Researchers introduced ττ-bench, a benchmark that tests AI systems' ability to construct customer-service agents from realistic business records, client requirements, and production APIs. Across 53 ta…
A developer recounts taking over four web apps generated by Figma Make and developing them with Claude Code, noting that the generated code is a projection of the design with exact-pinned dependencies…
A developer argues that most production AI agents should be built as simple while loops rather than complex frameworks like LangChain or CrewAI. The post highlights that top-performing agents on SWE-b…
OpenLedger, an Apache 2.0-licensed local-first double-entry accounting system with an SQLite backend and a Model Context Protocol (MCP) server exposing 15 tools, has been released by Attri Inc. The le…
Red Hat's Emerging Technologies group released ripwire, an open-source CLI and MCP server that generates a ranked, deterministic call graph for coding agents, aiming to replace grep-based exploration …
Organizations should not build their operations around a single AI model provider, warns a developer building the open-source aweb platform, as providers like Microsoft, OpenAI, and Anthropic increasi…
Virtuals announced that Robinhood, led by co-founder and CEO Vlad Tenev, has completed the rollout of Agentic Trading to all eligible users, a product launched on May 27 that lets outside AI agents pl…
FreeModel API's live status flipped to up, with Uprouter's best-effort probes recording 146ms latency 10 hours ago and 481ms one day ago, following a down reading 12 days earlier. Uprouter rates the f…
A developer resolved a critical flaw in their autonomous Claude Code setup where Stop hooks triggered audit notifications during unattended sessions, causing 19 log nags overnight. By reading the tran…
Anthropic's Claude Code 2.1.204 introduces a taxonomy for its five extension mechanisms—hooks, skills, subagents, plugins, and CLAUDE.md—differentiated by when each enters the context window. Measurem…
OpenAI's GPT-6 Astra, released Thursday, is now being used by developers as the orchestrator model inside Anthropic's Claude Code harness, a setup that combines OpenAI's frontier model with Anthropic'…
Medusa launched a blog series on September 7, 2026 detailing its agentic automations, starting with how it keeps documentation in sync across its AI toolkit. The toolkit includes Medusa Development Sk…
Pomeroy 1.0, a $19 macOS menu-bar app, connects any of 24 AI assistants to Apple apps including Mail, Calendar, Messages, and seven others via MCP, with a privacy pledge verified by tests. The app, bu…
The Fort That Holds has open-sourced Beta Reader, a free MIT-licensed tool that lets beta readers leave spoken feedback on manuscripts by tapping a passage and talking, with notes filed directly into …
Developer siropkin released chrome-bridge, an open-source tool that lets any AI agent drive a user's real, logged-in Chrome browser via one unpacked extension and a zero-dependency Node CLI, requiring…
In a 10-task SWE-bench verified harness benchmark, 3code solved 9 of 10 tasks using 5 million tokens, while Claude Code, opencode, pi, zcode, and hermes were also tested. The benchmark, conducted by i…
Manifold Security disclosed a vulnerability named GitSpawn that enables arbitrary code execution in AI coding agents, including Claude Code, OpenAI's Codex, and Cursor, via malicious Git repositories.…
Rune, an open-source tool from thecolourfoundation, addresses persistent codebase context loss in AI coding agents by maintaining continuous codebase understanding via the Model Context Protocol (MCP)…
Claude Code, Anthropic's coding agent, can drive Blender on macOS by directing it to the executable at /Applications/Blender and prompting it to write and execute Python scripts using the bpy module, …
Spotify Engineering cut Claude Code token usage by roughly 90% on a Java monorepo by routing bulk file reading and boilerplate code generation to a cheap model such as Gemini 2.5 Flash while keeping r…