Starting today, a LangChain's Managed Deep Agent deploy provisions... your Slack app for you 🤯 No manifest. No OAuth redirects. No bot tokens to copy around. One command, and your agent says 👋 in Slack.show more

HermesOS free tier is now live. No credit card... required. No markup on AI costs (BYO key). No trial countdown. Just sign up and deploy your own persistent AI agent. You get: • Persistent memory • Browser automation • Terminal access • Tool use • Scheduled tasks • Telegram, Discord, Slack & WhatsApp integrations Managed AI agent hosting. Live in 5 minutes.show more

Today, we launched agent-to-agent conversations in Slack to give... you real AI coworkers. Vellum assistants now talk to each other and coordinate work with your team all inside your workspace. We tested it with two agents in our own Slack. They planned our offsite for 19 people in 1 day 🧵 Here’s how they did it:show more

Starting today, LangChain’s Managed Deep Agents can bake your... agent’s environment at deploy time. 🧑‍💻 No clone. No install. No repeated setup. Drop in or a Dockerfile. Bake once. Every new thread starts ready. 👇show more

CopilotKit Open Sources Channels SDK: An MIT Licensed Library... That Runs Any AG-UI Agent Inside Slack And Microsoft Teams No per-platform rewrite. No platform credentials in your agent process. No second agent to maintain. Here's how it works: 1. Describe once, render native One message description is lowered to a serializable intermediate representation, then rendered in each platform's own format. → Block Kit on Slack, Adaptive Cards on Teams 2. Your agent doesn't move It connects over AG-UI, so the model, tools and business logic stay where they are. → LangGraph, CrewAI, Mastra, Pydantic AI, Google ADK 3. The runtime owns the lifecycle There is no channel.start(). You await channels.ready(), so a broken config fails startup loudly instead of silently. → ready() · status() · stop() 4. The concurrency trap Turns default to "parallel", and only the managed adapter serializes same-thread deliveries. On a direct adapter, one shared agent instance means two runs corrupt each other. → "parallel" (default) · "serial" · "drop" 5. The numbers → 0.7.3, shipped August 4, MIT licensed → 5 adapters: /slack, /teams, /discord, /telegram, /whatsapp → Node.js 22+, ESM only, one long-running process → Slack and Teams GA; Discord and WhatsApp next The key takeaway: one agent, five adapters, and platform credentials that never touch your process. Every channel needs a CopilotKit Intelligence key — free tier included, no standalone path. Full analysis: GitHub Repo: Technical details: CopilotKit🪁show more

I built a 1-click deploy for Hermes Agent No... terminal, no Docker, no API keys. In one click it: → Spins up a dedicated cloud container → Configures Hermes with persistent memory & 70+ skills → Connects it to your Telegram bot → Goes live in under 60 seconds Your own AI agent that learns, creates skills, and gets smarter the longer it runs. Reply "HERMES" + RT and I'll send you the link (must be following so I can DM)show more

Yesterday we launched the Agent Builder Template Library. Agent... templates are more than a starting point. They’re ready to deploy and fully customizable by giving your agent feedback in plain language. 🧵 for highlights Try Agent Builder:show more

The mintlify agent is now available on the web,... in addition to Slack, to help you make edits, create PRs, and keep your docs up to date.show more

No coding. No data leaks. Just your agent, live... on-chain. Build a private AI agent or app in the Vibe Code Challenge: Agent Edition. 175,000 $COTI in prizes Agent Skills, MCP, and Messaging SDK Works with Claude, OpenAI, Hermes, Manus Build it to win it. Enter now!show more

Everyone shipped an "AI employee in Slack" this summer.... Claude Tag, Grok Bot, Slack AI. All of them wait to be tagged. Mio, launched today, is the first one that starts on its own and the first one the whole team shares: - reads Slack, Notion, Linear, HubSpot and 3,000+ tools overnight - does the work, then DMs you what it did - finance and engineering use the same agent, each with their own permissions - sensitive actions wait for approval - 10,000s of tasks done in beta, 30 seconds to install Your team's AI should know what the rest of your team is working on. This is the first one that does. Beta open, first 100 companies get $100 in credits.show more

Someone built PrivatClaw. A 100% private, always on Al... agent that runs in Telegram, Slack, Discord, or WhatsApp no setup, no API keys, no risk. It browses the web, sends emails, does outreach, automates workflows, and works 24/7 on an isolated server while you sleep.show more

🚨Something big happened today in agentic AI. Your agent... can now connect with your friend’s agent with collaborator knowledge and more. Mercury agent just cracked the missing layer in agentic AI. No need to have half lid open macs.show more

$1.5M is up for grabs in the Great Tournament... of Agents! Build and deploy a trading agent using Cod3x Create today for your chance to win. Don't know how to build an agent? Join our FREE BootCamp @show more

Charmed to meet you, Muse 👋 We put Poki,... KITE AI ✈️ KBW🇰🇷’s mascot, inside Muse for a small experiment. If you’re exploring Muse, try Kite Agent Passport there and see what your agent can do: ▷ Give your agent a secure, verifiable identity ▷ Set spending limits and trusted recipients ▷ Keep approval for high-value transfers in your hands Try Kite Agent Passport in Muse: Let your agent act. You stay in control. 🪁show more

You can now give your Agent its own: +... Profile + Wallet + DMs + Network One setup prompt. No human in the loop required. An open playground for people and agents to interact. Works with Hermes, Openclaw and any other harness. Copy the prompt below ↓↓↓show more

This is what trading looks like now. No order... forms. No tabs. You just tell your agent what you want and it handles the rest. The whole thing took 18 seconds. Creating your own agent takes under a minute. ATLAS is live on Forkast today! 🚀show more

BREAKING: Someone just made sharing from AI agents 1000x... easier. It's called and it hosts anything your agent builds in 5 seconds flat. No GitHub. No Vercel. No sign-up required. Just tell your agent: "publish to → get a live URL instantly. 100% Free.show more

Your [Instinct, GrokBot, Muse] agent can read text. Now,... let it hear. Particle now supports x402: intelligence from 135,000+ podcasts, with zero friction for your bots. No account. No API key. Tell your agent: “Go to and use Particle via x402”show more

Today we're introducing Launchvideo Skills and references that let... your agent create tasteful product videos directly in your codebase. Local-first, AI native, no subscription.show more

This n8n agent tracks your competitors' Facebook ads on... autopilot 🤯 And drops a full AI breakdown in Slack every morning. Hooks. Offers. CTAs. Formats. All waiting for you before your first coffee. Perfect for e-comm brands & agencies who refuse to get outspent blindly. Here's the problem: Your competitors are testing 20+ new ads a week. New hooks, new angles, new offers. By the time you manually check the Ad Library, you've already missed the testing window. The winning creative is scaled. The moment is gone. This n8n automation stays on it for you: → Runs every morning automatically → Scrapes competitor ads via Foreplay API → AI analyzes each new ad (hook, CTA, offer, format) → Full breakdown delivered to Slack → Flags patterns and winning angles No manual Ad Library checks. No "wait, when did they launch that?" No falling behind while you're busy running your own ads. What lands in Slack every morning: - Every new ad from competitors you're tracking - AI breakdown of what hooks they're testing - Offers and CTAs they're pushing - Patterns in what's getting spend Built 100% in n8n. Want the full workflow? > Comment "SLACK" > Like this post And I'll send it over (must be following so I can DM)show more