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

T
Troy Hunt's Blog
Blog — PlanetScale
Blog — PlanetScale
Engineering at Meta
Engineering at Meta
F
Full Disclosure
Recorded Future
Recorded Future
The GitHub Blog
The GitHub Blog
Microsoft Security Blog
Microsoft Security Blog
GbyAI
GbyAI
博客园_首页
博客园 - 叶小钗
MongoDB | Blog
MongoDB | Blog
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
Recent Commits to openclaw:main
Recent Commits to openclaw:main
H
Hacker News: Front Page
人人都是产品经理
人人都是产品经理
The Cloudflare Blog
博客园 - 司徒正美
Webroot Blog
Webroot Blog
Google DeepMind News
Google DeepMind News
Help Net Security
Help Net Security
Cloudbric
Cloudbric
PCI Perspectives
PCI Perspectives
有赞技术团队
有赞技术团队
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
TaoSecurity Blog
TaoSecurity Blog
L
Lohrmann on Cybersecurity
量子位
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
T
Tailwind CSS Blog
Hacker News - Newest:
Hacker News - Newest: "LLM"
B
Blog RSS Feed
Apple Machine Learning Research
Apple Machine Learning Research
大猫的无限游戏
大猫的无限游戏
P
Proofpoint News Feed
N
News and Events Feed by Topic
罗磊的独立博客
T
Threat Research - Cisco Blogs
Schneier on Security
Schneier on Security
T
Tor Project blog
IT之家
IT之家
M
MIT News - Artificial intelligence
S
Security @ Cisco Blogs
O
OpenAI News
AI
AI
S
Securelist
Simon Willison's Weblog
Simon Willison's Weblog
The Last Watchdog
The Last Watchdog
月光博客
月光博客
Security Archives - TechRepublic
Security Archives - TechRepublic
L
LINUX DO - 热门话题

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%
Sakha | AI Onboarding Companion for Slack
ankleshh · 2026-06-19 · via Hacker News: Show HN

Now in Beta: 50% off the annual plan

Your new hire's first friend at the company.

Sakha lives in your Slack, learns your company's knowledge, and guides every new hire from Day 1 to fully productive, automatically.

14-day free trialFull accessNo credit card

Knowledge gap detected

6 people asked about parental leave this week. No doc exists.

Integrations

Connect it with apps you already know.

Sakha plugs into the tools your team already lives in. No migration, no new portals, no extra logins.

Why Sakha Exists

Onboarding is broken. Everyone knows it. Nobody fixes it.

33% of new hires leave within 90 days. Only 12% say their company onboarded them well. Not because companies are careless, but because the tools make everything harder than it needs to be.

The Knowledge Black Hole

Critical knowledge lives in Sarah's head, that one Slack thread from March, and a Google Doc nobody can find. When Sarah leaves, the knowledge leaves with her.

The Manager Tax

Your senior engineers spend 15+ hours per new hire answering the same 50 questions. That's $2,000+ in lost productivity per onboarding, every single time.

$0

The Contract Blindspot

HR ships out employment contracts, NDAs, and IP agreements with no second pair of eyes on the clauses. A bad non-compete or overbroad IP grant slips through, and 18 months later it becomes a legal headache nobody saw coming.

0%

of new hires gone within 90 days

0+ hrs

of senior time burned per hire

0

repeat questions per new hire

How It Works

From Slack install to first onboarding in under 10 minutes.

01 · Connect

One-click Slack OAuth. Takes 30 seconds.

02 · Feed

Upload policies and docs, or bulk-import from Drive and Notion.

Employee Handbook142 chunks

IT Equipment Policy38 chunks

Parental Leave Policy24 chunks

03 · Design

Build day-by-day onboarding journeys in the visual flow builder.

04 · Launch

Add a hire, assign a flow, and Sakha takes over: welcoming, guiding, answering.

Hey Alex! Welcome to Acme.

Welcome DM

Sent 9:00 AM · Day 1 of 7 started

Manager report scheduled for Friday

The Solution

An AI companion that owns onboarding, end to end.

From the moment someone accepts an offer to the day they're fully productive, Sakha handles it.

01: Answer

A company brain that never forgets.

Feed Sakha your policies, processes, tools, and culture docs. It embeds everything into a searchable knowledge graph. Any employee can ask Sakha a question in Slack and get an instant, sourced answer. No more @channel asking who knows the expense policy.

  • Semantic search, not keyword matching
  • Auto-detects knowledge gaps
  • Learns from every question asked

Knowledge gap found

6 people asked about parental leave this week. No doc exists.

02: Guide

Day-by-day onboarding on autopilot.

Design onboarding flows that unfold over days and weeks. Sakha delivers each step via Slack DM: welcome messages, team introductions, tool setup checklists, policy reads, and milestone check-ins.

  • Customizable per role and department
  • Checklists with completion tracking
  • Manager gets progress reports

Flow: Engineering · Day-by-Day

Day 1

Welcome DM

Delivering via Slack DM...

03: Review

Review your employment contracts before anyone signs them.

Upload your employment contracts, NDAs, and IP agreements. Sakha's AI analyzes every clause, scores risk, and suggests improvements, then generates a professional counter-draft DOCX with all changes applied. Fix problematic clauses before they become problems.

  • Clause-by-clause risk scoring (0-100)
  • Counter-draft DOCX generation in one click
  • Flags missing clauses your contracts should include

Overall Risk Score

Non-Compete (24 months)

critical

24 months post-employment

Termination Notice (standard)

safe

04: Govern

Create and review company policies in minutes, not weeks.

Need a remote work policy? Data protection policy? Code of conduct? Tell Sakha what you need and it generates a complete, professionally structured policy. Or upload an existing one and get an instant review with gap analysis, compliance flags, and clarity improvements. Publish with one click and it's instantly searchable in Slack.

  • AI generates complete policies from scratch
  • Reviews existing policies for gaps and compliance
  • Publish to auto-add it to the knowledge base for all employees

Reviewing

data_protection_v2.pdf

Gaps FoundCRITICAL

Missing: Data breach notification process

Clarity IssueMEDIUM

"Reasonable measures must be taken"

+ "AES-256 encryption, quarterly access review, MFA required"

See It In Action

This is what your new hire's first week looks like with Sakha.

Honest Comparisons

We know what you're thinking.

You've got options. Here's how Sakha compares, honestly.

"Why not Enboarder, Rippling, or BambooHR?"

Traditional onboarding & HRIS tools

Great at checklists and compliance. But...

No AI knowledge base: new hires still ping the team

No Slack bot: everything lives in a portal nobody checks

No contract review: employment docs are a blindspot

Per-employee pricing ($8 to $25/employee/month)

$5,000 to $20,000 implementation fees

You shouldn't need three tools and a $20K implementation budget to onboard a new hire properly.

Use Cases

Built for every team that hires.

Startups scaling fast

Hiring 5 people a quarter with no HR team? Sakha gives every hire a consistent, structured first week without anyone building it twice.

Remote & distributed teams

No office to absorb culture from. Sakha delivers the norms, the context, and the answers in Slack, across every time zone.

Engineering teams

Stop burning senior engineers on the same 50 questions. New devs self-serve setup guides, architecture docs, and who-owns-what.

People & HR teams

One person running onboarding for the whole company? Sakha is the teammate that never forgets a step, a doc, or a check-in.

Customer support teams

High-volume hiring with deep product knowledge to transfer. Sakha turns your macros, policies, and product docs into instant answers.

Agencies & consultancies

Contractors and project hires need fast, scoped context. Sakha onboards them for the work without weeks of shadowing.

Pricing

Flat pricing. No per-seat math.

14-day free trial. Full access. No credit card.

Starter

$29/mo

For small teams hiring their first 5 to 10 people.

  • 3 active onboardings / month
  • AI knowledge base in Slack
  • Onboarding flow builder
  • 2 contract reviews / month
  • Email support
Start 14-Day Free Trial

$99/mo

For scaling startups hiring 5 to 25 per quarter.

  • 15 active onboardings / month
  • Everything in Starter
  • AI policy generator & reviewer
  • 10 contract reviews / month
  • Knowledge gap detection
  • Priority support
Start 14-Day Free Trial

Scale

$299/mo

For companies onboarding 25+ per month.

  • Unlimited onboardings
  • Everything in Growth
  • Unlimited contract reviews
  • Google Drive & Notion ingestion
  • Analytics & ROI dashboard
  • Dedicated support
Start 14-Day Free Trial

Compare: 50 people on Guru runs $900 to $1,500/mo. Sakha's Growth plan is $99/mo, flat. See full plan details

Sakha is an AI onboarding companion that lives in your Slack. It learns your company's knowledge (policies, processes, tools, culture), guides every new hire through a day-by-day onboarding flow, answers their questions instantly with sourced answers, reviews employment contracts before anyone signs, and generates company policies in minutes.

About 10 minutes. Connect Sakha to Slack with one-click OAuth, upload your docs or bulk-import from Google Drive or Notion, pick or build an onboarding flow, and add your first hire. No engineering work, no implementation fees, no consultants.

Yes. Your knowledge base is isolated per workspace with row-level security, encrypted in transit and at rest, and never used to train AI models. Only your team can query your data, and admins control exactly what Sakha ingests.

Slack is the home base. For knowledge ingestion, Sakha connects to Google Drive and Notion today, with Confluence, GitHub, and more on the roadmap. New hires never need to learn a new portal: everything happens in Slack.

Flat platform pricing, not per-seat: Starter at $29/mo, Growth at $99/mo, and Scale at $299/mo. Every plan starts with a 14-day free trial with full access and no credit card required.

It says so honestly and flags the question as a knowledge gap instead of inventing an answer. Gap detection is built in: when multiple people ask about something undocumented, Sakha surfaces it so you can fill the gap once and answer it forever.

Yes. Onboarding flows are fully customizable per role, department, and seniority. An engineer's Day 1 looks different from a designer's, and Sakha delivers each one automatically with progress tracking for managers.

You pick a plan and keep going, or walk away with no charge. The trial includes full access to everything: onboarding flows, the knowledge base, contract review, and policy generation. No credit card is required to start, so there are no surprise charges.

27 free spots left in the Beta cohort

Stop losing your best people to bad first impressions.

Your next new hire deserves a companion, not a checklist.

No credit card requiredSetup in 2 minutesCancel anytime