The last few days have been wild. Here's what we've shipped over the weekend. But first, we're giving away free Nous Portal subscriptions to the first 250 people who claim code AGENTHERMES01 at portal.nousresearch.com - and there's a lot of exciting new stuff to use it on: -> Pokemon Player 🎮 Hermes can now play Pokemon Red/FireRed autonomously via headless emulation. The new pokemon-agent package (github.com/NousResearch/poke…) and built-in skill provides a REST API game server, and Hermes drives it through its native tools - reading game state from RAM, making strategic battle decisions, navigating the overworld, and saving progress to memory across sessions. It just plays Pokemon. From your terminal. No display server needed. -> Self-Evolution 🧬 We shipped hermes-agent-self-evolution (github.com/NousResearch/herm…) and an optional skill - an evolutionary self-improvement system that uses DSPy + GEPA to optimize Hermes's own skills, prompts, and code. It maintains populations of solutions, applies LLM-driven mutations targeted at specific failure cases, and selects based on fitness. Inspired by Imbue's Darwinian Evolver research that achieved 95.1% on ARC-AGI-2. -> OBLITERATUS 🔓 The abliteration skill got a major update. Hermes can now uncensor any open-weight LLM (Llama, Qwen, Mistral, etc.) by surgically removing refusal directions from model weights - 9 CLI methods, 116 model presets, tournament evaluation. Just say "abliterate this model" and it handles the rest. -> Signal, iMessage + 7-Platform Gateway 📱 Hermes now runs on iMessage and Signal alongside Telegram, Discord, WhatsApp, Slack, and CLI. Full feature parity: voice messages, image handling, DM pairing. Your agent is reachable everywhere. -> Automatic Provider Failover 🔄 When your primary model goes down (rate limits, outages), Hermes now automatically switches to a configured fallback model. Supports all providers including Codex OAuth and Nous Portal. One line of config, zero downtime. -> Secret Redaction Everywhere 🔒 All tool outputs now redact API keys, tokens, and passwords before they reach the LLM. 22+ patterns covering AWS, Stripe, HuggingFace, GitHub, SSH private keys, database connection strings, and more. Your secrets never leak into context.

Join around 4:15pm EST to hear from Nous Research's @dillonrolnick on @tbpn

Meet Hermes Agent, the open source agent that grows with you. Hermes Agent remembers what it learns and gets more capable over time, with a multi-level memory system and persistent dedicated machine access.

Our DeMo paper has been accepted to ICLR 2026! Developed by @bloc97_ and @theemozilla, DeMo helped kickstart industry research into communication-efficient optimizers. Today, it has become the core building block for Nous' low-bandwidth distributed training network. This year's ICLR class was particularly tough, with an acceptance rate of 28% across more than 19,000 submissions. We're thankful to the area chairs and reviewers for their overwhelming and difficult work. If you're in Rio in April, keep an eye out for our team (and some Nous swag) arxiv.org/pdf/2411.19870