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

aimingoo的专栏
aimingoo的专栏
Google DeepMind News
Google DeepMind News
S
SegmentFault 最新的问题
Project Zero
Project Zero
D
DataBreaches.Net
I
InfoQ
L
Lohrmann on Cybersecurity
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
酷 壳 – CoolShell
酷 壳 – CoolShell
Stack Overflow Blog
Stack Overflow Blog
The Register - Security
The Register - Security
Recorded Future
Recorded Future
Vercel News
Vercel News
博客园 - 司徒正美
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
I
Intezer
The Hacker News
The Hacker News
F
Fortinet All Blogs
Microsoft Azure Blog
Microsoft Azure Blog
P
Proofpoint News Feed
Help Net Security
Help Net Security
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Scott Helme
Scott Helme
T
Threatpost
爱范儿
爱范儿
N
Netflix TechBlog - Medium
D
Docker
云风的 BLOG
云风的 BLOG
C
Cisco Blogs
K
Kaspersky official blog
H
Help Net Security
S
Secure Thoughts
T
Threat Research - Cisco Blogs
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
S
Security @ Cisco Blogs
Cyberwarzone
Cyberwarzone
N
News and Events Feed by Topic
G
Google Developers Blog
Forbes - Security
Forbes - Security
博客园 - 三生石上(FineUI控件)
博客园 - 叶小钗
B
Blog
Google DeepMind News
Google DeepMind News
Recent Announcements
Recent Announcements
Simon Willison's Weblog
Simon Willison's Weblog
S
Securelist
P
Privacy International News Feed
Spread Privacy
Spread Privacy
The Last Watchdog
The Last Watchdog

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 - think41/extrasuite: Token-efficient pull/edit/push workflow for AI agents editing Google Workspace files (Sheets, Docs, Slides, Forms) 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 - 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 - audiodude/sudomake-friends
2026-04-16 · via Hacker News: Show HN

v1.5.0

A Telegram group chat where your friends are AI bots. Yes, it's come to this.

Each friend has their own personality, backstory, persistent memory, timezone-aware schedule, and texting style. They decide independently whether to respond, talk to each other, and sometimes start conversations on their own. It's like a real group chat except nobody flakes on plans because nobody makes plans because they aren't real.

Quick Start

You need git, uv, and Docker installed. Then:

uv run https://raw.githubusercontent.com/audiodude/sudomake-friends/main/scripts/initialize.py

That's it. One command. The wizard walks you through everything. Quit anytime — it checkpoints your progress:

  1. Profile — Tell the wizard about yourself (URLs, files, or just type). It auto-detects 14 platforms.
  2. Friends — Browse generated candidates in a TUI. Hold the ones you like, re-roll the rest.
  3. Telegram — Create bots via BotFather, set up a group chat.
  4. History — Generate a shared backstory for how you all know each other.
  5. Deploy — Docker builds and runs automatically.

All your data lives in ~/.sudomake-friends/. Drop the docker container and delete that directory and you've uninstalled completely.

Other commands

# Start completely fresh
uv run <url> -- --start-over

# If you have a sources.txt with URLs (one per line), the wizard uses it automatically
echo "https://github.com/yourname" > sources.txt
uv run <url>

Your profile

We don't want generic AI friends right? We want friends that get us. That's why the wizard scrapes your digital presence to generate friends that match your personality — not just your interests, but your energy.

Auto-detected platforms: Bandcamp, Bluesky, dev.to, Discogs, GitHub, Goodreads, Hacker News, Last.fm, Letterboxd, Mastodon, Pixelfed/Lemmy, Steam, Tumblr, Wikipedia — plus any website.

Provide as many sources as you want. More context means better friends. You can also save your sources to sources.txt for quick re-setup.

Friend generation

Friends are generated personality-first. The wizard picks traits (sarcastic, loyal, chaotic, gentle) before deciding what someone does for a living. Each friend gets:

  • SOUL.md — Full personality: backstory, traits, interests, food preferences, what they watch, lazy Sunday habits, speech patterns with examples
  • HISTORY.md — Shared history of how you all met (generated, editable)
  • candidate.json — Original generation data (for editing in the TUI later)

The TUI lets you hold friends you like, re-roll the rest, expand details, and edit candidates before committing.

Adjusting your setup

Run the wizard again on an existing setup:

uv run https://raw.githubusercontent.com/audiodude/sudomake-friends/main/scripts/initialize.py

You'll get options to adjust (walk through each step, keeping what you want), start over, or deploy. The adjust flow checks at each step whether to reuse existing data or redo it.

You can also edit any friend's personality directly at ~/.sudomake-friends/friends/<name>/SOUL.md.

Updates and migrations

Every time you re-run the wizard, two things happen before anything else:

  1. Update check. The wizard offers to pull the latest code from GitHub. You can decline. If you accept and the pull fails (e.g. you're hacking on a local checkout with uncommitted changes), it'll show the error and keep going with what you have.
  2. Migrations. If the new code includes data migrations that haven't been applied to your friends directory yet, the wizard lists them and asks before running. Each migration backs up ~/.sudomake-friends/friends/ to ~/.sudomake-friends/.backups/pre-<id>-<timestamp>/ before touching anything, so if something goes wrong you can restore. Backups are kept forever — delete ~/.sudomake-friends/ to uninstall.

Migrations are normal Python files under scripts/migrations/<timestamp>_<slug>/, each with an is_needed() check and a run() function. Some are optional (you can skip them); some are mandatory (the wizard halts until they're applied). Applied migrations are recorded in ~/.sudomake-friends/.migrations-applied so nothing runs twice.

If you're running from the published URL, the wizard keeps a cached checkout at ~/.sudomake-friends/.src-cache/ and pulls updates into that. If you're running from a local dev checkout, it leaves your working tree alone.

How it works

When you send a message in the group:

  1. Each bot checks their schedule — are they awake? At work? Day off? A random roll against their chattiness determines if they're "around". Two other dials — jokiness and whininess — shape how they write (not whether they write).
  2. Bots that pass the gate get a Claude call with their personality + memory + chat history, and decide whether to respond
  3. They wait a realistic delay before sending — sometimes splitting thoughts across multiple messages
  4. Important facts get saved to their memory for future conversations
  5. Old chat history is periodically summarized to keep context manageable

Bots also initiate conversations when the chat's been quiet, and catch up on messages where they were mentioned but unavailable.

Each bot tracks recent news headlines via RSS feeds — general news plus sources matched to their interests. Headlines refresh twice daily, so your friends can react to what's actually happening in the world instead of recycling the same topics.

Deploy somewhere else

The wizard defaults to local Docker, but you can deploy anywhere that runs containers.

Railway

railway init && railway link
railway volume add --mount /app/data
railway variables set DATA_DIR=/app/data
railway up --detach

Fly.io

fly launch --no-deploy
fly volumes create friend_data --size 1

Add to fly.toml:

[mounts]
  source = "friend_data"
  destination = "/app/data"

[env]
  DATA_DIR = "/app/data"

Any platform that supports Docker + persistent volumes will work. The key requirements: the DATA_DIR env var pointing to a volume mount, and ~/.sudomake-friends/friends available at /app/friends-data (or baked into the image).

Data

~/.sudomake-friends/
  .env                    # API keys and bot tokens
  profile.txt             # compiled user profile
  .init-checkpoint.json   # setup progress
  friends/
    HISTORY.md            # shared backstory
    <name>/
      SOUL.md             # personality — edit freely
      candidate.json      # original generation data
      config.yaml         # timezone, schedule, chattiness, jokiness, whininess
  # Docker volume (managed by container):
  #   memories/<name>/MEMORY.md
  #   CHAT.jsonl
  #   CHAT_SUMMARY.md

Commands

Send these in the Telegram group chat:

  • /test or /debug — All bots check in with "Hi it's me, <name>"

Versioning

The version at the top of this README is cosmetic — no build-time or runtime meaning, just a marker so you can tell at a glance whether your checkout is current. Rough guidance for bumps:

  • Patch — prompt tweaks, small fixes.
  • Minor — schema changes / migrations, major code revisions.
  • Major — reserved for big visible reworks.

FAQ

How much does it cost? Each response is one Claude API call (~$0.003-0.01). News headlines are fetched via RSS (free, no LLM calls). A quiet group might cost $1-2/month; an active one $5-10/month.

Can I change a friend's personality? Edit ~/.sudomake-friends/friends/<name>/SOUL.md. It's just markdown. Restart the container to pick up changes.

Why do my friends sound like AI? The prompt engineering fights hard against this, but sometimes Claude gonna Claude. Edit the Speech Patterns section of their SOUL.md to be more specific.

What's work_type in the config? "office" means they can sneak a text at work. "physical" means they mostly can't. Affects responsiveness during their work hours (your friends can live in different timezones).

What if I mention a friend and they're asleep? They'll catch up when they "wake up." Mentions get queued and replayed when the bot becomes available.

Is this sad? Probably. But at least they always text back.

By the way, how do you pronounce the name? It's "soo-doh-MAH-kee frendz" of course! 😉