Poolside releases Laguna S 2.1, a 118B open-weight coding agent with 1M context
ben_burtenshaw · x · 2026-07-22
Poolside has released Laguna S 2.1, a local coding-agent model aimed at long autonomous runs.
- 118B MoE with 8B active parameters and a 1M context window.
- Open weights under the OpenMDW license.
- Reported scores include 70.2% on Terminal-Bench 2.1, 78.5% on SWE-Bench Multilingual, and 59.4% on SWE-Bench Pro.
- The model is said to run on a single DGX Spark and can sustain up to 24-hour autonomous runs.
- The post also includes a demo prompt for generating a simple Doom-like game in JavaScript and saving it as game.html.
Related event: Poolside Releases Laguna S 2.1: An 118B Open-Weight Coding Model(9 posts)→
More from coding & agent
- Building a Secure AI Agent Gateway: Self-Hosting OAuth for Multiple SaaS Apps — Defiant_Cod_2654 · 2026-07-22
- Rowboat launches as an open-source, local-first AI coworker with memory — ycombinator · 2026-07-22
- Scoble says AI “loops” really means long-running multi-agent workspaces — Scobleizer · 2026-07-22
- Kimi Code opens a waitlist as Moonshot rolls out its coding product — Fabulous_Bonus_8981 · 2026-07-22
- Open-source runtime lets each repo define its own AI code reviewer — ibabufrik · 2026-07-22
- Indie Dev Asks: What's Actually Broken in Your AI Agent's Memory Today? — AcceptableTime7937 · 2026-07-22