AI Coding Tools
-
Chrome DevTools ships an official MCP server that lets coding agents control and inspect a live browser
The Chrome DevTools team shipped chrome-devtools-mcp — an official Model Context Protocol server that lets coding agents (Gemini, Claude, Cursor, Copilot) control and inspect a live Chrome browser. It gives agents the full DevTools toolkit for automation, debugging, and performance analysis. ## What an agent can do with it Record performance traces and extract actionable… Continue reading
-
MiniMax M2.7 Highspeed hits 100 tokens/sec — matches Opus 4.6 on coding benchmarks at a fraction of the cost
MiniMax released the Highspeed variant of its M2.7 coding model on May 18 — a latency-tuned version delivering roughly 100 tokens per second versus 60 for standard M2.7, with identical output behavior. It matches or approaches Claude Opus 4.6 and GPT-5 on the hardest coding and agentic benchmarks while running 3x faster and costing a… Continue reading
-
Runtime ships sandboxed coding agents for teams — parallel workflows, ticket integration, approval controls
Runtime launched on Product Hunt — sandboxed coding agents built for whole teams rather than solo developers. YC-backed, founded in 2026 by Gus Trigos and Carlos Volante. The pitch: run coding agents in isolated sandboxes with the guardrails an engineering org actually needs. ## What it does Each agent runs in a sandboxed execution environment,… Continue reading
-
andrej-karpathy-skills hits 1,955 daily stars: a CLAUDE.md that stops AI from breaking your code
Forrest Chang’s andrej-karpathy-skills is the #1 trending repo on GitHub today with 1,955 stars in a single day — and over 220,000 combined across his personal account and the multica-ai organization mirror. It’s a single CLAUDE.md file encoding four behavioral rules derived from Andrej Karpathy’s documented frustrations with LLM coding agents. ## The core rules… Continue reading
-
Cursor Composer 2.5 matches Opus 4.7 on SWE-Bench at 1/10th the cost — Kimi K2.5 base with 85% Cursor RL
Cursor shipped Composer 2.5 on May 18 — an in-house coding agent built on the open-source Kimi K2.5 checkpoint from Moonshot AI, then heavily post-trained by Cursor (roughly 85% of total compute budget went into Cursor’s own reinforcement learning and post-training pipeline). The headline: 79.8% on SWE-Bench Multilingual, matching Claude Opus 4.7 and GPT-5.5 at… Continue reading
-
academic-research-skills hits 1,300 daily stars: a 13-agent research team for Claude Code
Edward Cheng-I Wu’s academic-research-skills hit GitHub trending today with 1,302 stars in a single day. It’s a Claude Code skill suite that covers the full academic research pipeline: research → write → review → revise → finalize. ## What it actually does A 13-agent team with seven operational modes: full, quick, review, lit-review, fact-check, socratic,… Continue reading
-
Semble cuts AI agent code-search tokens by 98% with natural language queries instead of grep
MinishLab released Semble — a code search library purpose-built for AI agents. It returns the exact code snippets an agent needs instead of having grep dump full files into the context window. The result: roughly 98% fewer tokens used per code-search step. Show HN hit 212 points this morning. ## The numbers End-to-end indexing of… Continue reading
-
agent-skills hits 900+ daily stars: a vetted skill registry for Claude Code, Cursor, and 17 other AI coding agents
tech-leads-club’s agent-skills shot to the top of GitHub trending this weekend with 923+ daily stars. It’s a curated, security-hardened skill registry for Claude Code, Cursor, Copilot, Antigravity, Windsurf, Cline, and 13 more AI coding agents. ## The security pitch In an ecosystem where 13.4% of open-marketplace skills contain critical vulnerabilities, agent-skills positions itself as the… Continue reading
-
Zerostack: Unix-inspired Rust coding agent ships at 8MB RAM, 0% idle CPU
Zerostack is an open-source Unix-inspired coding agent written in pure Rust. It hit #1 on Hacker News this weekend with 223+ points. The pitch is unusual: a coding agent that doesn’t bloat your machine. ## The memory story Empty session: ~8MB RAM. Actively working: ~12MB. Compare to JavaScript-based coding agents like Claude Code, which typically… Continue reading
-
Agentmemory：给 Claude Code 装持久记忆，token 用量砍 92%
Agentmemory 是个 MCP 服务器，给 Claude Code、Codex CLI、Cursor、Gemini CLI、Hermes 这些编码 agent 装上跨 session 的持久记忆。它在后台安静跑，自动捕获 agent 做过的事，用 AI 压缩，下次 session 启动时把相关上下文注入回去。不需要手动 save，不用折腾 CLAUDE.md。 ## 数据 GitHub 几天内涨到 5,800+ stars，5 月 13 日冲到日 trending 第 2。Apache 2.0 开源，0.9.9 版本 5 月 11 日发布，npx 一行命令装好。所有数据留在你本地机器上。 ## 内部结构 51 个 MCP tool、6 个生命周期 hook（SessionStart、UserPromptSubmit、PreToolUse、PostToolUse、PreCompact、Stop）、4 个 slash 命令（/recall、/remember、/session-history、/forget）。240 个 observation 的基准测试里，agentmemory… Continue reading
Top AI Product 