4 comments · 2026-10-17#50[Bug/Feature] Windows 11 使用反馈:工具调用时命令行闪窗、子 Agent 退出登录失败及 pi agent 支持、模型切换保存后不生效3 comments · 2026-08-06#60[Feature] Allow per-agent environment overrides for ACP and CLI sub-agents2 comments · 2026-10-18#59[Windows] Add DSH sub-agent installation and auto-detection support2 comments · 2026-10-18#56Linux适用性问题2 comments · 2026-10-16#55Windows: sandbox setup/teardown runs icacls /T over toolchain folders, pegging CPU and stalling install and uninstall1 comments · 2026-10-09#53README demo video assets1 comments · 2026-09-06#78Decisions: make supersession explicit, and flag decisions whose grounds changed0 comments · 2026-11-14
Latest release
v0.22.0 v0.22.0 2026-11-13Orbital v0.22.0 Setting up Orbital with your own API key is now dependable from the first screen to the first task. This release also makes the app more responsive, fixes file edits that failed for no visible reason, and lets Codex run on the model you chose for it. New - A key is saved only when its connection test passes. In the setup wizard and in Settings, a key that fails its test is not stored, and you see the provider's reason in plain words. A saved key that still works is never touched, and renaming a key runs no test. - The setup wizard with a key. Next waits for a running test,