A developer building the Scarab diagnostic suite found that AI coding agents like Codex drift into unwanted fixes when given too much uncertainty. By tightening the diagnostic workflow to handle more …
Databricks open-sourced Omnigent, a meta-harness that sits above existing AI agents to enable composition, control, and collaboration. The tool addresses the fragmentation of agent harnesses by provid…
Fighter90 released career-ops-ui v1.69.2, a local-first web dashboard for the open-source AI job-search pipeline career-ops. The tool runs entirely on the user's machine with no cloud accounts or tele…
Microsoft and three Chinese universities developed SkillOpt, a method that optimizes instruction documents for AI agents using principles from traditional model training. A simple Markdown file booste…
A developer open-sourced Bottega, an internal agent orchestration tool used to manage coding agents, after reporting that 100% of their production code has been written by agents for the past 8 months…
Loop engineering is emerging as a new paradigm for working with coding agents, where developers design recursive systems that autonomously prompt agents rather than writing prompts manually. Industry …
A developer proposes a pattern for delivering overnight agent reports to a private, end-to-end encrypted inbox using the Agent Relay CLI, which encrypts files client-side before upload. The approach a…
A developer is building AccInt, a local Work Model for agent-run work that aims to determine what an AI coding agent should learn after a failed run. The project focuses on capturing settled commitmen…
OpenAI and Anthropic released a series of new tools and standards for building AI agents in 2025, including OpenAI's Responses API, Agents SDK, AgentKit, and Codex, as well as Anthropic's Model Contex…
A developer has built AccInt, a local work loop for AI coding agents that implements a Work Model to track context, decisions, failed attempts, and outcomes. The system uses late-interaction retrieval…
A developer built skillscore, an open-source Dart CLI that statically analyzes SKILL.md files for AI agents and scores them 0–100 based on 24 rules derived from official authoring guides. The tool run…
Agent Joe, an open source TUI-based coding tool limited to Rust and without shell access, has been released on GitHub. The tool aims to improve security by preventing arbitrary command execution and f…
Vercel released AI SDK 7 with HarnessAgent, an experimental API that provides a unified programming model for running coding agent harnesses like Claude Code, Codex, and Pi harness, supporting sandbox…
A developer has published a recipe for writing effective Flutter agent skills, synthesizing official guidance from Flutter, Anthropic, Google, and OpenAI into a single copy-pasteable format. The recip…
OpenAI introduced flexible rate-limit resets for its Codex coding agent, allowing users to bank and manually trigger resets instead of losing them on a fixed schedule. Users on Go, Plus, Pro, and Busi…
Nango and Codex released a guide for building a customer-facing Google Sheets API integration in about an hour, addressing challenges like OAuth setup, rate limits, and the lack of webhooks. The integ…
Tenet Security researchers disclosed a new supply-chain attack called "Agentjacking" that tricks AI coding agents into executing attacker-controlled code by injecting malicious error events into Sentr…
A new open-source tool called cost-xray captures the actual local API traffic for AI coding agents Claude Code and Codex, attributing tokens and costs down to individual sources like system prompts, t…
Anthropic's Fable 5 model has become the company's most "honest" model to date, frequently telling users it is being honest in its responses. A user who indexed 202,381 messages from local Claude Code…
OpenAI acquired Ona, the company formerly known as Gitpod, on Thursday to integrate its secure cloud platform into the Codex coding agent. The deal gives OpenAI’s enterprise customers the ability to r…