Brent Ozar shares lessons learned from building AI-powered applications in July 2026, emphasizing adversarial development where different LLMs handle specification, coding, and review to catch bugs ea…
Hallmark, an open-source design skill by Hassan El Mghari (Nutlope) at Together AI, has crossed 12,300 GitHub stars by preventing AI coding agents from generating homogeneous landing pages. The skill …
Noticky, a local MCP server for macOS sticky notes, lets AI apps like Claude Desktop and Codex search, read, create, update, open, trash, and restore notes directly on a user's Mac. The server runs lo…
An architect at a company built Memsprout, a platform for sharing AI context among teammates, after finding existing solutions inadequate for non-repo teams like product, design, and support. The tool…
OpenAI will provide free access to its most advanced AI models and research tools to up to 100,000 academic researchers, starting with 10,000 participants in summer 2026 and expanding through 2027. Th…
OpenAI CFO Sarah Friar told employees on July 29 that annualized recurring revenue in July exceeded the entire second quarter, according to CNBC, but the company did not disclose a dollar figure or de…
Jacobian, a high-level mathematics toolkit for AI agents, provides executable mathematics with composable operations for conjectures, counterexamples, exact computation, and formal proof, featuring an…
Unit 42 identified a Chinese-speaking threat actor using the Hermes Agent framework with DeepSeek as an autonomous offensive operator to target infrastructure via seven vulnerabilities, combining AI-d…
Agent-Manager, a terminal user interface that runs multiple AI coding agents side by side in tmux sessions, has been released by developer YoanWai. The tool supports Claude Code, Codex, OpenCode, and …
A free backlink exchange for indie builders, driven from a coding agent, has launched at builders-backlinks.com. Built by nicklaunches.com, the platform exposes an MCP server that lets developers trad…
GitHub Copilot in Visual Studio Code released July 2026 updates (versions 1.127–1.131) featuring a redesigned Agents window with multi-chat support for Claude, generally available Copilot vision for i…
Graft, a tool from Nanonets, reduces coding agent tool calls by 46%, tokens by 42%, and time by 60% in a 162-run controlled benchmark by building a persistent graph of codebase context as linked markd…
OpenAI reported that GPT-5.6 Sol's score on the ARC-AGI-3 benchmark nearly tripled from 13.3% to 38.3% after replacing the default test harness with two settings from its Responses API: retained reaso…
Microsoft shipped VS Code 1.131 on July 29 with subagent status visibility, letting developers see live indicators for each running subagent's model, runtime, and current tool call without opening sep…
A developer benchmarked AI coding agents on a real-world task-manager project, finding that a greenfield build completed in 34 minutes and a subsequent authentication refactor took 42 minutes of activ…
Perplexity AI released Numbat, an open-source agent runtime detection and response tool that provides endpoint visibility into AI agent activity with local detection, optional pre-action blocking, and…
Unblocked, a context engine provider, argues that connecting AI agents to sources via MCP connectors gives access but not understanding, costing up to 83% slower task completion and 60% more tokens. I…
Agentics hosted its second in-person meetup and first Spotlight event in NYC, focusing on personalizing coding agents to overcome flaws in the default 'happy helpful assistant' personality, such as sy…
Reused input from conversation history, not new typing, is the main driver of token consumption in AI chat tools like Claude and Codex, according to a technical analysis by Remy. Nine practical habits…
Reused input dominates token bills because every API call resends the full conversation history, with one Codex user recording 3.59 billion reused tokens out of 3.77 billion total in a single day. Ant…