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

Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Microsoft Azure Blog
Microsoft Azure Blog
Cloudbric
Cloudbric
I
InfoQ
V
V2EX
博客园_首页
The Register - Security
The Register - Security
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
S
Secure Thoughts
Vercel News
Vercel News
Forbes - Security
Forbes - Security
云风的 BLOG
云风的 BLOG
PCI Perspectives
PCI Perspectives
L
LINUX DO - 最新话题
D
DataBreaches.Net
H
Hacker News: Front Page
Application and Cybersecurity Blog
Application and Cybersecurity Blog
B
Blog RSS Feed
A
About on SuperTechFans
N
News and Events Feed by Topic
Apple Machine Learning Research
Apple Machine Learning Research
Help Net Security
Help Net Security
Attack and Defense Labs
Attack and Defense Labs
N
Netflix TechBlog - Medium
Spread Privacy
Spread Privacy
F
Full Disclosure
Recorded Future
Recorded Future
AWS News Blog
AWS News Blog
博客园 - 【当耐特】
The Cloudflare Blog
T
Threatpost
T
Tor Project blog
Google DeepMind News
Google DeepMind News
C
CXSECURITY Database RSS Feed - CXSecurity.com
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
Recent Announcements
Recent Announcements
M
MIT News - Artificial intelligence
A
Arctic Wolf
C
Check Point Blog
Stack Overflow Blog
Stack Overflow Blog
T
Threat Research - Cisco Blogs
Security Archives - TechRepublic
Security Archives - TechRepublic
Hacker News - Newest:
Hacker News - Newest: "LLM"
WordPress大学
WordPress大学
Cyberwarzone
Cyberwarzone
小众软件
小众软件
C
Cyber Attacks, Cyber Crime and Cyber Security
P
Proofpoint News Feed
Security Latest
Security Latest
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 - 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 - incursa/codex-telegram: Telegram bot for controlling a local Codex CLI session from an allowlisted chat.
mcaravey · 2026-05-07 · via Hacker News: Show HN

Incursa Codex Telegram lets you talk to a local Codex CLI session from a private Telegram chat. It runs on your own machine, stores state locally, and only accepts messages from allowlisted Telegram users.

Use it when you want to start, steer, and inspect Codex work from your phone without exposing your whole machine to Telegram users.

Demo

Watch a two-minute private-chat demo showing a local Codex session controlled from Telegram with project selection, text prompts, and voice input.

Watch the Codex Telegram demo

For the available Telegram buttons and menus, see the menus and button reference.

Download

Download the latest release binary for your operating system:

Platform Download Checksum
Windows x64 codex-telegram-win-x64.exe sha256
Linux x64 codex-telegram-linux-x64 sha256
macOS arm64 codex-telegram-osx-arm64 sha256

All releases are listed at GitHub Releases.

What You Need

Before starting, have these ready:

  1. A Telegram account.
  2. A Telegram bot token from @BotFather.
  3. A local Codex CLI installation that already works in a terminal.
  4. At least one local repository or workspace directory you want Codex to use.
  5. Optional: an OpenAI API key for voice-note transcription. Install ffmpeg only if Telegram audio must be transcoded; Telegram voice notes commonly need it.

This app does not bundle Codex, Telegram credentials, or OpenAI credentials. If you use voice notes, any required audio transcoder must already exist on the machine running the bot.

For Codex CLI setup, use OpenAI's official Codex CLI docs.

Quick Start

Start by creating a Telegram bot, then follow the complete setup path for your operating system.

Create A Telegram Bot

In Telegram:

  1. Open a chat with @BotFather.
  2. Send /newbot.
  3. Choose a display name.
  4. Choose a username ending in bot.
  5. Copy the bot token.

Keep the token private. Anyone with the token can control the bot account.

Recommended BotFather settings for a first private-chat release:

  1. Use /setdescription and /setabouttext to explain that this bot controls a local Codex installation.
  2. Keep group joins disabled unless you intentionally want group support.
  3. Keep privacy mode enabled unless you intentionally need ordinary group text routed to Codex.
  4. Add commands later after the private-chat flow works.

Copy-paste BotFather text, command lists, and privacy recommendations are in BotFather setup.

BotFather gives you the bot token, but it cannot give you your personal Telegram user ID. On first run, Codex Telegram can validate the bot token, wait for one private message to the bot, and save your user ID automatically.

Windows

Use this path if the bot will run on Windows x64.

  1. Download codex-telegram-win-x64.exe and codex-telegram-win-x64.exe.sha256 from the latest release.
  2. Optional but recommended: verify the checksum before renaming or moving the file.
Get-FileHash .\codex-telegram-win-x64.exe -Algorithm SHA256
Get-Content .\codex-telegram-win-x64.exe.sha256
  1. Put the binary in a stable folder.
New-Item -ItemType Directory -Force C:\tools\codex-telegram | Out-Null
Move-Item .\codex-telegram-win-x64.exe C:\tools\codex-telegram\codex-telegram.exe
Set-Location C:\tools\codex-telegram
  1. Confirm Codex works locally before involving Telegram.
codex --version
codex
  1. Start the setup menu from the app folder.
.\codex-telegram.exe
  1. Complete the first-run wizard.

Use these values as a starting point:

Telegram bot token: <token from BotFather>
Telegram polling: enabled
Admin user ID: let the wizard capture it by sending one private Telegram message to the bot
Codex executable path: leave blank if codex is on PATH, otherwise set the full codex.exe path
Workspace root: C:\src
Default working directory: C:\src\your-repo
OpenAI transcription: only if you want voice notes
Local data root: leave blank unless you need a custom state folder

The app writes appsettings.Local.json beside the executable by default. Keep that file local and untracked. If you launch the app from another command-line directory later, it still uses the settings file in the app folder.

  1. Start normal operation with the menu skipped.
.\codex-telegram.exe --run

Keep that terminal open, or run the app under your preferred Windows service manager.

  1. In the private Telegram chat, run the first private Codex session.
/doctor
/projects
/project add C:\src\your-repo
/new release-demo
Summarize this repository and tell me the next safest setup check to run.
/tail

At this point you have a working private Telegram chat connected to a local Codex session.

Linux

Use this path if the bot will run on Linux x64.

  1. Download codex-telegram-linux-x64 and codex-telegram-linux-x64.sha256 from the latest release.
  2. Or download both files directly with curl.
curl -fL -o codex-telegram-linux-x64 https://github.com/incursa/codex-telegram/releases/latest/download/codex-telegram-linux-x64
curl -fL -o codex-telegram-linux-x64.sha256 https://github.com/incursa/codex-telegram/releases/latest/download/codex-telegram-linux-x64.sha256
  1. Optional but recommended: verify the checksum before renaming or moving the file.
shasum -a 256 -c ./codex-telegram-linux-x64.sha256
  1. Put the binary in a stable folder and mark it executable.
mkdir -p ~/tools/codex-telegram
mv ./codex-telegram-linux-x64 ~/tools/codex-telegram/codex-telegram
chmod +x ~/tools/codex-telegram/codex-telegram
cd ~/tools/codex-telegram
  1. Confirm Codex works locally before involving Telegram.
codex --version
codex
  1. Start the setup menu from the app folder.
./codex-telegram
  1. Complete the first-run wizard.

Use these values as a starting point:

Telegram bot token: <token from BotFather>
Telegram polling: enabled
Admin user ID: let the wizard capture it by sending one private Telegram message to the bot
Codex executable path: leave blank if codex is on PATH, otherwise set the full codex path
Workspace root: /home/you/src
Default working directory: /home/you/src/your-repo
OpenAI transcription: only if you want voice notes
Local data root: leave blank unless you need a custom state folder

The app writes appsettings.Local.json beside the executable by default. Keep that file local and untracked. If you launch the app from another command-line directory later, it still uses the settings file in the app folder.

  1. Start normal operation with the menu skipped.
./codex-telegram --run

Keep that terminal open, or run the app under systemd, tmux, screen, or another process supervisor.

  1. In the private Telegram chat, run the first private Codex session.
/doctor
/projects
/project add /home/you/src/your-repo
/new release-demo
Summarize this repository and tell me the next safest setup check to run.
/tail

At this point you have a working private Telegram chat connected to a local Codex session.

macOS

Use this path if the bot will run on Apple Silicon macOS.

  1. Download codex-telegram-osx-arm64 and codex-telegram-osx-arm64.sha256 from the latest release.
  2. Or download both files directly with curl.
curl -fL -o codex-telegram-osx-arm64 https://github.com/incursa/codex-telegram/releases/latest/download/codex-telegram-osx-arm64
curl -fL -o codex-telegram-osx-arm64.sha256 https://github.com/incursa/codex-telegram/releases/latest/download/codex-telegram-osx-arm64.sha256
  1. Optional but recommended: verify the checksum before renaming or moving the file.
shasum -a 256 -c ./codex-telegram-osx-arm64.sha256
  1. Put the binary in a stable folder and mark it executable.
mkdir -p ~/tools/codex-telegram
mv ./codex-telegram-osx-arm64 ~/tools/codex-telegram/codex-telegram
chmod +x ~/tools/codex-telegram/codex-telegram
cd ~/tools/codex-telegram
  1. If macOS blocks the binary because it was downloaded from the internet, verify the checksum first. If you trust the release, remove the quarantine attribute.
xattr -d com.apple.quarantine ~/tools/codex-telegram/codex-telegram
  1. Confirm Codex works locally before involving Telegram.
codex --version
codex
  1. Start the setup menu from the app folder.
./codex-telegram
  1. Complete the first-run wizard.

Use these values as a starting point:

Telegram bot token: <token from BotFather>
Telegram polling: enabled
Admin user ID: let the wizard capture it by sending one private Telegram message to the bot
Codex executable path: leave blank if codex is on PATH, otherwise set the full codex path
Workspace root: /Users/you/src
Default working directory: /Users/you/src/your-repo
OpenAI transcription: only if you want voice notes
Local data root: leave blank unless you need a custom state folder

The app writes appsettings.Local.json beside the executable by default. Keep that file local and untracked. If you launch the app from another command-line directory later, it still uses the settings file in the app folder.

  1. Start normal operation with the menu skipped.
./codex-telegram --run

Keep that terminal open, or run the app under launchd, tmux, screen, or another process supervisor.

  1. In the private Telegram chat, run the first private Codex session.
/doctor
/projects
/project add /Users/you/src/your-repo
/new release-demo
Summarize this repository and tell me the next safest setup check to run.
/tail

At this point you have a working private Telegram chat connected to a local Codex session.

Voice Notes

Voice notes are optional. The bot downloads Telegram audio, transcribes it with OpenAI, shows the transcript, and sends only the transcribed text to the active Codex session. Codex does not receive raw Telegram audio.

Voice note requirements:

  1. OpenAI:ApiKey or OPENAI_API_KEY.
  2. A transcription-capable OpenAI:Model.
  3. ffmpeg only when the downloaded audio is not in a format OpenAI accepts directly. Telegram voice notes commonly arrive as OGG/OPUS, so install ffmpeg or configure OpenAI:FfmpegPath for reliable voice-note support.

If ffmpeg is missing when a voice note needs conversion, the bot leaves the Codex session untouched and replies with setup guidance instead of failing silently.

Suggested first voice test:

Please review the current project and tell me the three most important setup risks. Keep it concise and do not edit files.

After a successful test, you should see the transcription in Telegram before the Codex response starts.

Day-To-Day Commands

Command Use
/doctor Explain authorization, routing, active project/session, workspace roots, queue state, and next action.
/help Show the built-in command summary.
/whoami Show Telegram user, chat, and topic IDs for setup and troubleshooting.
/projects List known local project directories.
/project add <path> Add and select a repository or workspace.
/project current Confirm the active project for this Telegram conversation.
/new <name> Create and select a fresh Codex session.
/sessions Show active and Telegram-managed sessions.
/sessions all [count] Show older Codex history.
/use <sessionId> Resume an existing session.
/send <text> Send text when plain text is not automatically routed, especially in groups.
/steer <text> Add guidance to a currently active turn.
/queue View queued prompts for the conversation, then edit, delete, or send one now.
/model Show or change the active session model.
/thinking Show or change reasoning effort.
/status Show active session status, including compact Codex usage when available.
/usage Show five-hour and weekly Codex usage, with reset times.
/tail [lines] Show recent output and keep following the session; defaults to 40 lines.
/outbound Inspect delayed or batched Telegram output.
/stop Gracefully stop a session.
/restart confirm Show standalone-process restart guidance.
/topic ... Manage forum-topic sessions in allowed supergroups.

For a fuller operator guide, see docs/usage.md. For every command, parameter, and expected behavior, see docs/command-reference.md.

How Output Delivery Works

Telegram output is rate-limited and batched so active Codex sessions do not flood your chat.

Practical rules:

  1. Use /tail before assuming Telegram scrollback contains the full transcript.
  2. Use /outbound if messages seem delayed.
  3. Use /usage when you need current five-hour and weekly Codex usage percentages and reset times.
  4. Batched messages are concatenated with simple spacing and preserve multi-line content, including numbered lists and headings.
  5. If the local outbound buffer is compacted, the bot sends an explicit compaction notice.
  6. A final ~~ fin ~~ marker means the turn reached a terminal event.

Local State And Safety

The app stores local state under CodexTelegram:Workspace:DataRoot. By default, that is the user's application data folder.

State includes:

  1. projects.json
  2. telegram-state.json
  3. Per-thread manifests

Secrets should stay in appsettings.Local.json, user secrets, environment variables, or another secret store. Secrets are not supposed to be written to the state files.

Security rules:

  1. Keep TelegramBot:AllowedUserIds narrow.
  2. Keep TelegramBot:AllowedChatIds empty unless you intentionally want group or forum-topic access.
  3. Set explicit workspace roots and a default working directory before enabling polling.
  4. Review Codex sandbox and approval settings before exposing sensitive repositories.
  5. Rotate the BotFather token if it is exposed.

Supported Modes

Private chat is the primary supported operating mode and the recommended first setup path.

Groups and forum topics are available for advanced workflows, but they require:

  1. An allowed Telegram user.
  2. An allowed group chat ID.
  3. BotFather privacy settings that match the desired behavior.
  4. Topic-management rights if the bot should create forum topics.

Start privately first. Add groups only after the private flow works.

Support And Security

For general open-source project questions, contact oss@incursa.com.

For security issues, use GitHub private vulnerability reporting when it is enabled for this repository. If that is unavailable, contact security@incursa.com. Do not include secrets, private transcripts, exploit details, or local credential paths in public issues.

More Documentation

User and operator docs:

Developer and maintainer docs: