Full-text search across 58474 articles. Combine with topic and date filters; results sorted by relevance.
Franz Enzenhofer released chrome-tab-group-cleaner, an open-source tool that bulk-deletes saved tab groups in Chrome, addressing the 71 saved groups left behind by Claude Code in his browser. The tool, available as a Cla…
A developer built vibestretch, a Claude Code plugin that nudges users to stretch during long waits for their coding agent, after exploring and rejecting the idea of selling ads in the terminal. The plugin tracks idle tim…
Bold Software released Shelley, a mobile-friendly, web-based, multi-conversation, multi-modal, multi-model, single-user coding agent, available for download via GitHub releases or Homebrew. Shelley is built for but not e…
A developer has released AMB, an open and preregistered benchmark that tests whether memory layers in coding agents improve real coding work, using executable tests to grade artifacts in a sandboxed repository. The publi…
A new arXiv paper (2608.28905v1) finds that off-policy evaluation (OPE) for semantic ID recommenders can be made feasible by using the model's own code hierarchy as an action abstraction, but the benefit comes from coars…
Relace reports that search consumed more than half the tokens across 1,200 coding agent traces, and a dedicated retrieval model achieved 0.71 Recall@k while a compaction pass cut one real trace by 55 percent, while Incep…
Anthropic has made auto mode the default in Claude Code for Pro, Max, and Team plans, enabling longer-running autonomous work and catching more dangerous commands, according to a blog post by Claude. Users on a forum dis…
The WUIC Assistant, an agentic VS Code plugin built on the WUIC framework, improved its local coding agent by applying Direct Preference Optimization (DPO) to a 30B-parameter model served via Ollama. The team fixed two e…
Sonde, a local code-context engine for AI coding agents, claims to match agentic search recall on structural tasks while using 3x less context, 8x fewer tool calls, and 147x less wall-clock time, based on benchmarks on a…
A developer proposes that coding agents maintain a plain-text journal file in the working directory to remember actions across sessions and context compactions, with the pattern described as simple markdown files per ses…
Retrieving the correct code for agentic software development lifecycles (SDLCs) presents three major problems, according to an unnamed source: similarity is not relevance, capacity is not attention, and gullibility. Thes…
Envault, a new open-source tool from developer MildyNora, provides a local, encrypted vault that lets coding agents like Claude Code, Codex, and opencode use API keys and secrets without ever seeing the plaintext values.…
Beckon, a new open-source tool by developer Isa1asN, assigns distinct sounds to an AI coding agent's lifecycle events so developers can know whether to look, unblock, wait, or read an error without watching the terminal.…
Kontext Security released Sandy 0.1.x, an experimental sandbox for AI coding agents that restricts agent access to a project without requiring a container or VM, and it has not completed an independent security audit. Sa…
Anthropic's Claude Opus 5 makes writing code nearly free, shifting the bottleneck to reviewing AI-generated changes, as the model's scope expansion is 'expected behavior' per Anthropic's documentation. The article recomm…
Shopify CEO Tobi Lütke signaled on Twitter that the company is considering banning Claude Code from enterprise use, citing unspecified security, governance, or productivity concerns. The statement reflects growing enterp…
A new analysis by an industry observer argues that agentic coding will not replace junior engineers because three of four necessary conditions are unmet, citing METR's finding that frontier AI systems succeed less than 1…
Postman Blog argues that AI coding agents fail not because of small context windows but because they lack a knowledge graph of code, APIs, and vendors, emphasizing the need for context graphs to improve performance.
Developer Ruvian Fabrin has built Cerne Code, a free, open-source desktop coding agent that runs 100% locally, compatible with Ollama, llama.cpp, LM Studio, and any OpenAI-compatible API. The agent can read, edit, and cr…
Antigma Labs released Ante, a self-contained coding agent that runs as a single Rust executable with zero runtime dependencies, claiming the #1 same-model agent on Terminal-Bench 2.1 and using ~7× less peak memory, ~9× l…