Subconscious Blog

WATTER and Subconscious partner to power AI agents with your water heater

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.

Read post

All posts

Jun 22, 2026 · 7 min readAgents

Subconscious + GLM-5.2 Makes "/compact" Obsolete

Model-driven context engineering improves agent inference and reasoning

Caching engineered context for agent inference

Jun 3, 2026 · 12 min readResearch

Subconscious Cache: Reliably Capture Your Agent Context

We introduce an inference runtime optimization specifically for agent systems with automated context pruning and the underlying caching technology to make it happen.

May 21, 2026 · 4 min readAnnouncements

Introducing TIM-Qwen3.6-27B

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.

Apr 23, 2026 · 6 min readAgents

A New Hope for SLMs

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.

Apr 2, 2026 · 6 min readResearch

Context Intelligence is the Key for AI Agents: March 2026 Benchmarks

The benchmarks are in. Training models to manage their own context sets a new frontier across browser control, computer use, and coding.

Mar 20, 2026 · 5 min readAgents

Fight context rot with garbage collection

Python programs manage memory efficiently with garbage collection. Agents should do the same thing for managing context.

Mar 17, 2026 · 4 min readAnnouncements

Why I joined Subconscious

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.

Feb 24, 2026 · 5 min readAgents

Start Your (Agent) Engines

We think it’s a bit outdated to define an agent only by its underlying model.

Dec 17, 2025 · 5 min readAgents

Better Call TIM: Filling out forms with an agent

Thread Inference Model (TIM) outperforms frontier browser agent.

Nov 7, 2025 · 15 min read

The End of the Agent Dev Paradox

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.

Oct 16, 2025 · 4 min readAgents

Abstract as High as Possible

When you write at a lower level abstraction than you have to, you’re going to regret it.

Aug 27, 2025 · 5 min readAgents

Make Agent Frameworks Trainable

Agent frameworks cannot generalize. Something that can is inevitable.

Aug 22, 2025 · 5 min readResearch

Dawn of a New Interface

LLM OS is here

Aug 18, 2025 · 4 min readAgents

Agents Without Training Wheels: The Model Agent

It's time to remove the training wheels from Agents. The model agents are here.

Aug 1, 2025 · 4 min readAgents

The Cure for Context Rot

Context rot is the slow death of an agent’s attention span, and a key problem holding agents back today.

Jul 24, 2025 · 4 min readAnnouncements

Introducing Subconscious: Build Flexible, Capable Agents

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

Try TIM via the API.

Start building