Nous Research publishes an agent manifesto: your model, your memory, your hardware
NousResearch · x · 2026-10-06
Nous Research posted a 20-point "agent manifesto" arguing users should have full control over their AI agents:
- Model freedom: use smarter, cheaper, or local models, a different model per task, or switch mid-conversation
- Data and memory autonomy: users decide what the agent sees, remembers, and forgets
- Runtime autonomy: run on machines that never touch the internet, on a closed laptop, reachable from existing apps
- Transparency: read the prompt, see every tool and disable unwanted ones, know what the agent did and why
- Portability: export the agent, read and change the code
It closes with "Your agent should be yours" — a clear counter-position to closed, cloud-locked agent products.
More from coding & agent
- Matt Shumer builds Hogwarts live on Spawn with AI in a multiplayer world — mattshumer_ · 2026-10-06
- Ruff author shares build-speed trick: one crate per file for faster compiles — charliermarsh · 2026-10-06
- Notable MCP critic converts, now wants an official Gmail MCP — zeeg · 2026-10-06
- Developer Runs 1,200+ Blender Modeling Sessions to Blind-Rank LLMs and Agent Harnesses — Izolight · 2026-10-06
- Software-in-the-loop: self-supervised scaling of terminal environments lifts Terminal-Bench 2 to 53.56% — Zhongzhi Li · 2026-10-06
- Real product photos plus LTX-2.5 rotation videos and Codex-coded UI rebuild a brand demo — OpenAIDevs · 2026-10-06