Condense.chat launched a public context-compression proxy for AI coding agents that reduces API bills by up to 72%. The proxy sits between agents and upstream models, compressing repeated context in l…
OpenAI fine-tuning team members Will Hang and Wenjie Zi presented on Agent RFT, a method to enhance agent performance through reinforcement learning. They discussed how agents interact with tools and …
Conductor released version 0.72.0 with a new algorithm that more accurately identifies and collapses less important agent messages, especially for Claude Code background agents. The update also adds t…
Exe.dev announced that users can now connect their ChatGPT subscription to the platform, enabling the use of OpenAI models with the coding agent Shelley. The integration is configured via the LLM inte…
SpaceX's $60 billion acquisition of AI coding startup Cursor raises questions about whether the platform will continue offering models from rival labs Anthropic and OpenAI. Cursor hopes to remain mode…
Paul Bakaus, creator of the open-source design skills system Impeccable, argues that AI agents require human steering and domain-specific vocabularies rather than one-shot design. He advocates for ski…
Codex and Claude Code are competing AI-powered developer tools from OpenAI and Anthropic, respectively, each using state-of-the-art models to read and modify entire codebases. The article compares the…
An open-source CLI tool called ghealth wraps the Google Health API v4, exposing 40 verified data types such as sleep, heart rate, and steps as structured JSON for use in terminals and AI agents. The t…
OmniRoute, an open-source AI gateway, has released version 3.8.42, enabling developers to connect to over 236 AI providers through a single API endpoint. The tool offers automatic failover, token comp…
Developer pdumicz released Secret Shuttle, a local bridge that lets AI coding agents use secrets like API keys without ever seeing the plaintext values. The tool stores secrets in a local daemon vault…
OpenAI now allows ChatGPT Plus subscribers to use their $20/month plan inside third-party coding agents like Pi and OpenCode, effectively providing $100–$200 worth of tokens. However, the policy is no…
OpenAI announced GPT-5.6 Sol, Terra, and Luna on June 26, but access is limited to a small group of trusted partners via Codex and the API at the request of the U.S. government. The model family featu…
A developer released Ur-Agent-Team, an open-source, local-first agent hub that coordinates multiple AI agents on a single machine. The hub allows any connected agent to act as the system's brain, assi…
A developer spent nearly $200 in GitHub Actions CI costs overnight after AI-generated test suites and unowned test fixtures caused 49 out of 168 CI runs to fail, revealing brittle test infrastructure …
SelectPdf has released a free, open-source (MIT) set of Agent Skills called SelectPdf AI Tools that prevents AI coding assistants from hallucinating PDF API methods. The tools provide accurate, versio…
AI agents in data engineering should be structured with a deterministic correctness layer to ensure reproducibility and trust, according to a new analysis. The article outlines three levels of AI agen…
OpenAI announced its first hardware product, the Codex Micro, a macro pad built with Work Louder for users of its AI coding tool Codex. The device, teased on July 15, is a niche accessory for develope…
OpenAI introduced native sandbox execution and a SandboxAgent harness in its Agents SDK on April 15, 2026, while Cloudflare released the Dynamic Worker Loader in open beta on March 24, 2026, for ephem…
AI coding tools like Anthropic's Claude and OpenAI's Codex are reshaping software engineering, splitting developers into enthusiasts, skeptics, and those in between. A Stack Overflow survey found near…
A developer created Ask My Health, a local MCP server that lets AI agents like Codex read Apple Health data and schedule Apple Watch workouts via an iPhone bridge. The tool exposes HealthKit and Worko…