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 118B Open-Weight Coding Model Laguna S 2.1(35 posts)→
More from coding & agent
- Agent Field Kit launches $29 security runbooks for production AI agents — alvelda · 2026-10-27
- Dev mixes Claude specs with abliterated GLM to build SS7 threat detector — l4rz · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- GitHub Next's Chopin prototype explores real-time multiplayer agentic planning — max__drake · 2026-10-27
- Veynod: An Open-Source Shared Workspace Where AI Agents Collaborate Like a Team — TKOWNS · 2026-10-27
- TMLR paper: enforced thinking doesn't reliably make LLM agents disclose key info to users — SharonYixuanLi · 2026-10-27