Druva announced Druva AI Resilience, a new approach for recovering, governing, and defending AI-powered work, introducing capabilities for Microsoft Copilot, Claude Code, Druva Model Context Protocol …
A Hacker News user reports using OpenAI GPT-5.6 Sol with the Pi coding agent but finds it slower than Claude Code, and asks the community which models others use, including hosted open-source options.…
Ataraxy Labs has released Sem, a CLI tool that parses codebases with tree-sitter to produce entity-level diffs for functions, classes, and methods instead of traditional line-level diffs, addressing t…
Komodor Ltd. announced the immediate availability of Klaudia Memory, a new capability within its autonomous site reliability engineering platform Klaudia that enables its AI assistants to remember and…
Sfora, a new project management platform built entirely around markdown files, launched to let human developers and AI agents collaborate in a single workspace via CLI and MCP. Every task, post, and d…
A developer released unclaude.py, an open-source Git hook that automatically removes Anthropic's Co-Authored-By lines from commit messages generated by Claude Code. The script, available under the Unl…
Anthropic's Claude Code team members Cat Wu and Thariq Shihipar said during a fireside chat at the AI Engineer World's Fair that coding agents have shifted engineering from months-long planning cycles…
A new wave of open-source AI assistants that run entirely on local hardware, with no subscription fees or data leaving the machine, includes MiniCPM Desk Pet, OpenHuman, and Jan AI, which has six mill…
Zhejiang University's Qiushi Engine topped the ResearchClawBench leaderboard, outperforming Anthropic's Claude Code in autonomous research tasks. The benchmark, created by the Shanghai Artificial Inte…
The Model Context Protocol (MCP) introduces a structural problem where developers control only the server middle layer, not the client or model, making failures non-deterministic and hard to debug, ac…
ZigZag, a CLI codebase walker designed to reduce token consumption for AI coding agents, initially made workflows worse because its condensed AST report was larger than the source code it summarized. …
A developer released ChatPanel, an open-source browser side panel that acts as a privacy-first AI agent, allowing users to bring their own models (Codex, Claude Code, local, in-browser, or remote) and…
Anthropic's Fable 5 model achieves 96% of the performance of the full Fable 5 at 46% of the cost when used as an orchestrator that delegates implementation to cheaper models, according to a technical …
A developer building automation infrastructure for shipping personal projects at scale with Claude Code designed a '5% human check' gate to mass-produce long-form X Articles while maintaining quality.…
A developer built Full-Stack Quality Skill, a reusable AI coding skill for full-stack audits, architecture guidance, long-term project memory, and CI quality gates. The skill enables AI agents like Cu…
A developer built a self-learning video editing agent using Claude Skills that can automatically edit a 30-minute video in 10 minutes. The agent separates five core editing tasks into independent Skil…
RubenGlez released Lokalite, a local-first secrets manager for macOS that encrypts API keys, tokens, and credentials in an AES-256-GCM vault stored in Apple Keychain, delivering secrets to AI coding a…
A user's field report of running the open-source tool claude-real-video on 2,181 videos revealed a critical design flaw: percentage-based frame deduplication was structurally blind to small subjects, …
A developer created ubuntu-server-dotfiles (v1.3.0), a one-command bootstrap that turns a fresh Ubuntu 24.04 server into a 24/7 AI development machine. The tool installs a full developer environment i…
A Hacker News user asks the community to compare Claude Code and Codex, seeking opinions on which tool is preferred and why, along with subscription plan details.…