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

L
LINUX DO - 最新话题
G
Google Developers Blog
J
Java Code Geeks
The GitHub Blog
The GitHub Blog
F
Full Disclosure
H
Help Net Security
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Vercel News
Vercel News
酷 壳 – CoolShell
酷 壳 – CoolShell
Recent Announcements
Recent Announcements
Help Net Security
Help Net Security
The Hacker News
The Hacker News
IT之家
IT之家
Y
Y Combinator Blog
Martin Fowler
Martin Fowler
L
Lohrmann on Cybersecurity
C
CERT Recently Published Vulnerability Notes
V
Visual Studio Blog
博客园 - 聂微东
Hacker News: Ask HN
Hacker News: Ask HN
H
Hacker News: Front Page
Know Your Adversary
Know Your Adversary
Security Latest
Security Latest
Security Archives - TechRepublic
Security Archives - TechRepublic
Simon Willison's Weblog
Simon Willison's Weblog
www.infosecurity-magazine.com
www.infosecurity-magazine.com
T
Troy Hunt's Blog
Last Week in AI
Last Week in AI
Schneier on Security
Schneier on Security
N
News and Events Feed by Topic
博客园 - 【当耐特】
有赞技术团队
有赞技术团队
AWS News Blog
AWS News Blog
Blog — PlanetScale
Blog — PlanetScale
博客园_首页
Google DeepMind News
Google DeepMind News
Cloudbric
Cloudbric
N
News | PayPal Newsroom
A
About on SuperTechFans
S
Schneier on Security
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
Hugging Face - Blog
Hugging Face - Blog
M
MIT News - Artificial intelligence
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
雷峰网
雷峰网
T
The Exploit Database - CXSecurity.com
罗磊的独立博客
K
Kaspersky official blog
The Cloudflare Blog
I
Intezer

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 - yashau/dexgram: Telegram bridge for Codex Desktop
yashau · 2026-05-13 · via Hacker News: Show HN

Dexgram is a Windows Telegram bridge for Codex Desktop. It runs as a single Windows binary, listens to a private Telegram bot chat with threaded topics enabled, and maps each Telegram topic to a Codex thread.

Unlike most other Codex-to-Telegram bridges, Dexgram is specifically built around Codex Desktop and Codex app-server threads. Telegram chats created through Dexgram are registered in Codex Desktop's chat history, so you can start or continue a conversation from Telegram and then pick it up again in Codex Desktop.

Features

  • Creates Codex chats from Telegram topics, with each topic mapped to a resumable Codex app-server thread.
  • Keeps Dexgram-created chats visible in Codex Desktop history so conversations can move between Telegram and the desktop app.
  • Supports project-bound chats with fuzzy Codex Desktop project matching and inline selection buttons for ambiguous matches.
  • Creates dated one-off workspaces for projectless chats, matching Codex Desktop's "Don't work in a project" flow.
  • Mirrors Codex progress back to Telegram with initial replies, live run-log updates, final answers, and a Stop button for active turns.
  • Queues new Telegram messages while Codex is busy, with inline controls to steer queued items into the active turn or delete them before they run.
  • Supports native Codex goals from Telegram with /goal <objective>.
  • Downloads Telegram photos and documents for Codex prompts, stages attachment-only messages, and uploads final-answer local file links back to Telegram.
  • Installs as a current-user Windows login task, with a Startup-folder fallback when Task Scheduler is unavailable.

Windows Only

Dexgram is designed for Windows. Its service mode uses a current-user Windows Task Scheduler login task, with a Startup-folder fallback if Task Scheduler denies access.

Because, apparently, macOS is not the only desktop allowed to receive nice things.

Requirements

  • Windows
  • Codex Desktop installed and signed in
  • A Telegram bot token from @BotFather
  • Telegram threaded topics enabled for the bot

In @BotFather, enable:

Bot Settings -> Threads Settings -> Threaded Mode

Setup

Option 1: Install The Latest Release

Run the one-line installer:

irm https://raw.githubusercontent.com/yashau/dexgram/main/install.ps1 | iex

The installer downloads the latest GitHub release, puts dexgram.exe under %LOCALAPPDATA%\Dexgram, adds that folder to your user PATH, creates the Dexgram config/log/state directories, and starts onboarding from the installed dexgram.exe path.

After onboarding, validate the setup with the command printed by the installer.

Update later with:

dexgram update

After a successful update, the installer starts the Dexgram service again from the newly installed binary.

Option 2: Manual Setup

If you already have dexgram.exe, run onboarding yourself:

.\dexgram.exe onboard

You can also copy the example config and edit it manually:

Copy-Item .\dexgram.example.toml .\dexgram.toml
notepad .\dexgram.toml

At minimum, set:

[telegram]
bot_token = "123456789:replace-me"
chat_id = 0

Use chat_id = 0 temporarily to discover your private chat id. Start Dexgram, send the bot a DM, then copy the logged chat_id into the config.

Validate the setup:

.\dexgram.exe -check

Start Dexgram:

.\dexgram.exe

Service Mode

Dexgram can install itself as a user-login background process:

.\dexgram.exe service install
.\dexgram.exe service start

This is not a Windows Service. It runs in the signed-in user's context so it can talk to the same Codex Desktop environment. Dexgram tries a current-user scheduled task first; if Windows denies that, it installs a per-user Startup folder fallback.

Service paths:

Binary: %LOCALAPPDATA%\Dexgram\dexgram.exe
Config: %APPDATA%\Dexgram\dexgram.toml
Logs:   %APPDATA%\Dexgram\dexgram.log
State:  %APPDATA%\Dexgram\dexgram.db

Telegram Commands

  • /new [title] creates a new Telegram topic for a Codex chat.
  • /project <project name> binds a new topic to a Codex Desktop project before the first prompt. Project matching is fuzzy, so partial names usually work; if multiple projects match, Dexgram shows inline selection buttons.
  • /status shows the topic's Dexgram mapping and active turn state.
  • /sync mirrors new completed Codex turns for chats Dexgram already created.
  • /steer <message> steers the currently active Codex turn.
  • /goal <objective> sets the native Codex goal for the topic. As of writing, goals must be enabled in your Codex config first: %USERPROFILE%\.codex\config.toml with [features] and goals = true.
  • /stop or /cancel interrupts the active Codex turn.

How Chats Run

On the first prompt in a Telegram topic, Dexgram starts a Codex thread and saves the mapping by Telegram chat_id and message_thread_id. Later messages in that topic use the stored Codex thread id. If no project is selected, Dexgram creates a one-off workspace similar to Codex Desktop's "Don't work in a project" flow under:

%USERPROFILE%\Documents\Codex\YYYY-MM-DD\chat-title

Each Codex turn is mirrored back into Telegram as a small set of messages:

  • An initial assistant or plan message, when Codex sends one.
  • One live run-log message for commands, tools, file edits, searches, and media.
  • The final assistant answer.

The active turn status message includes a Stop button. It does the same job as /stop or /cancel: Dexgram interrupts the current Codex turn for that topic.

Limitations

  • Dexgram does not import arbitrary Codex Desktop chats into Telegram.
  • /sync only works for chats Dexgram already created and mapped.
  • Desktop work in a mapped chat can be mirrored back with /sync; unrelated Desktop chats will not appear in Telegram.

Queued Messages

If you send another Telegram message while Codex is already working in that topic, Dexgram still submits it to Codex. Codex queues it natively, and Dexgram replies to the queued Telegram message with two buttons:

  • Steer merges that queued input into the currently active Codex turn, then deletes the queued turn.
  • Delete queued cancels the queued Codex turn without steering it.

The /steer <message> command is the text-command version of steering: it sends that message directly into the active Codex turn.

Files And Attachments

Dexgram downloads Telegram photos, image documents, and regular documents to local files before sending them to Codex. Images are passed as local image inputs; other documents are included by absolute path.

Messages that include both text and files are sent to Codex as one prompt. If you send files without text, Dexgram stages them and attaches them to the next message in that chat. The same attachment handling applies when a prompt is queued behind an active Codex turn.

Dexgram does not upload files reported by intermediate tool calls, file edits, or image-generation events while Codex is working. If the final assistant answer explicitly links to a local file, Dexgram uploads that file after the final text answer. Images are sent as photos; everything else is sent as a document.

License

MIT. See LICENSE.