More agents ≠ engineering transformation. Meet Cosmos, the OS for agentic software development.
Joined November 2023
- Tweets1.8K
- Following56
- Followers22.3K
- Likes2.4K
Augment Code by Harness retweeted
@Claude Haiku 5.5 is now available in Cosmos.
Use it for fast, everyday coding work: quick edits, code questions, and short agent tasks where speed matters more than depth. Keep the larger models for the heavy lifting.
Big news from Augment Code.
We've agreed to sell Cosmos, Auggie CLI, the Code Context Engine & related tech to @harnessio, the Autonomous SDLC Platform. Harness's integrated ecosystem provides the ideal home to deliver these capabilities at true enterprise scale.
We started Augment to help enterprises build software faster. As AI generates more code, orchestrating it reliably at scale has become the real bottleneck.
At Harness, our team will continue this work by bringing software factory capabilities to its Autonomous SDLC Platform.
Thank you to our customers, partners, investors, and team.
Read the announcement: augmentcode.com/blog/augment…
From @OpenAI DevDay to @augmentcode... GPT-6.1 Sol is now available in Cosmos!
We'll be trying it in place of GPT-5.6 Sol and GPT-6 Sol in the coming days to power our software factory!
GPT-6 Sol and Luna by @OpenAI are now available in Cosmos!
We'll be upgrading all our workflows from the GPT-5.6 series of models in the coming days and measuring the impact on our software factory...
Claude Opus 5.5 by @AnthropicAI is now available in Cosmos!
Agentic tasks running on Opus 5.5 are completed at 40% of the cost Opus 5, making it a must-have upgrade for Claude power users!
We're excited to see this model improve outcomes for our customers' software factories!
Your PR sat for three days. CI was red, comments piled up — and your reviewer didn't have the confidence to hit approve.
A fleet of agents performs multiple rounds of review, fixes the CI, the comments, the conflicts, then hands your reviewer a deep review briefing and end-to-end evidence.
Humans still approve and merge 👇
If you’ll be in town for @TheLeadDev NYC this week, join us on Thursday for a practical, half day workshop on building your own software factory
Request a spot here: luma.com/augment-wi86
Have you wondered why your single bug-fixing agent doesn't actually burn down your team's bug backlog effectively? Read this insight from Augment's CTO and co-founder @igoro, and let us know what you think!
Why bug fixing is the least important part of a bug-fixing software factory
Software factories are very effective at burning down issue backlogs, but it's primarily NOT about the fix implementation.
See the next article in my series on software factories:
igoro.com/archive/bug-fixing…
Quick start: a software factory in Cosmos is two screens and one prompt.
1. Connect your repo
2. Create an environment
3. Describe the factory you want
Advisor picks the experts, writes the configs, applies them, and asks you when it needs a decision.
Gemini 3.8 Flash is now half price in Augment for the next two weeks ($0.38/M input, $1.88/M output tokens).
Our team has been throwing mockups and screenshots at the new model and getting back web pages that can ship without a redesign pass. This is the cheapest the model gets, so it's a good time to point it at your hardest frontend work and find out what @GeminiApp is capable of!
Available today. Start something and go do something else: cosmos.augmentcode.com.
The best part of an agent that runs in the cloud isn't the speed. It's that you can walk away.
Cosmos notifies you the moment it needs you. Everything else, it handles.
Cosmos Files — shared context for your team and their agents, across your whole org. Try it in Cosmos: cosmos.augmentcode.com
Watch a PM and an engineer collaborate on a PRD — with their agents, without leaving Cosmos.
A PM drafts it with her agent. An engineer opens the same file, has his own agent review it, leaves a comment. Her agent answers it and updates the doc.
One filesystem. Both people. Both agents.
GPT-6 Astra is live in Cosmos!
OpenAI's most capable model yet brings a significant jump on long-horizon coding and multi-step agentic work.
Give it your hardest task to work on over the holiday weekend at augmentcode.com!
Two new models are live in Cosmos today! We've come a long way since declaring that the era of single-model engineering is over augmentcode.com/blog/the-era…, and more models are coming soon...
GLM 5.3 Flash from @Zai_org (with US-based inference provided by @FireworksAI_HQ) is an order of magnitude cheaper than the most intelligent open-source models we've tested, while achieving the same level of intelligence as Sonnet 5.
Gemini 3.8 Flash from @GoogleDeepMind achieves a clear step in intelligence over Gemini 3.7 Flash at the same price point.
Try them both today: augmentcode.com
No more click-ops to configure your agent platform. The three things in the video are three sentences typed into the same box — one to build the automation, one to fix it, one to ask what it cost.
Try it now → cosmos.augmentcode.com