Full-text search across 59437 articles. Combine with topic and date filters; results sorted by relevance.
OpenCode, a terminal coding agent, stores session metadata in a local SQLite database, and a dlt pipeline moves that data into DuckDB for analytics. The pipeline, built by Alena Astrakhantseva and Alexey Grigorev in a Da…
GitHub released Agent Plugins 1.0 on August 6, an open standard that packages agent skills and MCP servers into a single installable plugin, with support from AWS, Anysphere, Microsoft, OpenAI, Vercel, and Google as a co…
A new arXiv preprint by Kushal Chakrabarti finds that agentic coding prompts such as CLAUDE.md grow without bound, more than tripling over their lifetime (+226%) and gaining +4.9 net instructions per commit, a phenomenon…
Unsloth AI released a native desktop app on Tuesday, August 11th, 2026, that packages its local model training and inference software for Mac, Windows, and Linux, claiming it is the first desktop app capable of both runn…
Hindcast, a new Mac app by developer Karan B, indexes, searches, and replays every Claude Code session locally, reading transcripts from ~/.claude/projects/ without sending data off-device. As of August 2026, the develop…
CodeRabbit, NVIDIA, and Baseten post-trained NVIDIA Nemotron 3.5 Lightning to route code reviews, achieving 80.7% exact route agreement (up from 75.8% for the GPT baseline) and cutting estimated inference costs by about …
A developer who is a non-native English speaker built a Chrome extension to rewrite text in place, aiming to eliminate the 'blunt tax' and 'junior tax' that non-native speakers face in code reviews and team communication…
A developer's custom AI code review agent, built with a two-step 'Reviewer-Critic' loop using Claude 3.5 Sonnet, caught 30% more edge-case bugs than manual reviews while cutting review turnaround from 4 hours to 15 secon…
A developer reports that AI coding agents' summaries of their own work are frequently inaccurate, citing instances where an agent incorrectly stated nothing was staged, silently dropped part of a request, miscounted chan…
MiniMax, the Shanghai-based AI developer, plans to release the 2K regeneration stage of its H3 multimodal video model, publish sparse-attention reference code, and develop a unified model for image generation and editing…
Sekai, a platform founded in 2024 by former ByteDance executive Lucky Zhang, has seen users create over 20 million AI-generated mini-apps since its late 2025 launch, with about 250,000 new apps added daily. The company h…
The Botslab W510 4K AI Security Camera System 2-Camera Kit is available for $220.58, a 31% discount off its $319 RRP, using promo code AA18 at Botslab. The kit includes two wire-free 4K/8MP cameras with solar panels, a h…
Amazon Web Services Inc. launched Kiro Crew, an autonomous agentic orchestrator that keeps AI coding agents running 24/7, allowing developers to start tasks and walk away. Built on the Kiro development environment, Crew …
Mert, creator of MoneyCo (thecompany.money), launched a coding agent built for accounting that connects to multiple QuickBooks and Xero accounts via API instead of MCP, deploys client files in a sandbox on Modal, and use…
Developer Kirill Chistov released VibeMenu v1.0, a free, open-source macOS menu-bar app that keeps a Mac awake while Claude Code, Codex, or ChatGPT Work sessions are active and releases the sleep assertion when work fini…
Boris Cherny, head of Claude Code at Anthropic, revealed at Y Combinator's Startup School 2026 that he set Claude Tag, a new product running Claude in Slack, to rewrite the Claude desktop app from Electron to Swift, a ta…
Plasma AI released Plasma Wiki, an open-source command-line tool that gives AI coding agents a deterministic way to inspect project knowledge stored in Markdown files, avoiding the need to load entire documentation repos…
An engineer detailed how to set up routines, background agents, and stacked skills in Claude Code, sharing a repo-health check routine that runs scheduled cloud agents to verify README instructions. The routine uses a se…
DeepSeek released V4-Flash-0731, an updated API for coding agents, into public beta on July 31, keeping the model's 284-billion-parameter mixture-of-experts architecture unchanged while adding native support for OpenAI's…
Punctuation choices directly affect how large language models process instructions, with hard stops like periods and numbered lists outperforming comma-spliced run-ons in agentic tools such as Claude Code, according to a…