Context Engineering

Google Cloud announced Agent Compute Engine, a compute service that gives every AI agent its own hardware-isolated microVM with no credentials inside. It already runs Gemini agents and enters preview in the coming months.

Cohere Rerank 5 ships in Pro and Fast tiers with a 32K context window, Context Focus passage extraction and calibrated relevance scores. Pro scores 82.2 on BRIGHT and costs $0.05 per 1M tokens.

DeepSeek has released official macOS and Windows desktop apps for DeepSeek Harness v0.2, its MIT-licensed agent harness. The preview adds a plugin manager, file and code-change review, and scheduled Automation Tasks. It also supports non-DeepSeek models through OpenAI-compatible endpoints.

Perplexity Research and turbopuffer have released pplx-embed-v2-context-9b-preview, a contextual embedding model for RAG pipelines. Each chunk is embedded with the full document in view....

Fastino Labs has released GLiNER2.5-Decide, a 340M-parameter open-weight decision model. It takes text and a schema of typed questions and returns structured answers. Each...

Nokia's applied research team has open-sourced AnyJev, a Python library that turns an open LLM into a decision model. It needs no training. It...

ByteDance Seed, SUTD, Georgia Tech, M-A-P, and TokenWave.AI introduce HarnessDev, a benchmark that scores the runnable harness a model builds rather than the answer it returns. Starting from a seed that scores 0, 6 creator LLMs construct harnesses across 5 benchmarks and 2,207 tasks, then evolve them from execution feedback. Self-built harnesses match human references on writing and ML experimentation but trail on code and search, and only 34 of 64 evolution changes move the same direction on held-out tasks.

Google Cloud AI Research, with Washington University in St. Louis and UNC Chapel Hill, has released EnvHarness, an Apache-2.0 layer that turns a static agent benchmark into one that adapts to the policy training on it. It wraps a frozen environment through the standard reset()/step() interface, so tasks and human-built verifiers stay untouched — and an LLM designer, EnvRigger, writes those wrappers automatically against flaws diagnosed in the agent's own rollouts. Across five benchmarks, mined skills gain up to 9.0 points on held-out tasks with 9.8% fewer execution steps.

DeepSeek Harness v0.1 is an MIT-licensed agent harness where every capability is a Cordis plugin. Four runtime modes, append-only session logs, and provider-agnostic model routing.

Three terms now compete for the same line in AI engineering job descriptions. Prompt engineering is the established one. Loop engineering entered the AI...

EverMind has open-sourced EverOS, a local-first memory runtime that stores AI agent memory as plain Markdown indexed by SQLite and LanceDB. It combines hybrid BM25 + vector retrieval, multimodal ingestion, and self-evolving Skills under an Apache 2.0 license. Here's what it is, how the architecture works, where the benchmarks stand, and where it still falls short — plus a runnable code walkthrough and an interactive demo.

We break down Google Cloud's new Open Knowledge Format (OKF), an open spec that formalizes the LLM-wiki pattern. We explain how a bundle works: a directory of markdown files with YAML frontmatter, where each concept needs only a type field. We cover the three design principles, the reference tools Google shipped, and how OKF differs from RAG. We include a working Python consumer and an interactive bundle explorer you can embed.

NVIDIA has released Nemotron 3 Ultra, a 550B total (55B active) open Mixture-of-Experts hybrid Mamba-Transformer for long-running agents. It pairs a 1M-token context with up to ~6x higher inference throughput than comparable open LLMs at on-par accuracy, and ships with open weights, training data, and recipes under OpenMDW-1.1.

Nous Research has published Lighthouse Attention, a selection-based hierarchical attention mechanism that wraps around standard scaled dot-product attention during pretraining and is removed afterward. Unlike prior methods such as NSA and HISA that pool only keys and values, Lighthouse pools Q, K, and V symmetrically across a multi-resolution pyramid, reducing the attention call from O(N·S·d) to O(S²·d) and running stock FlashAttention on a small dense sub-sequence. Tested on a 530M Llama-3-style model at 98K context, it achieves a 1.40–1.69× end-to-end wall-clock speedup against a cuDNN SDPA baseline with matching or lower final training loss.

In this tutorial, we implement how Memori serves as an agent-native memory infrastructure layer for building more persistent, context-aware LLM applications. We start by...

Moonshot AI, the Chinese AI lab behind the Kimi assistant, today open-sourced Kimi K2.6 — a native multimodal agentic model that pushes the boundaries...

In this tutorial, we build a robust, multi-layered safety filter designed to defend large language models against adaptive and paraphrased attacks. We combine semantic...

How do you build a language model that grows in capacity but keeps the computation for each token almost unchanged? The Inclusion AI team from...

Anthropic recently released a guide on effective Context Engineering for AI Agents — a reminder that context is a critical yet limited resource. The...

In this tutorial, we explore how to build a Context-Folding LLM Agent that efficiently solves long, complex tasks by intelligently managing limited context. We...

Context engineering has become a transformative force in moving from experimental AI demos to robust, production-grade systems across various industries. Below are distilled examples...

Estimated reading time: 4 minutes Table of contentsWhat Is Context Engineering?Taxonomy of Context EngineeringKey Insights and Research GapsApplications and ImpactFuture Directions The paper “A Survey of...