A developer created SinkSeal, a set of git hooks that act as guardrails for AI coding agents. The tool intercepts commits and pushes to catch risky code patterns, such as wiring demo features to produ…
JetBrains' 2026 Developer Ecosystem Survey of over 15,000 developers found that more than half of professional developers now manually write less than 20% of their code, with AI agents generating 46% …
An engineer analyzed 559 public CLAUDE.md files and found that 62.9% of the content is documentation rather than actionable rules, with only 43.5% of actual rules being mechanically checkable. The fin…
Gawkbot, an open-source alternative to xAI's Grok bot, lets users run AI bots locally on their own machines with their own API keys, offering per-action approvals and per-bot tool allowlists to minimi…
A new open-source method called C1 lets users orchestrate multiple frontier AI models on existing subscriptions by pasting their answers into a single merge prompt to produce one document showing agre…
Developer and open-source maintainer Mario Zechner's minimal coding agent Pi has become the author's preferred AI coding harness, offering a command-line environment with only four core tools—read, wr…
A developer proposes storing AI agent skills as tagged documents in a semantic memory store instead of files to prevent skill rot and context bloat. The approach enables automatic versioning, deprecat…
A developer rants on Hacker News that the AWS Management Console is broken for cross-region S3 bucket replication, citing missing monitoring and a batch operation that cannot select source and destina…
A reverse-engineering analysis of the 1992 DOS game Utopia reveals that its Tandy sound driver secretly emulates the ZX Spectrum 128's sound chip, writing to registers via Spectrum port numbers and us…
A developer found that seven of eight custom agents defined in Claude Code had zero invocations over a 30-day period, despite being injected into the system prompt on every request. The unused agent d…
An evaluation by the SLayer team found that an AI agent using the open-source version of Cube, an incumbent open-core semantic layer, solved zero of 10 tasks from the LiveSQLBench-Lite benchmark, whil…
Sidequest, a Kanban board plugin for Claude Code from Eigenwise Toolshed, automates task management by having AI models execute tickets autonomously, with users filing an average of 120 tickets per da…
Developer Chudi Nnorukam released a public MIT-licensed repository, github.com/ChudiNnorukam/claude-code-adhd-skills, containing two Claude Code skills—mirror and librarian—that he runs daily to addre…
LoreConvo, a new tool for AI practitioners, enables coordinated multi-agent handoff, cross-surface persistence, and data portability by storing all session interactions in a local SQLite file, with su…
Anthropic launched Claude Fable 5.1 and Claude Mythos 5.1, with Fable generally available and Mythos limited to vetted cyber defenders and life scientists. Cache reads cost 75% less at $0.25 per milli…
A technical guide from Towards AI details how to configure the unsloth/Qwen3.8-27B-GGUF model in Claude Code via Ollama, emphasizing that Ollama's default context is 4096 tokens and must be overridden…
Anthropic's Claude Fable 5.1 API now rejects requests when prior conversation turns are modified, unless the `prefix_mismatch_behavior` is set to `"drop_block"`, a change enforced by default for new a…
Matt Pocock, a developer and educator, has released a set of AI coding agent skills designed to help engineers use tools like Claude Code and Codex for real engineering work, addressing common failure…
OpenClaw 2.0, released on August 31, introduces multiplayer AI agent sessions, allowing multiple users to collaborate in real time on a single live agent session with granular permissions, and rebuild…
Superagent, a free and open-source Mac app for coding agents, launched with MIT licensing and Apple notarization, offering a real browser, an iPhone simulator, and persistent chats that work with Clau…