# oh-my-openagent v5.0.0-beta.8

- Product: oh-my-openagent (https://whatsnew.fyi/product/oh-my-openagent)
- Vendor: oh-my-openagent
- Date: 2026-08-17
- Version: v5.0.0-beta.8
- Original notes: https://github.com/code-yeongyu/oh-my-openagent/releases/tag/v5.0.0-beta.8
- Permalink: https://whatsnew.fyi/product/oh-my-openagent/releases/v5.0.0-beta.8
- Labels: Pre-release

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Run dozens of agents in parallel waves with automatic recovery if a crash occurs mid-run
- **added** — Sign in with Cursor Pro, Ultra, or Teams subscription via `/login cursor`
- **added** — Grok 4.6 is now a first-class model with tuned system prompt and set as default for quick lightweight tasks
- **added** — Check background memory system status with `/facts status` and retry failed extractions with `/facts retry`
- **added** — One canonical home for settings at ~/.omo/agent with automatic one-time migration of existing settings
- **added** — Memory consolidation now decides between reusing active session and starting fresh based on actual token cost
- **added** — Design reference library stops for frontend work are now binding instead of advisory with dedicated layout-mechanics reference
- **added** — Built-in measurement of wall-clock time saved by running tool calls in parallel
- **changed** — Failed memory extractions back off and stop retrying after a few attempts instead of looping forever
- **changed** — Planning now derives sensible defaults for budget, tech stack, scale, and compliance needs instead of assuming nothing or interrogating
- **changed** — Planning review loop is capped at 5 rounds instead of running indefinitely
- **changed** — Browser automation stack refreshed to current Playwright baseline for web research, login-gated scraping, and screenshot workflows
- **changed** — Team Mode boundary enforcement is repaired to prevent members from stepping outside assigned scope
- **changed** — Read-only shell output in Team Mode is now capped to prevent chatty commands from blowing up agent context window
- **fixed** — Disk usage in background memory system is now bounded with automatic cleanup of old extraction runs and payloads capped at 128KiB
- **fixed** — Background memory consolidation no longer silently fails on many model providers by falling back to available model if preferred model unavailable
- **fixed** — Model names with slashes are no longer invisible to the memory system
- **fixed** — Spawning background agent on Windows no longer flashes a console window
- **fixed** — Timeout and race condition fixes across Windows and macOS
- **removed** — Standalone `/omo-telemetry` command is removed in favor of built-in parallelism measurement

#### OMO 5.0.0-beta.8

This release is about doing more work at once and trusting what runs in the background. OMO can now run dozens of agents in parallel and recover if something crashes mid-run. You can sign in with your Cursor subscription, and Grok 4.6 is supported out of the box. The background memory system, which learns from your conversations, got a major reliability overhaul after an incident where it filled a disk with retries. Rounding it out: your settings now survive every update, planning asks fewer questions, and Windows got smoother.

##### Highlights

###### Run dozens of agents at once

Give OMO a big task and it can now break it into parts, run them as parallel waves of agents, collect the results, and move on to the next wave. Before, agents mostly ran one at a time. If a crash happens partway through, OMO picks up where it left off instead of losing the work. Nothing to configure, big tasks just fan out on their own.

###### Sign in with Cursor, and Grok 4.6 support

You can now connect your Cursor Pro, Ultra, or Teams subscription. Run `/login cursor`, approve in your browser, and you're signed in. For now this is authentication only. Cursor models don't show up in the model picker yet, but the groundwork is in place.

Grok 4.6 is now a first-class model. It gets a system prompt tuned for how Grok actually works instead of a generic fallback, and when OMO picks a model for quick, lightweight tasks, Grok 4.6 is the new default.

###### Memory that doesn't eat your disk

OMO quietly extracts facts from your conversations so it remembers things about you and your projects. On August 14 that system hit an infinite retry loop and consumed 388GB of disk. This release fixes all five root causes:

- Failed extractions back off and stop retrying after a few attempts instead of looping forever.
- Disk usage is bounded. Old extraction runs are cleaned up automatically and payloads are capped at 128KiB.
- You can check what the memory system is doing with `/facts status` and retry a failed extraction with `/facts retry`.
- Background memory consolidation no longer silently fails on many model providers. If its preferred model isn't available, it falls back to whatever is.
- Model names with slashes in them (like `openrouter/deepseek-ai/deepseek-v4-pro`) are no longer invisible to the memory system.

There's new smarts here too. Memory consolidation now decides between reusing your active session (faster, cache-warm) and starting fresh (more reliable) based on actual token cost. And the planning review loop can no longer run indefinitely; it's capped at 5 rounds.

###### Your settings survive every update

Updating OMO used to sometimes wipe your favorite models, fallback chains, or auth tokens, because different parts of the system looked for settings in different places. Now there's one home for your config, `~/.omo/agent`, and everything (launchers, child agents, doctor, setup, the installer) uses it. A one-time migration moves your existing settings there automatically.

###### Smarter planning when you don't spell everything out

When you ask for something without specifying budget, tech stack, scale, or compliance needs, OMO used to either assume nothing or interrogate you. Now it derives sensible defaults, records what it assumed so you can review it, and asks only the one question that genuinely needs your input.

###### See how much time parallel work saves

OMO now measures the wall-clock time saved by running tool calls in parallel and reports it. The old standalone `/omo-telemetry` command is removed; the measurement is built in now.

###### Smoother on Windows

Spawning a background agent on Windows no longer flashes a console window, thanks to community contributor @sanguneo. A batch of timeout and race condition fixes landed across Windows and macOS as well.

###### Agents doing UI work now actually study design

OMO ships a library of design references for frontend work, but agents mostly skimmed past

_[Truncated at 4000 characters — full notes: https://github.com/code-yeongyu/oh-my-openagent/releases/tag/v5.0.0-beta.8]_