Bookmarks

A unified storage SDK for object and blob backends. One small, honest API. Web-standards I/O. An escape hatch when you need the native client.

A unified storage SDK for object and blob backends. One small, honest API. Web-standards I/O. - haydenbleasel/files-sdk

Operations chief Andrew Macdonald said he's not seeing proportional productivity gains from increasing AI costs within Uber.

A recursive evidence-gated cognitive runtime for memory-native AI agents, combining hybrid retrieval, temporal reasoning, async learning, and plug-and-play tools. - quarqlabs/agent-oss

Fast, stateless CLI for web search and scrape. Built for AI agents. - 1broseidon/ketch

Peaceful task list meticulously crafted for Agents in war mode. - scarce/axel

Queue tasks, dispatch to Claude/Codex/OpenCode, manage permissions from one inbox. Native macOS app.

⚡ Rust/WebAssembly image processing library. Contribute to silvia-odwyer/photon development by creating an account on GitHub.

omo; the best agent harness - previously oh-my-opencode - code-yeongyu/oh-my-openagent

A lot of people seem convinced that the point of AI coding is to write low-quality code as fast as possible. Spew out barely-passable slop, open massive PRs, and merge them unvetted. Ship it! But t…

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10. - microsoft/age...

I’m calling it now, the adoption of AI agents into software development will be one of the most costly mistakes in the field’s history. Agents cannot program, and it’s taking longer and longer to realize that they can’t. They are a highly sophisticated statistical model designed to mimic the distribution of programming. The output is broken, but in a way that’s getting harder and harder to detect. Which is exactly what you’d expect from an increasingly accurate statistical model.

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks. - microsoft/Webwright

Contribute to webhooked/kanso.nvim development by creating an account on GitHub.

I built ZIP Shrinker, a little browser tool to shrink ZIP files. It also works with formats that are secretly ZIPs underneath, like EPUB, and JAR.

Token efficient IDs for AI agents. UUID alternative for the agentic era - vostride/id-agent

A video wallpaper engine for macOS Tahoe. Contribute to kageroumado/phosphene development by creating an account on GitHub.

Clipboard Manager for macOS. Contribute to yarasaa/Clippy development by creating an account on GitHub.

Quick warning before you read: this isn't a launch announcement. It's a story about getting...

Rails actions do not return HTTP responses. They perform response state that Rails turns into status, headers, and body.

2026-07-28 MCP 仕様リリース候補の最も大きな変更点は、MCP サーバーがステートレスファーストになることです。これにより、MCP サーバーはシンプルなロードバランサーの背後でスケーリングできるようになります。また `Mcp-Method` ヘッダに基づいたトラフィックのルーティングや、サーバー応答のキャッシュなども可能になります。この記事では 2026-07-28 MCP 仕様リリース候補におけるステートレスなプロトコルの変更点について紹介します。

Models.dev is a comprehensive open-source database of AI model specifications, pricing, and features.

Universal Rust multiplexer with a typed SDK — drive any CLI or TUI app from code. Native on Linux, macOS, and Windows. - Helvesec/rmux

Starting more agents is easy now. However, more agents running doesn't mean more of you available - your cognitive bandwidth doesn't parallelize. All the jud...

Contribute to hamsterbase/tasks development by creating an account on GitHub.

Data retrieval for Markdown files. Think Dataview without Obsidian. Works on macOS and Linux. - rhsev/grubber

雑コラ作ろうと思って力尽きた… tflat github.com ルートモジュールから参照しているモジュールのresourceを展開するツール。movedブロックも自動定義する。 Example # main.tf module "web" { source = "./modules/web" bucket = "my…

Lightweight (7MB) Terminal-first AI-native dev workspace - crynta/terax-ai

Terax is a lightweight AI terminal with a built-in editor, AI agents, voice input, and live web preview. 7 MB on disk, 300 ms cold start. Free and open source. BYOK or fully local via LM Studio.