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

G
GRAHAM CLULEY
V
V2EX
WordPress大学
WordPress大学
博客园 - Franky
Last Week in AI
Last Week in AI
博客园 - 司徒正美
有赞技术团队
有赞技术团队
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园 - 【当耐特】
V
Visual Studio Blog
C
CERT Recently Published Vulnerability Notes
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Jina AI
Jina AI
Attack and Defense Labs
Attack and Defense Labs
腾讯CDC
The Hacker News
The Hacker News
Hugging Face - Blog
Hugging Face - Blog
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
J
Java Code Geeks
人人都是产品经理
人人都是产品经理
阮一峰的网络日志
阮一峰的网络日志
T
Tailwind CSS Blog
S
SegmentFault 最新的问题
大猫的无限游戏
大猫的无限游戏
小众软件
小众软件
A
Arctic Wolf
量子位
博客园 - 聂微东
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
N
News and Events Feed by Topic
雷峰网
雷峰网
博客园_首页
Google Online Security Blog
Google Online Security Blog
Spread Privacy
Spread Privacy
罗磊的独立博客
H
Hacker News: Front Page
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
月光博客
月光博客
TaoSecurity Blog
TaoSecurity Blog
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
博客园 - 三生石上(FineUI控件)
宝玉的分享
宝玉的分享
IT之家
IT之家
The Cloudflare Blog
爱范儿
爱范儿
博客园 - 叶小钗
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Apple Machine Learning Research
Apple Machine Learning Research
酷 壳 – CoolShell
酷 壳 – CoolShell

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 - think41/extrasuite: Token-efficient pull/edit/push workflow for AI agents editing Google Workspace files (Sheets, Docs, Slides, Forms)
ksri · 2026-04-17 · via Hacker News: Show HN

ExtraSuite is a library to create and edit google docs/sheets etc using simple formats like markdown / json / tsv. It is meant for AI agents like claude / codex, and is designed to be token efficient.

Lets assume you want to edit a large google document:

  1. You pull the google document. This creates a local folder with 1 markdown file per tab, and an index.md with the headings from each tab.
  2. You edit the markdown files. No special rules - its simple markdown
  3. You push the folder. This command understands your changes and applies them to the google document.

The push command does a lot of heavy lifting.

  1. It first diffs the markdown to find exactly what you changed.
  2. Then it finds out what batchUpdate requests are needed to reconcile the document
  3. If tracks index drifts and ensures subsequent operations use the correct index
  4. It tracks dependencies across batchUpdate calls. For example, if you create a new markdown file for a tab - then it will first create the tab in one request, then use the id to create the contents inside that tab.

Net result: A single pull command can make complex changes across the entire google document.

The push command makes a few promises:

  1. It won't change anything it doesn't understand. So if you have complex formatting, fonts, styles - it won't modify or make changes to it. You can still edit the content without messing with the styles.
  2. It will make the smallest operation to reconcile the document. In other words - "Delete and re-insert" is a bug.

The push command also supports comments. This lets you provide feedback to the agent via comments, and then ask the agent to address them.

Similar principles apply to google sheets:

  • A google sheet is a folder with a spreadsheet.json. The spreadsheet.json shows the shape of every worksheet (top 5 rows per worksheet)
  • Each worksheet is a folder. It has a data.tsv, formula.json and other feature specific files
  • Formulas and formatting details are compressed and applied to a range rather than to a cell. The agent sees 'Okay, this column has sum applied' or 'Okay - that row is bold'.
  • Reference documents are provided - for example, the list of formulas provided by google sheets.

Why ExtraSuite when gws / goglcli exist?

gws and gogcli cover a breadth of use cases in the google workspace ecosystem, but fail short when it comes to editing files. They can edit small things here are and there, but struggle when you want to make changes in a meaningful manner. You want to take to your agent in your domain - "Modify this SOW based on the pricing from this spreadsheet". For a task like that, gws/gogcli will struggle.

Google Docs (and spreadsheets to a lesser extent) have a complex representation.

  • The agent must reason about the API's internal structure (paragraph indices, cell references, range coordinates) rather than content.
  • Every edit requires reading back the current state to compute correct offsets and IDs.
  • Token usage balloons: raw API responses for a 20-page doc or a 500-row sheet are enormous.
  • There's no clean way to review or test what the agent will change before it changes it.

ExtraSuite complements gws and gogcli — if you have either of these tools installed, you can directly run


Getting Started

Install

uvx extrasuite --help

Or install persistently:

uv tool install extrasuite

The --help flag on any command is the authoritative reference. Run extrasuite <module> --help for a workflow overview, and extrasuite <module> <command> --help for full flag documentation.

Authentication

ExtraSuite piggybacks on credentials from other Google CLI tools you may already have configured.

If you use gws: ExtraSuite auto-detects your gws credentials (~/.config/gws/client_secret.json) and reuses them. No additional setup.

If you use gogcli: ExtraSuite auto-detects your gogcli credentials and reuses them. No additional setup.

From scratch: Set up OAuth client credentials using either gws's setup guide or gogcli's setup guide, then use ExtraSuite alongside them.

In all the above modes, edits appear in Google Drive under your own Google account.

ExtraSuite gateway server (teams): For a distinct agent identity and audit trail, deploy the ExtraSuite server. See the deployment documentation for setup.

Quick Start

Once authenticated:

# Pull a sheet, edit it, push it back
uvx extrasuite sheets pull "https://docs.google.com/spreadsheets/d/..." <folder>
# edit files in <folder>
uvx extrasuite sheets push <folder>

# Pull a doc, edit it, push it back
uvx extrasuite docs pull "https://docs.google.com/document/d/..." <folder>
# edit files in <foldeR>
uvx extrasuite docs push <folder>

Agent Identity and Security (ExtraSuite Gateway Mode)

The features below require deploying the ExtraSuite server. This is suitable for teams and small organizations who want tighter control over what agents can access and do.

A Dedicated Identity Per Employee

Every employee's agent gets its own Google service account (e.g. alice-agent@your-project.iam.gserviceaccount.com). The agent can only access files that have been explicitly shared with that service account — nothing else in Drive is visible. All edits appear in Google Drive version history as "Edited by Alice's agent", not as Alice herself.

Typed Commands and Minimal Scope

The client sends a typed command to the ExtraSuite server along with the agent's stated reason. The server determines the minimum required credentials:

  • Pull/push operations (Sheets, Docs, Slides, Forms, Drive) → short-lived service account token, valid 1 hour
  • User-impersonating operations (Gmail, Calendar, Apps Script, Contacts) → short-lived delegated token scoped to exactly the required OAuth scope, valid 1 hour

The command type, context, and reason are logged server-side before any token is issued.

Security Properties

Property How ExtraSuite Achieves It
Scoped access Each agent has a dedicated service account; only sees explicitly shared files
Short-lived tokens Google access tokens expire after ~1 hour; generated on demand, never stored
Typed commands Server issues the minimum token type and scope for the declared operation
Agent intent logging Reason logged alongside command type before any token is issued
Audit trail All agent edits appear in Google Drive version history attributed to the agent
Sandboxable Agent only edits local files and calls pull/push; no arbitrary API access
Minimal OAuth scope Only the scopes needed for the specific operation are requested

Deploy the Server

gcloud run deploy extrasuite-server \
  --image=ghcr.io/think41/extrasuite-server:latest \
  --service-account=extrasuite-server@$PROJECT_ID.iam.gserviceaccount.com \
  --region=us-central1 \
  --allow-unauthenticated \
  --set-env-vars="ENVIRONMENT=production,GOOGLE_CLOUD_PROJECT=$PROJECT_ID" \
  --set-secrets="GOOGLE_CLIENT_ID=extrasuite-client-id:latest,GOOGLE_CLIENT_SECRET=extrasuite-client-secret:latest,SECRET_KEY=extrasuite-secret-key:latest"

See the deployment documentation for full setup instructions.

Employee Onboarding (gateway mode)

  1. Employee logs into the ExtraSuite server and notes their agent's service account email
  2. Runs extrasuite auth install-skill to give the agent its instructions
  3. Shares specific Google files with the service account (editor or viewer, as needed)
  4. Agent runs extrasuite <module> pull <url> and the workflow begins

CLI Reference

Modules

Module Description
sheets Google Sheets — pull/edit/push spreadsheets via TSV and JSON
docs Google Docs — pull/edit/push documents via markdown
slides Google Slides — pull/edit/push presentations via SML markup
forms Google Forms — pull/edit/push surveys and quizzes via JSON
script Google Apps Script — pull/edit/push standalone and bound scripts
gmail Gmail — compose drafts, read and reply to emails
calendar Google Calendar — view, create, update, delete events
drive Google Drive — list and search files
contacts Google Contacts — sync, search, and manage contacts
auth Authentication management

Core Commands (sheets / docs / slides / forms / script)

Command Description
pull <url> Download the file to a local folder
push <folder> Apply changes to Google
create <title> Create a new file
share <url> <emails> Share the file with trusted contacts

Gmail Commands

Command Description
compose <file> Save an email draft from a markdown file
edit-draft <id> <file> Update an existing Gmail draft
reply <thread_id> <file> Create a reply draft in an existing thread
list Search and list Gmail messages
read <id> Read a Gmail message

Calendar Commands

Command Description
view View events for a time range
list List all calendars
search Search events by title or attendee
freebusy Check when a group of people are free
create <file> Create an event from a JSON file
update <id> Update an existing event
delete <id> Cancel or delete an event
rsvp <id> Accept, decline, or mark tentative

Development

# Client
cd client && uv sync
uv run pytest tests/ -v

# Server
cd server && uv sync
uv run uvicorn extrasuite.server.main:app --reload --port 8001

# Tests and linting
cd server && uv run pytest tests/ -v && uv run ruff check .

License

MIT License — see LICENSE for details.