13 releases covered on ThursdAI · nousresearch.com ↗
Nous Research launches Hermes Desktop agent app for Mac/Win/Linux
Nous Research launched Hermes Desktop, packaging the Hermes Agent harness into a native desktop app for Mac, Windows, and Linux. Karan previewed chat, permissions, tool-call visibility, reasoning traces, and admin controls aimed at small teams, startups, and personal agent fleets.
Nous Research publishes Lighthouse Attention for fast long-context pretraining
Nous Research released Lighthouse Attention, a sparse attention method for long-context pretraining that delivers major speedups. The release includes a blog post, an arXiv paper and an open-source GitHub implementation.
Hermes passes OpenClaw as #1 CLI agent on OpenRouter, adds computer use
Nous Research's Hermes overtook OpenClaw as the #1 CLI agent on OpenRouter. It also added background computer use via Trykua, and Alex described switching his own daily agent workflow from OpenClaw to Hermes.
Nous Research TST: 2-3x training speedup without architecture changes
Nous Research released Token Superposition Training (TST), a training technique that achieves 2-3x wall-clock speedup at matched FLOPs. It requires no architecture changes, making it a drop-in efficiency win for LLM training runs.
Nous Research ships Hermes 27B, paired with the Hermes harness
Nisten's pick of the week: Hermes 27B, an open model trained specifically to be paired with the Hermes harness and allegedly distilled from the Opus API. Model and harness ship together as a portable unit, a notable take on the harness-engineering trend Swyx discussed.
Nous Research ships a research agent
Nous Research announced a research agent, joining the wave of lab-built agentic tools shipped this week. It was covered in the roundup of new agent products alongside Cursor cloud agents and Perplexity Computer.
NousCoder 14B: 7% LiveCodeBench jump in 4 days of RL training
Nous Research released NousCoder 14B, an open source competitive programming model that achieved a 7% jump on LiveCodeBench accuracy in just four days of RL training on 48 NVIDIA B200 GPUs. Training used 24,000 verifiable problems, and the release ships under a full Apache 2 license with training code and a benchmark harness.
Nous Research ships Hermes 4.3 36B with decentralized training
Nous Research released Hermes 4.3-36B, highlighted on the show for being trained with decentralized infrastructure and for state-of-the-art RefusalBench performance. The release continues the Hermes line of open, steerable instruction-tuned models.
Nous Research releases Hermes 4 14B compact hybrid reasoning model
Nous Research launched Hermes 4 at 14B, a compact hybrid reasoning model with tool calling designed for both local and cloud use. It extends the Hermes 4 family down to a size practical for local deployment while keeping reasoning and tool-use capabilities, with a full tech report published on arXiv.
Nous launches Husky Hold'em Bench, an open-source pokerbot eval for LLMs
Nous Research released Husky Hold'em Bench, an open-source poker benchmark that evaluates LLM strategic play in a richer agentic environment than standard leaderboards. Guests Roger Jin and Bhavesh Kumar joined the show to explain how it measures agent behavior and decision-making under uncertainty rather than chasing another leaderboard point.
Nous Research launches Psyche, a decentralized cooperative-training network
Psyche is Nous Research's decentralized cooperative-training network that lets distributed participants jointly train large models over the internet. The launch includes open code on GitHub and a live dashboard tracking the first run, a 40B model called Consilience. COO Dillon Rolnick joined the show to explain the decentralized training push.
Nous Research releases DeepHermes 24B and 3B hybrid reasoning models
Nous Research released DeepHermes hybrid reasoners at 24B (Mistral-based) and 3B sizes, models that can toggle between standard chat responses and long chain-of-thought reasoning. The 24B preview is available on Hugging Face as part of the week's wave of open-source reasoning model releases.
Nous Research opens Portal, an inference API for Hermes models
Nous Research launched Portal, its new inference API service offering access to models like Hermes 3 Llama 70B and DeepHermes 3 8B directly via API. It marks another open-source lab standing up hosted API access to make its models more accessible.
Never miss a Nous Research launch — we cover every release live, every Thursday.