Olo guides and release notes https://www.olomni.com/en/ 2026-10-09T12:00:00Z Olomnihttps://www.olomni.com/ https://www.olomni.com/en/guides/approve-claude-code-from-your-phone2026-10-09T12:00:00Z

Approve or reject what Claude Code asks for from your iPhone or Android, seeing the action’s real effect. Step by step with Olo, no app store needed.

https://www.olomni.com/en/guides/claude-code-usage-limit2026-10-09T12:00:00Z

What to do when Claude Code stops at its usage limit: save where the work was left and continue with Codex, Gemini CLI or Cursor with full context.

https://www.olomni.com/en/guides/shared-memory-between-ai-agents2026-10-09T12:00:00Z

Make Claude Code, Codex, Cursor and Gemini CLI remember the same things: what one learns, the others read. You confirm, edit or delete every memory.

https://www.olomni.com/en/guides/hand-off-a-task-from-claude-code-to-codex2026-10-09T12:00:00Z

Move a task from one AI to another without re-explaining anything: Olo’s handoff carries where the work was left, the branch and whether tests passed. All on your computer.

https://www.olomni.com/en/guides/stop-an-ai-agent-from-force-pushing2026-10-09T12:00:00Z

Put a gate between your AI agent and anything irreversible: force pushes, reset --hard, deploys and deletions wait for your approval and show the real effect.

https://www.olomni.com/en/guides/what-is-an-ai-agent-approval-layer2026-10-09T12:00:00Z

An approval layer puts a human decision between an AI agent and actions with real consequences. What it is, what it needs and how Olomni does it.

https://www.olomni.com/en/guides/olo-vs-claude-code-remote-control2026-10-09T12:00:00Z

Claude Code’s Remote Control already lets you approve permissions from your phone. What Olo adds (several vendors, checking whether the AI really finished, handoff) and when you don’t need it.

https://www.olomni.com/en/guides/control-claude-code-and-codex-from-your-phone2026-10-09T12:00:00Z

Claude Code Remote Control, Codex in the ChatGPT app, Happy Coder, Omnara and Olo: what each does, which vendors it covers and which to pick for how you work.

https://www.olomni.com/en/guides/how-to-tell-if-an-ai-coding-agent-really-finished2026-10-09T12:00:00Z

A coding AI can say “done” without having tested anything. How to check in five steps, and how Olo automates it with a green, amber or red verdict.

https://www.olomni.com/en/changelog#v0-1-372026-10-09T12:00:00Z

Olo gets a new look: three styles to choose from (Status, Porcelain and Graphite) in the panel and on your phone. In “Status” the background is what is happening: mint when calm, yellow when something waits for your answer, pink when something failed. The panel folds itself away when it is no longer needed and leaves just Olo, or with the arrow in its header. What waits for your OK shows in a strip outside “Now”, and the phone verdict reads without knowing how to code.

https://www.olomni.com/en/changelog#v0-1-362026-10-09T12:00:00Z

“Try it now”: as soon as your phone is linked, Olo sends you a pretend permission request and you approve it with one tap, no AI needed. In a minute you see how the real, sensitive ones will reach you, and it tells you whether you decided from the phone or the computer.

https://www.olomni.com/en/changelog#v0-1-352026-10-09T12:00:00Z

Olo judges each turn by what it saw on your machine, not by what the AI said: green only with a test observed after the last change, amber if it was not tested, red if it fails or touches a protected path. It warns you when an AI loops on the same failure, and introduces the project contract: your rules, protected paths and how "done" is checked, for any AI.

https://www.olomni.com/en/changelog#v0-1-342026-10-05T12:00:00Z

Strict mode: your approvals move into the system configuration, so no AI can remove them or approve itself. Sensitive actions can only be approved from the phone you link with the code Olo shows you, verified by the server. Olo restores its hooks if someone removes them, and the checkup tells you how secure each AI is.

https://www.olomni.com/en/changelog#v0-1-332026-10-05T12:00:00Z

Olo finds Codex even when it ships inside the ChatGPT app: it shows up on your phone to start tasks and to review another AI’s work.

https://www.olomni.com/en/changelog#v0-1-322026-10-05T12:00:00Z

Your AIs review each other: from your phone, ask another AI to check what the first one did and get a verdict (it never sees your .env files or keys, and secrets are redacted). You also see what each AI spends and, when it reports it (Codex), how much quota is left. A cleaner, tidier phone app.

https://www.olomni.com/en/changelog#v0-1-312026-10-04T12:00:00Z

Ask and review from your phone, no coding needed: tell Olo what you want and pick the AI (Claude Code, Codex or Gemini). Watch each task go from “Requested” to “Done”, see which files changed, ask for a tweak or undo it all. Approvals in plain words, and you choose how much freedom they get.

https://www.olomni.com/en/changelog#v0-1-302026-10-04T12:00:00Z

Your next AI gets a more reliable project state: anchored to the repo root, with a summary of each repo, and never trusting a test whose result wasn’t seen. If Olo crashes it reopens itself, and it tells you about anything sensitive an AI did while Olo was closed.

https://www.olomni.com/en/changelog#v0-1-292026-10-04T12:00:00Z

Olo opens at login so your approvals, memory and phone are never left without it, and only one copy can run at a time.

https://www.olomni.com/en/changelog#v0-1-282026-10-04T12:00:00Z

Olo looks sharper and livelier: new lighting, a vinyl finish, a glass screen on its chest and smooth transitions between states. It uses less memory.