A tutorial demonstrates building an OpenHarness-style agent runtime from scratch, covering tool use, typed schemas, permissions, memory, skills, multi-agent coordination, and other core components. Th…
A tutorial demonstrates building a fully offline Graphify pipeline to convert a multi-module Python application into a knowledge graph, using tree-sitter for extraction and NetworkX for analysis inclu…
Nous Research has added a /learn command to its Hermes Agent Skills System, enabling the agent to automatically generate a standards-compliant SKILL.md file from local directories, documentation URLs,…
Generative AI coding tools have evolved from autocomplete to full application generation, with platforms like Atoms, GitHub Copilot, Tabnine, Replit, and Warp leading in 2026. These tools enable devel…
UC San Diego researchers developed DFlash, a speculative decoding method that uses a lightweight block diffusion model to draft entire token blocks in parallel, achieving up to 6.08x speedup on Qwen3-…
Mistral AI released OCR 4, a document-understanding model that adds bounding boxes, block classification, and confidence scores to extracted text, supporting 170 languages. The model is designed for e…
NVIDIA released Canary-1B-v2, a multilingual speech recognition and translation model, with a Python tutorial demonstrating ASR, translation, and SRT subtitle export. The tutorial shows how to install…
Prime Intellect released prime-rl 0.6.0, an open framework for asynchronous reinforcement learning on trillion-parameter Mixture-of-Experts models, enabling training on agentic RL workloads with optim…
MarkTechPost published a hands-on guide to GLM-5.2's OpenAI-compatible API, demonstrating reasoning effort control, function calling, tool-using agents, structured JSON output, and long-context retrie…
XAI launched /goal in Grok Build, a mode for long-running autonomous coding tasks with built-in verification. The agent plans, executes, and verifies multi-step objectives like module migration, reduc…
Sakana AI launched Sakana Fugu, a multi-agent orchestration system that routes tasks across a pool of frontier LLMs via a single API. The system, available in two variants (Fugu and Fugu Ultra), outpe…
MoonMath AI open-sourced a bf16 forward attention kernel for AMD MI300X GPUs that outperforms AMD's AITER v3 on every tested shape and rounding mode, achieving up to 1.26x speedup. The kernel, written…
Prefab released a tutorial demonstrating how to build interactive Python-first dashboards using its reactive UI components and static HTML export. The tutorial shows developers how to create a polishe…
Large language models are stateless by default, but agents require memory to retain context across steps. A new technical guide identifies seven types of agent memory—working, semantic, episodic, proc…
Apify released a tutorial for Crawlee for Python, demonstrating how to build a web crawling pipeline with robots handling, link graphs, and RAG chunk export. The tutorial covers environment setup, sta…
Cisco Foundation AI open-sourced FAPO, a Claude Code-driven system that autonomously optimizes multi-step LLM pipelines by attributing failures at the step level and proposing variants. In evaluations…
Nous Research updated its open-source Hermes Agent with a Blank Slate setup mode that starts with only provider, model, File Operations, and Terminal enabled, disabling all other tools by default. The…
MarkTechPost published a tutorial on building a forecasting pipeline with TimeCopilot, using foundation models and automated anomaly detection on airline passenger data and synthetic seasonal series. …
NVIDIA Research released SpatialClaw, a training-free framework that uses code as the action interface for spatial reasoning in vision-language models. The framework achieves 59.9% average accuracy ac…
Researchers from Sina Weibo Inc (China) released VibeThinker-3B, a 3-billion-parameter dense reasoning model built on Qwen2.5-Coder-3B using the Spectrum-to-Signal post-training pipeline. The open-sou…