A developer built memcp, an open-source tool that unifies session logs from multiple AI coding agents like Claude Code and Codex CLI into a single local SQLite database, enabling cross-agent memory sh…
Amdb, a zero-runtime, single-binary code context MCP server that indexes codebases entirely on the local machine with combined graph and vector retrieval, has been released as an open-source tool. The…
Andrej Karpathy, who coined the term 'vibe coding,' said on the No Priors podcast in March 2026 that he has not typed a line of code since December 2025, reflecting a dramatic shift in software engine…
A developer discovered that asking Claude Code 'who are you' triggered a 118,693-byte request, with the actual 19-byte question comprising just 0.016% of the payload. The bulk consisted of 38 tool JSO…
A set of Claude Code PreToolUse hooks blocks specific Bash command patterns that duplicate built-in Claude Code tools, such as find with -exec or piped grep, sed -i, and cat/head/tail on single files,…
Developer Danilo Znamerovszkij built and open-sourced a pipeline that turns a single photo of handwriting into an installable TTF font. The tool runs locally with no system dependencies, using npm lib…
Letta released the open-source trajectory package on July 24, 2026, a standard format for recording coding-agent sessions across harnesses including Claude Code, Codex, and Letta Code. The package red…
A developer discovered that a timezone bug in the tool claude-code-notify was invisible to local tests because the test expected values were derived from the same host-local timezone as the buggy code…
A developer building a Telegram notification tool for Claude Code discovered that the tool silently failed to detect usage limits because it read the session transcript before Claude Code finished wri…
A developer created a Gmail CLI tool for Claude Code that provides multi-account Gmail access via the command line. The tool uses the Google Gmail API directly and supports multiple accounts through s…
A developer built a self-auditing loop for Claude Code that detects environmental degradation from conversation transcripts and triggers automatic repairs. The script, running weekly via launchd, moni…
A developer built an AI Skill that generates production-ready GitHub Actions workflows with zero configuration errors. The skill enforces 12 quality gates, 5 decision templates, and 3 mandatory securi…
The AI boom is straining family dynamics, particularly in the Bay Area, where many men work in AI while their partners feel neglected and overwhelmed by the technology's dominance in their lives. One …
AI agent tool calling has converged on open protocols like MCP, function calling, and A2A, but scaling to multi-user production agents introduces new bottlenecks in tool quality, context efficiency, m…
Druva announced Druva AI Resilience, a new approach for recovering, governing, and defending AI-powered workloads, with new capabilities for Microsoft Copilot, Claude Code, Druva Model Context Protoco…
Developer danilo-znamerovszkij has open-sourced a pipeline that converts handwriting photos into TTF fonts using npm, with a Claude Code skill wrapper that automates vision labeling and local build. T…
Anthropic's Fable 5 is the most capable Claude Code model, but setting it as the default is a trap because it cannot stop thinking and thinking is billed as output, leading to unexpectedly high costs.…
Promptforce.ai launched Prefex, a local-first proxy that bundles over a dozen LLM cost-optimization techniques into a single Go binary for Claude Code and OpenAI-compatible APIs, claiming to reduce sp…
A developer created a Claude Code skill that rewrites the previous response into a skimmable format. The skill restructures content with numbered steps, concrete next actions, and specific time estima…
Tencent's WorkBuddy Bench leaderboard shows no single model dominates agentic coding tasks, with Claude Opus 4.8 leading five of eight scored columns, GLM-5.2 leading two, and GPT-5.5 leading one. The…