Cookbook launched as a workspace that lets teams hand tasks to agents including Anthropic's Claude and OpenAI's Codex, attributing every action to the person whose agent ran it and reporting each run'…
Unreal Labs released Unreal Agent, an open-source agent harness that achieves up to 40% cost savings compared to Codex and up to 20% compared to Pi on production workloads and agentic benchmarks with …
OpenAI released GPT-6 Sol and GPT-6 Luna on Tuesday, priced roughly 50% cheaper per million tokens than the previous Sol and Luna generations. GPT-6 Sol costs $2 per million input tokens and $10 per m…
A developer is proposing that TypeScript add an optional compiler flag to preserve enough type information to generate JSON Schema at runtime, eliminating the need to duplicate native TypeScript types…
Researcher Oren Yomtov of Accomplish AI disclosed two OpenAI Codex sandbox escape vulnerabilities, Heapjack and Overpatch, that were reported on August 12, patched within eight days, and publicly disc…
A developer reports that a client replaced two human virtual assistants with Anthropic's Claude and OpenAI's Codex, and is considering adding xAI's Grok, as part of a broader shift away from offshore …
Developer Roy Osherove released Graphlin, an open-source plugin for Claude Code and Codex that automatically visualizes an agent's software architecture as it is being built, using Jev as a runtime cl…
Technical founder Jev published a September 21, 2026 essay arguing that product launches succeed on communication and decision speed, not engineering quality alone, citing the TypeSafe frenzy as his t…
Agnostic-ai released v0.65.0, which changes Windsurf agents or permission rules that grant only `Write` to emit Devin's `write` tool instead of `edit`, so they no longer grant file editing (#1022). Th…
A developer released v0.7.0 of PR Tour, an open-source skill for Codex and Claude Code that generates guided walkthroughs of pull requests, adding an optional "transition" field that lets readers insp…
A GitHub project called token-limit-resets now tracks when Codex and Claude Code usage limits reset so developers can spend remaining tokens on their own builds. The tool is distributed through GitHub…
A developer built a Gomoku arena at gomoku.pickuma.com where AI agents connect via MCP, read the board, and select their own moves with no installation required. In a 31-move, 21-minute match, Claude …
Vijaye Raji, chief technology officer of OpenAI's Applications division, leads key technical teams powering ChatGPT and Codex, and said Codex has made OpenAI's engineers "10 times more productive." Th…
A developer building Ordewell, an open-source Apache-2.0 orchestrator that turns a single goal into a reviewed plan of coding-agent tasks, has detailed how its planner runs inside a read-only explorat…
Alibaba.com's CommerceAgentBench, an open-source benchmark of 107 end-to-end e-commerce tasks, found that the strongest AI agent tested completed 61.7% of real-world commerce tasks, with different mod…
Developer Mark Wylde released @markwylde/all-your-agents, an open-source tool that watches every coding agent session on a machine without polling, tracking harnesses including Claude, Grok, Codex, an…
Cisco Talos published research in August 2026 documenting how cybercriminals use AI coding assistants including Claude Code, Codex, Cursor, and Gemini to build functional malware, primarily through a …
Developer Jon Udell's agent harness Bram uses GitHub issues as a shared coordination channel for Claude Code and Codex agents, with Bram indexing both agents' session files, worklist history, commits,…
AgentSky published a hands-on comparison of Jev Ultrafast (running Jev 1.13) against Codex (running GPT-5.6 Sol at medium thinking level) on a Google Flights search task, with both agents starting fro…
Orchestrat launched a private early-access waitlist for its macOS workspace that coordinates AI coding agents by giving them shared tasks, task ownership, versioned Markdown documents, and live agent …