Tech News
← Home  ·  All topics

Claude Code

43 GoKawiil briefs on this topic

Researchers reverse-engineer Claude Code Web's hidden Firecracker-based hosting platform

Engineers building the ArcBox sandbox platform used standard Linux debugging tools like strace and objdump inside a live Claude Code Web session to inspect its runtime. They discovered the environment runs on Firecracker microVMs, identical to the technology behind AWS Lambda and Fargate, complete with hardcoded ACPI signatures, minimal 4-vCPU/16GB instances, and an unstripped Go binary called environment-manager pointing to a previously undocumented Anthropic internal deployment platform.

Open-source library gives AI coding agents 501 trading-infrastructure skills

A new open-source project called Algo-Trading-Skills packages 501 reference implementations covering algorithmic trading engineering, spanning 16 technical domains and five regulatory/exchange frameworks. Each skill is backed by unit tests (over 20,000 total) and follows the agentskills.io SKILL.md standard, making it usable by Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, and similar tools. It's released under Apache 2.0 and explicitly framed as engineering guidance, not financial or compliance advice.

Simulation of 91,874 real agentic-LLM requests shows LRU still beats proposed KV-cache alternatives

A researcher replayed 68,266 requests from 393 Claude Code sessions and 23,608 Mooncake requests through a custom prefix-cache simulator, testing three approaches meant to outperform the standard LRU eviction policy used by vLLM, SGLang, LMCache and Mooncake Store. None of the alternatives beat the default LRU-over-radix-leaves baseline, and the analysis found that cache misses mostly come from rapid, seconds-apart tool-calling loops rather than sessions timing out after going idle.

Developer Mayuki recreates Windows 3.1 Program Manager using Claude AI in under an hour

Developer Mayuki used Claude to vibe-code ReProgman, a lightweight clone of the classic Windows 3.1 Program Manager shell that ran until Windows 95 replaced it in the mid-1990s. The 12-16MB tool requires no installation, runs on both Windows 11 and Apple Silicon Macs via .NET SDK 10.0+, and has been published on GitHub under the MIT license.

Omarchy pairs Arch Linux with built-in AI coding agents for easier setup

Omarchy is a Linux distribution built on Arch that automates installation and configuration while integrating multiple AI coding agents such as Claude Code, GitHub Copilot CLI, and Grok CLI directly into the desktop. Users can pick a default agent to debug system issues, tweak settings, or build apps and themes, and can also run local models via LM Studio or Ollama. It targets developers on modern x86-64 hardware, though it can run on older machines too.

OtoDock launches self-hosted 'company OS' built on Claude Code and Codex agents

OtoDock is a new self-hosted platform that lets businesses build AI agents—like a Personal Assistant, System Admin, or Marketing Manager—powered by Claude Code and OpenAI Codex using a company's own API subscriptions or local models. Each agent has six configurable parts: persona, memory, workspace, knowledge base, and skills, and can be shared across teams or kept private depending on one of four operating modes. Users interact through a self-hosted dashboard or even by phone, and the system supports multi-tenant use so multiple employees can work with the same agents.

New CLI tool 'geiger' audits every AI agent and MCP server on a computer

A developer released geiger, a free command-line utility that scans a machine for installed AI agents, harnesses, MCP servers, plugins and extensions, then reports in plain language what each one can access. It runs via npx with no installation or account required, only reads configuration files and directories, and writes nothing to disk unless a JSON export is explicitly requested.

Anthropic confirms stolen session keys let hackers drain Claude subscribers' tokens

UK-based AI consultant Grant de Swardt found his Claude Max subscription burning through tokens even when he wasn't using the service. Anthropic investigated and told him a compromised session key had been used to generate unauthorized OAuth tokens, allowing a third party to consume his allotted usage. The company suspended his account, wiped his active sessions, and issued a partial refund but could not explain how the credentials were obtained.

Anthropic Tops Fast Company's 2026 Best Workplaces for Innovators List

Anthropic has been ranked No. 1 on Fast Company's Best Workplaces for Innovators 2026 list, with recognition tied partly to Claude Code, a tool originally built internally for engineers to test AI models and assist with coding. The tool spread organically inside the company before Anthropic released it publicly in early 2025, later evolving into the broader Claude Cowork product launched in early 2026.

Author explores Git worktrees after seeing AI coding agents rely on them

A developer describes discovering git worktrees—a decade-old git feature they'd never used—after noticing tools like Claude Code create a separate worktree for each task so multiple AI agents can work on the same repository in parallel. The piece explains that worktrees let you check out multiple branches into separate working directories simultaneously, all sharing the same underlying repository data, unlike traditional branch switching which requires stashing and checking out.

Claude Code and Instinct run mobile AI agents inside dedicated microVMs

Coding assistants like Claude Code, Instinct, and Poke are shifting from local machines to cloud-hosted virtual machines so they can be accessed from phones. Inspection of Claude Code's setup shows it runs inside a Firecracker microVM with a custom Rust-based init process controlling the session over a vsock connection, while inference calls go out through a locked-down, MITM'd egress gateway to Anthropic's servers.

Engrim launches as local-first SQLite memory layer for AI coding agents

A new open-source tool called Engrim gives AI coding assistants persistent, project-level memory stored in a local SQLite database rather than tied to any single vendor's cloud. It lets developers switch between tools like Claude Code, Cursor, Windsurf and Google Antigravity mid-project while retaining architectural decisions and constraints, using a hybrid search combining SQLite FTS5 keyword search with lightweight vector embeddings. The creator reports it was validated over 105 sessions on a 50,000-line trading codebase with zero regressions and no loss of context across model switches.