Ornith-1.5-122B is now live & free in Command Code.
125B params, 262K context, ZDR by default
Open-weight strong and fast agentic coding model
Available for all plans, all subscribers. 
Back in 2009, NoSQL took web development by storm. What happened since?
Lost a thread? Ask Delta to find it. Delta has built-in tools to search and read your past threads. Just describe what you remember.
RSVP on Luma: luma.com/jfqreyyn Interactive Agent Runners can ask clarifying questions before it builds. On Thursday, Oct 22 at 1 PM ET, KP and Tania go live with Vanessa Ramos and Gehrig Kunz, who worked on it, for demos and Q&A.
www.youtube.com/watch?v=PbVs... 
Explore and publish your Command Code Mods: commandcode.ai/mods Introducing the Mods Hub for Command Code.
An open-source registry to discover, install, and publish mods for Command Code.
· Add tools, commands, hooks, rules, or build and share your own.
· 30+ mods already live. Time to mod your agent. We tested 25 approaches to MCP tool search, including decision models, LLMs, and embeddings. Our benchmark runs 150 search queries against 536 tools. We settled on weighted BM25 with a few normalization rules. Fast, local, no model or API calls.
It's been one month since we released the Neki platform preview. Since then we've added $50 Metal nodes, improved Postgres compatibility, read-only replicas, Azure support, and more. Full list of updates and where to start:
Tania built a copy review app inspired by her work on Netlify's marketing and community teams. With Netlify Preview alongside Agent Runners, she can see changes as she builds and keep refining the app without constantly opening separate preview links.
Introducing tsrs: a Rust port of the TypeScript compiler 🦀
We are not forking TypeScript!
◆ In close collab with the TypeScript team
◆ Up to 8x faster than TS 7.0 & ~70% less memory
◆ Runs in WASM (works in your browser & workers)
◆ Soon part of Oxc
npx tsrs
blog.cloudflare.com/typescript-r... DeepSeek V4.1 Flash 1017 (latest) now has $100 usage, for the next 24 hours.
$10 GOAT → $100 in credits.
After that, it's back $80 as before. LFG!
🐐 Statusline is now live in Command Code.
Run /statusline to customize line below your prompt.
Show model, usage, reasoning level, costs, and more. Reorder items and toggle indicators your way. 
DeepSeek V4.1 Flash 1017 now live in Command Code
· All DeepSeek 4.1 requests use the latest 1017 version
· Matches Opus 5 level perf at 60x cheaper cost
· Beats Kimi K3 (max) at 10x lower cost
Available across on all plans and api right away. Richard Terry-Lloyd needed his AI workflow to run every morning at 6 a.m., even when his laptop was closed. He'd never worked with cron jobs or serverless functions before. With Netlify Agent Runners, he was able to set up a scheduled function to publish his document automatically.
RVSP here: luma.com/ur4pm34i Come meet the Bay Area Rust community! We meet every third Wednesday of the month. And our next meetup is already here, on October 21. We'll meet at the Atuin office in the Mission. And we have a very cool lineup of speakers including @bedrockrobotics. RSVP below!
It alters the global settings, so it persists between threads. We don't directly allow an agent to edit the raw json either, we have a tool that the agent uses to interact with settings, so we can prevent the agent from seeing certain sensitive bits.
MiniMax M3.1 Flash beats DeepSeek V4.1 Flash 1017, GLM 5.3, and Kimi K3 on cowork AutomationBench v1.0.6.
It also scores 73.7% on DeepSWE v1.1, delivering frontier-level coding and engineering performance.
Thanks to team MiniMax on partnering for their day 0 launch. MiniMax M3.1 Flash (aka Space Bunny) is now live and FREE in Command Code for limited time!
· 1M token context window
· Frontier level coding performance
· Available all plans, all subscribers In this video, Joseph asks Delta to configure itself to use Ollama as a custom OpenAI-compatible provider. It all happens in the thread, without Joseph ever touching Settings.
