Available models
Powerful open weight base models, on inference designed for agents.
Latest post
Nori and Subconscious partner to let teams run long, tool-heavy AI agents in the cloud. Kick off a session in a few clicks and close your laptop.
All posts
MIT researchers discovered a way to dynamically compress up to 80% of an AI agent’s context to make it much more efficient and accurate. Now, they’re turning that core technology into an opinionated inference platform to power agents that run can faster, for longer, at a lower cost with no changes to the underlying hardware, AI models, or apps that use them.
We have partnered with WATTER to bring our inference system and models to the WATTER AI platform, making it possible to run capable, long-context agents on a distributed fleet of GPUs built into water heaters.
Model-driven context engineering improves agent inference and reasoning
We introduce an inference runtime optimization specifically for agent systems with automated context pruning and the underlying caching technology to make it happen.
Today we're releasing TIM-Qwen3.6-27B on a new OpenAI and Anthropic compatible API, powered by a TIMRUN runtime breakthrough that delivers 10x effective context and 3x concurrent throughput on the same hardware.
Last week Claude Opus 4.7 became the most powerful model ever released to the public. This week it doesn’t seem to matter very much.
The benchmarks are in. Training models to manage their own context sets a new frontier across browser control, computer use, and coding.
Python programs manage memory efficiently with garbage collection. Agents should do the same thing for managing context.
A simple AI agent that helps users click a few buttons shouldn't cost $0.50 per conversation. And building it shouldn't require some of the best engineering work I've done in my 10-year career.
We think it’s a bit outdated to define an agent only by its underlying model.
Thread Inference Model (TIM) outperforms frontier browser agent.
We want flexibility and rigidity, we want a do-it-all blackbox but with complete observability, and we want tools for fast prototyping and performance tuning all at the same time in the same agent.
When you write at a lower level abstraction than you have to, you’re going to regret it.
Agent frameworks cannot generalize. Something that can is inevitable.
LLM OS is here
It's time to remove the training wheels from Agents. The model agents are here.
Context rot is the slow death of an agent’s attention span, and a key problem holding agents back today.
Backed by MIT research on a co-designed AI model and runtime, Subconscious is an inference engine for AI agents that allows for strong reasoning across external tool calls and virtually unlimited context.
Get started
