惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 聂微东
罗磊的独立博客
S
SegmentFault 最新的问题
The GitHub Blog
The GitHub Blog
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
L
LINUX DO - 最新话题
Webroot Blog
Webroot Blog
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
Microsoft Azure Blog
Microsoft Azure Blog
GbyAI
GbyAI
T
Tenable Blog
Help Net Security
Help Net Security
WordPress大学
WordPress大学
H
Heimdal Security Blog
SecWiki News
SecWiki News
V2EX - 技术
V2EX - 技术
C
CERT Recently Published Vulnerability Notes
P
Privacy International News Feed
T
Tailwind CSS Blog
L
LINUX DO - 热门话题
Scott Helme
Scott Helme
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
O
OpenAI News
Latest news
Latest news
月光博客
月光博客
L
LangChain Blog
Google DeepMind News
Google DeepMind News
爱范儿
爱范儿
I
InfoQ
T
Threat Research - Cisco Blogs
人人都是产品经理
人人都是产品经理
Forbes - Security
Forbes - Security
Recent Commits to openclaw:main
Recent Commits to openclaw:main
博客园_首页
雷峰网
雷峰网
T
Tor Project blog
Security Archives - TechRepublic
Security Archives - TechRepublic
G
GRAHAM CLULEY
Project Zero
Project Zero
MyScale Blog
MyScale Blog
V
V2EX
Vercel News
Vercel News
F
Fortinet All Blogs
The Register - Security
The Register - Security
N
News and Events Feed by Topic
P
Palo Alto Networks Blog
H
Hacker News: Front Page
Application and Cybersecurity Blog
Application and Cybersecurity Blog
博客园 - 司徒正美

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店 GitHub - EdoardoBambini/Agent-Armor-Iaga: AI agents are getting tool access — shell, file system, databases, APIs, secrets. But **nobody is governing what they actually do with it**. Frameworks like LangChain, CrewAI, AutoGen, and Claude Code give agents the power to execute. Agent Armor gives you the power to control, audit, and approve every single action before it happens. HN Vibes — Week 15, Apr 7–13 2026 GitHub - chojs23/ec: Easy terminal-native 3-way git mergetool vim-like workflow GitHub - SethPyle376/hiraeth: Local AWS emulator focused on fast integration testing, with SQS support, SQLite-backed state, and a debug-friendly web UI. GitHub - JakOb-dotcom/cloud-sandbox-security-analysis: Technical analysis and Proof of Concept (PoC) regarding environment variable exfiltration in containerized cloud sandboxes via side-channel data leaks. Springboards - Flint Alpha Show HN: A simpler coding agent harness GitHub - audiodude/sudomake-friends GitHub - 256thFission/mini-mythos: OSS clone of Anthropic’s Mythos harness to locate C/C++ memory vulnerabilities Show HN: OpenParallax: OS-level privilege separation for AI agent execution Hacker News Sorted - Chrome 应用商店 Show HN: How to Install Docker on Ubuntu 24.04 LTS: Complete 2026 Guide GitHub - himanshudongre/smriti GitHub - sverrirsig/claude-control: macOS desktop dashboard for monitoring and managing multiple Claude Code sessions GitHub - ory/dockertest: Write better integration tests! Dockertest helps you boot up ephermal docker images for your Go tests with minimal work. Chiral - Chrome 应用商店 Show HN: Two Claudes collaborating through shared memory on a $100 mini-PC GitHub - pmichaillat/latex-cv: Minimalist LaTeX template for academic CVs GitHub - oguzbilgic/posse: A web UI for Anthropic Managed Agents. GitHub - sshiraz/depsly: Dependency risk analysis tool for npm packages ABI Add safari/agent-harness — Safari browser automation via safari-mcp by achiya-automation · Pull Request #212 · HKUDS/CLI-Anything GitHub - Halfblood-Prince/trustcheck: Verify PyPI package attestations and improve Python supply-chain security GitHub - oguzbilgic/kern-ai: Agents that do the work and show it. GitHub - bruits/satteri: High-performance Markdown and MDX processing for the JavaScript ecosystem GitHub - tylergibbs1/feedstock: High-performance web crawler and scraper for TypeScript, powered by Bun and Playwright GitHub - Grimm67123/grimmbot: The self-improving sandboxed and open-source AI agent. With persistent memory and scheduling. GitHub - whitevanillaskies/whitebloom: Local whiteboard that blooms. GitHub - hwdsl2/docker-whisper: Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64). GitHub - yisding/reviewwiggum GitHub - MarwanAlsoltany/serrors: Structured errors for Go: sentinel hierarchies, typed data, custom formatting, and slog integration. GitHub - soatok/age-php GitHub - Luthiraa/markitme GitHub - stagas/rtdiff: realtime git diff gui and AI-assisted commits GitHub - tombedor/excalicharts GitHub - wh1le/excalidraw-edit: Open and edit .excalidraw files from the terminal. Offline, auto-saves to disk. MalExt Sentry - Malicious Extension Scanner - Chrome 应用商店 GitHub - syi0808/asciianimesvg: Generate animated ASCII art SVGs from text. CLI, Rust library, WASM, and web editor. GitHub - zaina-ml/ml_forge: A visual-based graph node editor for training computer vision models. GitHub - anakin87/llm-rl-environments-lil-course: 🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models GitHub - takaakit/superpowers-uml: Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling. AdriByte Studio - Sviluppo Web e Soluzioni Digitali GitHub - chouligi/angel-copilot: Your personalized Angel Investment Advisor Show HN: MoodSense AI (ML and FastAPI and Gradio, Deployed on Hugging Face) Moodsense Ai - a Hugging Face Space by aman179102 GitHub - agenteractai/lodmem: Level Of Detail Context Management for Agents GitHub - ostefani/subnetlens: A fast, concurrent network scanner with a TUI and plain-text CLI, built in Go. It discovers live hosts on your network, scans their open ports, resolves hostnames, and fingerprints operating systems—delivered. Cyber Pulse: Agentic Intel - Apps on Google Play Whisper API: Self-Hostable Speech to Text Transcription The Agent-Web Protocol Stack: A Research Thesis GitHub - msmarkgu/RelayFreeLLM: A restful API designed to route user prompts to various AI model providers. Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs Show HN: Pardonned.com – A searchable database of US Pardons GitHub - patrickdappollonio/dux: Dux is a terminal UI that lets you run multiple AI coding agents side by side, each in its own git worktree, with full companion terminals, macros, commit generation, and a command palette that knows more tricks than you do. kMC Crystal Simulator Show HN: HyperFlow – A self-improving agent framework built on LangGraph GitHub - stef41/vibescore: 🎵 Grade your vibe-coded project. One command, instant letter grade across security, quality, dependencies, and testing. GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. imgur.com GitHub - visionscaper/collabmem: Enabling long-term collaboration with Agentic AI - building up episodic and world model memory over time with in-context awareness 在 Steam 上购买 FriedrichAI: Offline AI 立省 10% GitHub - atripati/ark: AI Runtime Kernel — a context operating system for AI agents. Eliminates tool bloat, loads only what’s needed, and gives LLMs their reasoning space back. GitHub - nowork-studio/toprank: Open-source Claude Code skills for SEO, SEM, Google Ads GitHub - tacomanator/sash: Lightweight macOS menu bar app for reliably cycling through windows of the current application. Appents | Social Media Management for Product-First Teams GitHub - pnhoang/youtube-spam-blocker: Automatically detects and hides spam messages in YouTube Live chat. Set rate limits, keyword filters, and block repeat offenders. GitHub - decisionnode/DecisionNode: CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable. GitHub - AvaCodeSolutions/django-email-learning: An open source Django app for creating email-based learning platforms with IMAP integration and React frontend components. The $100K Gap in Kubernetes Security Tooling Function Calling Harness: From 6.75% to 100%
GitHub - erkandogan/doom-in-claude-code
redoh · 2026-04-27 · via Hacker News: Show HN

Play Doom inside Claude Code. The actual Doom engine renders to your status line, you move by typing keys into the chat box, and an MCP server lets Claude itself play the game.

┌───────────────────────────────────────────────┐
│  Claude Code                                  │
│                                               │
│  you: wwwf                                    │
│  claude: ...                                  │
│                                               │
│  [ status line below renders real Doom here ] │
│                                               │
│  ┌─────────────────────────────────────────┐  │
│  │ DOOM E1M1   HP 87  ARM 0  PISTOL 34/200 │  │
│  │ ▓▓▓▓▓▓▓▓▓▓▓  █▓▓▓▓▓█  ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ │  │
│  │ ▓░▒▒░▒▓░░▓▓  ▓░▒░░░▓  ▓▓▒▒░░▒▒▒░░░▒▒▓▓ │  │
│  │ ... (28 rows of chafa-rendered frame) . │  │
│  └─────────────────────────────────────────┘  │
└───────────────────────────────────────────────┘

What this is

Four native Claude Code surfaces cooperate to host a real Doom game:

Surface Role
Status line (refreshInterval: 1) Renders each frame as ANSI art in the bottom bar
UserPromptSubmit hook Captures your keystrokes (w, a, s, d, f, ...) from the chat input
MCP server Exposes doom_look, doom_move, doom_state, etc. so Claude can play
Slash command /doom Controls the daemon (start, stop, status, preset, render mode, gamma)

A background daemon holds the game state. Two daemon backends are provided:

  • doomgeneric backend — real Doom. Built from doomgeneric, wrapped with a tick-on-demand controller. C + Makefile, requires a toolchain.
  • stub backend — a pure-Node fake Doom that implements the same file contract. Works out of the box without compiling anything. Use it to verify the integration.

Architecture

                ┌─────────────────────────────────────────┐
                │  daemon (doomgeneric OR stub)           │
                │  ─ reads:  /tmp/doom-in-claude/input.fifo│
                │  ─ writes: frame.ansi, frame.png,       │
                │            state.json                    │
                └──────┬────────────┬──────────────┬──────┘
                       │            │              │
               ┌───────▼──┐  ┌──────▼─────┐  ┌─────▼──────┐
               │Status    │  │UserPrompt- │  │MCP server  │
               │line      │  │Submit hook │  │(stdio)     │
               │(display) │  │(your keys) │  │(Claude's   │
               │          │  │            │  │  tools)    │
               └──────────┘  └────────────┘  └────────────┘

All four Claude Code surfaces are documented, stable extension points. The daemon is an ordinary background process.

Install

Requires: macOS or Linux, bash, node >= 18, jq, perl (for the byte-stability normalizer), and (for real Doom) gcc/clang + make. Also recommended: chafa (brew install chafa) — the default renderer.

git clone https://github.com/erkandogan/doom-in-claude-code.git
cd doom-in-claude-code
./install.sh

The installer:

  1. Copies the status line script, hook, slash command, and MCP server to ~/.claude/.
  2. Patches ~/.claude/settings.json to register statusLine, hooks.UserPromptSubmit, and the doom-in-claude MCP server.
  3. Attempts to build the doomgeneric backend. If the build fails or gcc is missing, falls back to the stub backend.
  4. Installs the doom-in-claude CLI to ~/.local/bin/.
  5. Downloads the Freedoom WADs (GPL, free to redistribute).

Uninstall with ./install.sh --uninstall.

Recommended setup

The default install gives you a playable Doom that's stable for most play sessions. A few tweaks make it more stable and more legible. None are strictly required.

1. Recommended play command

/doom start --gamma 0.7
  • Default renderer: chafa with 256-color palette + ordered dither — half the per-cell SGR byte cost of TrueColor, drift-resistant under heavy scene changes (damage flashes, fireballs). This is the main drift mitigation and it's on by default.
  • --gamma 0.7: lifts Doom's dark corridor values out of the single "black cube entry" so walls and textures are legible. Without it, dark rooms can collapse to monochrome. Range 0.5–1.0, 0.7 is the sweet spot.

2. Optional: run Claude Code inside tmux for bulletproof stability

Claude Code's Ink-based renderer maintains an internal cell-diff cache that can occasionally drift under heavy scene changes (big damage flashes, sudden full-screen color swaps). The default renderer's byte-stability + static anchor border + lower frame rate keep this rare. If you want it impossible, run Claude Code inside tmux — tmux re-parses ANSI into its own canonical grid and re-emits cleanly, absorbing any drift from Ink.

Your ~/.tmux.conf:

set -g default-terminal "tmux-256color"
set -sa terminal-overrides ",xterm*:Tc"
set -sa terminal-overrides ",iterm*:Tc"
set -sa terminal-overrides ",kitty*:Tc"
set -sa terminal-overrides ",ghostty*:Tc"
set -sa terminal-overrides ",alacritty*:Tc"
set -sa terminal-features ",*:RGB"
set-environment -g COLORTERM "truecolor"

3. If you go tmux: restore TrueColor for Claude Code's UI

Claude Code has a defensive clamp to 256-color when $TMUX is set. Without the following, Claude's own TUI colors look muted inside tmux:

# Add to ~/.zshrc (or ~/.bashrc)
export CLAUDE_CODE_TMUX_TRUECOLOR=1

This restores TrueColor for Claude's TUI. The Doom frame still renders in 256-palette regardless (that's intentional for drift resistance), but Claude's prompt / diff / syntax highlighting use the full gamut.

See anthropics/claude-code#46146 for the env var reference.

Usage

In a Claude Code session:

/doom start --gamma 0.7    # start the daemon with recommended settings
wwwasdw                    # type keys as a single prompt → you move
/doom look                 # print the current frame
/doom stop

Input language

The hook interprets chat submits as Doom commands whenever the daemon is active:

Prompt Action
w / a / s / d forward / strafe-left / back / strafe-right
q / e turn left / turn right
f fire current weapon
space or u use (open door, press switch)
digits 1..7 switch weapon
a run of characters each char is one action, executed in order (wwwf = walk 3 then fire)
rush, retreat, ... named macros from ~/.claude/doom/macros.json
go <n> let n ticks elapse with no input (enemies move)
anything else passes through to Claude as normal

Letting Claude play

With the MCP server running, the full tool surface is:

  • doom_state — game state JSON (hp, armor, weapon, ammo, position, killcount, map, tick)
  • doom_look — current frame as PNG (Claude can see the scene)
  • doom_move — send keys
  • doom_burst — send multiple key sequences in order
  • doom_wait — advance N ticks with no input
  • doom_macro — run a named macro
  • doom_start / doom_stop / doom_status — daemon lifecycle

A prompt that reliably gets Claude through E1M1 is in docs/claude-play.md.

Coach mode

You play; Claude watches via doom_state on each of your moves and comments in chat:

"Shotgun behind you, two imps in the left corridor. Duck left before firing."

Just ask Claude to watch while you play.

Renderer options

/doom start [--render MODE] [--chafa-preset NAME]
            [--blocks-colors 256|full] [--gamma VALUE]
            [--cols N] [--rows N]

Render modes

Mode Native? Notes
chafa (default) external gold-standard quality; auto-selected if installed
blocks-hq yes area-averaged native C renderer, no external deps
timg external brew install timg — different color quantization
quadrant yes simpler native point-sampled blocks
sextant yes Unicode 13 sextants (2×3 subpixels, drift risk outside tmux)
sixel / kitty image protocols; confirmed blocked by Ink

Chafa presets

Preset Colors Dither Notes
default / balanced 256 ordered 4×4 recommended — drift-safe, good colors
detailed 256 ordered 2×2 + preprocess + avg extractor, pair with --cols 160
sextant-tmux 256 ordered 2×3 subpixel density, requires tmux
rich full ordered TrueColor gamut, moderate drift risk
vivid full diffusion best first-frame colors, drift under heavy scenes
sharp / fast 256 none flat colors, no dither noise

Gamma (--gamma VALUE)

Applies a pre-quantization gamma curve:

  • < 1.0 brightens midtones (recommended for Doom: 0.60.8)
  • 1.0 no change (default)
  • > 1.0 darkens

Zero byte-count cost — the LUT is per-pixel, not per-frame. Drift risk unchanged.

Blocks-hq color depth

--blocks-colors 256 switches the native renderer to xterm-palette output for the smallest possible byte stream (~78 KB frames). Default is TrueColor (138 KB).

Limits (inherent)

  • Turn-based cadence. One Enter press per decision. You can't hold W to run — you type www + Enter. Use go N to auto-tick.
  • Passive refresh at 3.3 Hz. The daemon writes a new frame every 300 ms; the statusline reads on refresh + events.
  • ~28 rows × 120 cols of frame at default size, tunable via --cols/--rows.
  • Residual drift is possible under extreme scene changes. The internal mitigations (byte-stable cells, static black border, 256-palette default, fixed-width HUD) keep drift rare in normal play. If you want it impossible, run Claude Code inside tmux — tmux's grid-repair absorbs any remaining drift.
  • MCP screenshots cost tokens. doom_look returns a PNG (~1–2k tokens). Use doom_state first, doom_look when stuck.

Why this architecture

Claude Code's TUI does not expose a "custom panel" API. Status lines, hooks, slash commands, and MCP are the documented extension surfaces. This project composes all four to create something that feels like a built-in Doom panel without patching the binary.

A full rationale, including 15+ alternative approaches that don't work, is in docs/design.md.

Contributing

The stub backend is the reference contract. A new real-Doom backend (e.g., Chocolate Doom fork, WASM Doom) implements the same file interface:

  • Read tick-delimited commands from /tmp/doom-in-claude/input.fifo
  • Write an ANSI frame to frame.ansi after each tick
  • Write a PNG screenshot to frame.png
  • Write game state to state.json (see docs/state-schema.json)

License

MIT. See LICENSE.

Doom itself is not included. This project is not affiliated with id Software or Bethesda. Use Freedoom (GPL) for a legally redistributable WAD, or point the daemon at your own licensed doom.wad / doom2.wad.