AI Agents
AI Agent technology and applications
Articles
xAI Launches /goal in Grok Build: Long-Running Autonomous⭐6
xAI launches /goal in Grok Build for autonomous multi-step coding with built-in verification, reducing human oversight and streamlining complex development task...
Sakana AI Introduces Sakana Fugu: A Dynamic Orchestration Model⭐8
Sakana AI launches Sakana Fugu, a dynamic orchestration model that routes tasks across swappable frontier LLMs for cost, performance, and vendor flexibility.
MoonMath AI Open-Sources HIP Attention Kernel for AMD MI300X:⭐8
MoonMath AI open-sources a high-performance HIP attention kernel for AMD MI300X, beating AITER v3 across all tested shapes and rounding modes under MIT license.
The 7 Types of Agent Memory: A Technical Guide for AI Engineers⭐7
Discover the 7 essential types of agent memory for AI engineers. This 2026 guide explains how to transform stateless LLMs into context-aware, production-ready s...
Crawlee for Python: Build a Web Crawling Pipeline with Robots⭐8
Build web crawling pipelines in Python using Crawlee, featuring robots.txt handling, link graphs, and RAG chunk export for AI applications.
Cisco AI Launches FAPO: Pipeline-Aware Prompt Optimization with⭐7
Cisco AI launches FAPO, an automated prompt optimization system using Claude Code for step-level failure attribution in LLM pipelines.
Nous Research Updates Hermes Agent With a Blank Slate Mode That⭐6
Nous Research updates Hermes Agent with Blank Slate mode, requiring users to define toolsets via platform_toolsets.cli and disabled_toolsets for precise, effici...
How to Build a Forecasting Pipeline with TimeCopilot Using⭐9
Build an end-to-end forecasting pipeline with TimeCopilot: prepare panel data, evaluate statistical & foundation models, generate probabilistic forecasts,
Yandex Open-Sources YaFF: A Zero-Copy Wire Format for Protobuf⭐7
Yandex open-sources YaFF, a zero-copy Protobuf wire format achieving near-struct read speeds. Reduces latency for high-performance 2026 scenarios. Apache 2.0, C...
VibeThinker-3B: A 3B Dense Reasoning Model Built on⭐8
VibeThinker-3B: a 3B dense reasoning model built on Qwen2.5-Coder-3B using the Spectrum-to-Signal pipeline for efficient, high-performance logical deduction and...