- 01Read the task
- 02Call a tool
- 03Check the result
Home/Tools & Agents
What the agent is allowed to do.
Tools, workflows, and the open-source projects agents actually use.
- browser-use
- OpenHands
- MCP servers
- AutoGen
The tool only does what the setup allows.
/ Tools & Agents
AI agent news and tools, including the Model Context Protocol. What the systems do, and what a demo does not prove.

LangChain hits $3B valuation with $300M Series C for enterprise AI agents
Agent management startup LangChain has raised a $300 million Series C at a $3 billion valuation led by CapitalG. The company now claims 7,000 customers for its LangSmith agent development platform, more than doubling its $1.25 billion valuation from 2025.

Meta's Muse AI can now call US businesses for you
Meta's consumer AI agent Muse can place calls to US businesses on behalf of paid subscribers, handling tasks like reservations, insurance calls, and DMV inquiries.

Adobe goes all in on agentic AI at Max 2026 with MCP integrations and always-on Firefly agents
At its Max 2026 conference in Miami Beach, Adobe announced MCP integrations that let third-party AI agents like ChatGPT, Claude and Gemini work directly in Creative Cloud apps, always-on agents for background creative tasks, and a new Firefly AI creative studio that brings together Adobe's tools, third-party models and the Creative Agent in one place.

Aina launches an AI smart ring with a screen, joystick, and microphone for $399
Aina released a $399 smart ring with a screen, joystick, microphone and speaker, positioning it as the interface for interacting with AI agents from your finger. Preorders open now with shipping set for January 2027.

Meta lets Muse users build custom AI app experiences called spaces
Meta launched Spaces, a new feature that lets Muse AI users create custom app-like workspaces for specific tasks by describing them in chat.

Airbnb commits to launching an AI travel agent in the first half of 2027
Airbnb announced a dedicated AI travel agent that will compose maps, photos, comparisons, and itineraries in real time, launching in the first half of 2027 alongside its strongest quarterly revenue growth in three years.

Perplexity launches Teammates, always-on AI agents for work that can complete multiple roles simultaneously
Perplexity launched Teammates, always-on AI agents that can take on multiple roles within a workspace simultaneously, competing with OpenAI Dots and Claude Duet at $200 per month on the Max plan.

SoundCloud lets ElevenMusic users publish AI-generated songs directly from ElevenLabs
SoundCloud becomes the first platform outside ElevenLabs where ElevenMusic users can publish AI-generated tracks directly, with AI labels applied automatically and a free ElevenMusic Pro trial for Artist Pro subscribers.

Meta opens real-time voice and video chat with Muse AI to all US users
Meta rolled out real-time voice and video conversations with its Muse AI agent to all US users, featuring expressive animated avatars. The launch precedes a Tamagotchi-like wearable device due by year-end.

Anthropic launches Claude Personal Finance, connecting to bank accounts via Plaid for read-only spending analysis
Anthropic launched Personal Finance for Claude Pro, Max and Ultra subscribers in the US, connecting bank and card accounts via Plaid for read-only spending analysis, bill tracking and duplicate charge alerts.

Box taps Nvidia's Nemotron for faster, cheaper AI agent content retrieval
Box unveiled Box Content Retrieval at BoxWorks 2026, using Nvidia Nemotron embedding models to power faster, more accurate and less expensive queries for AI agents.

Gemini for Home now plugs into AT&T's smart security system
AT&T has integrated Gemini for Home into its Connected Life security system, enabling natural language video search, AI-generated event descriptions, and daily household summaries. The integration makes AT&T the first home security provider to use Google Home Premium's advanced capabilities.

ChatGPT now creates animated GIFs as OpenAI rolls out Images 2.6
OpenAI has added native animated GIF creation to ChatGPT as part of its Images 2.6 rollout. Users can create GIFs from prompts or uploaded photos, adjust playback speed, edit individual frames, and share them directly. The update also brings faster image generation across ChatGPT and the API.

Meta acquires Conductor to run teams of AI coding agents in parallel
Meta has acquired Conductor, an AI coding startup that lets developers run teams of coding agents from different labs in parallel workspaces. CEO Charlie Holtz and CTO Jackson de Campos will join Meta Superintelligence Labs, and Conductor's cloud service will shut down on November 20.

Apple opens Siri AI to every third-party app in the iOS 27.3 developer preview
Any app can now bring its content and actions into Siri AI through App Intents, with a new skills feature that chains several actions into one request.

OpenAI builds Pando, a new Git backend that cuts push latency 5x for agent-scale development
OpenAI rebuilt its source-control backend for a monorepo where Codex-driven development generates hundreds of concurrent pushes per minute. The new backend, called Pando, uses causal consistency and reusable packfiles to cut median push latency by nearly 5x.

HuggingFace proposes Model Integration Contracts to catch Transformers regressions before they ship
HuggingFace's Transformers library now supports 750-plus model types and its test suite runs 88,000 tests on every commit, but integration bugs still reach main. Model Integration Contracts use shrunk model fixtures to catch regressions at the PR level.

Anthropic adds two sentences to Claude Code to stop AI video game clones
Anthropic updated Claude Code's system prompt on Opus 5.5 to prevent the AI tool from recreating specific existing video games, as retro gaming gets 'overrun' with AI-made decompilations and clones.

DeepSeek adds a creator mode that lets Harness users build plugins by describing them
DeepSeek introduced creator mode for its Harness agent platform on November 2, letting users generate working plugins, including a 3D model viewer, a video editing workbench and a paper reader, from ordinary English prompts.

Google takes Dreambeans to India with 13 languages and a privacy question attached
Dreambeans, Google's app for AI-generated personal stories drawn from Gmail, Photos and Calendar, launched in India with 13 local languages. It is the app's first market outside the US, and its download numbers there are small.

Anthropic blocks Claude from reverse-engineering video games, hitting modders and developers too
Anthropic's Claude AI has quietly started refusing work related to video game modding, decompilation, and reverse engineering, blocking both malicious cloning attempts and legitimate development tasks.

Anthropic renames Claude Max plans to Ultra, drops the five-hour limit for verified accounts
Anthropic renamed its Max 5x and Max 20x tiers to Max and Ultra on October 31, with no price change. For verified Ultra subscribers, the rolling five-hour session limit is gone — but weekly usage caps stay the same.

Vercel Labs open-sources agent-desktop, a Rust CLI that gives any AI agent computer use through accessibility trees
Vercel Labs released agent-desktop 1.0.2 under Apache-2.0 on October 30. The Rust CLI reads desktop apps through OS accessibility trees instead of screenshots, giving agents stable refs and retry-safe actions.

DeepSeek open-sources Super-Agent, a coding agent that reads team chats
The MIT-licensed research prototype listens to GitHub and Feishu, dispatches work to isolated worker sessions, and replies in the original conversation with a pull request.

Researchers find bugs in five AI developer tools as Codex and VS Code flaws stay unpatched
Forever Security found vulnerabilities in five AI developer tools — Cursor, GitHub Copilot, Claude Desktop, VS Code and Codex — rooted in the privileged embedded browsers these tools ship. Cursor's flaw enabled host command execution via prompt injection; Copilot allowed address-bar spoofing; and Codex and VS Code still have arbitrary file-read bugs unpatched.

Spawn builds a massively multiplayer game world with autonomous AI agents burning $3 million a month
Spawn is a massively multiplayer online environment where players modify the game world through natural-language prompts to an in-game agent, while a swarm of Fable 5-powered AI agents edits live game code and ships to production hourly, burning over $3 million in tokens per month according to its creator Jacob Sansbury.

vLLM 0.32.0 patches eight security vulnerabilities including Ghostscript remote code execution
vLLM, the popular open-source LLM inference and serving engine, shipped version 0.32.0 on 28 October 2026 patching eight CVEs, including a critical shared-memory handle forgery that reaches pickle.loads in the model worker and an EPS image-input chain that can trigger Ghostscript command execution on vulnerable hosts.

Google opens Android Studio to third-party AI coding agents with 'Bring Your Own Agent'
Google announced at the Android Dev Summit that Android Studio now supports more than 40 third-party coding agents through its 'Bring Your Own Agent' feature, including Anthropic's Claude Agent, OpenAI's Codex and Google Antigravity, via the open Agent Client Protocol. New Android CLI tools help agents finish UI tasks 77 percent faster with up to three times fewer tokens, per Google.

Local AI agents: what runs on your machine
A local AI agent runs its model and tools on hardware you operate. A hosted agent loop does that work on a provider’s side.

Opera launches WebAI, a proposed web standard for running AI locally in the browser
Opera launched WebAI, a proposed web standard backed by Google and Microsoft, that lets websites and extensions use AI running locally in the browser, now in early preview across Opera One, Opera GX and Opera Neon.

Siri AI expands to five new languages with the iOS 27.2 updates
Apple's reimagined Siri AI is now available in French, Japanese, Korean, Portuguese and Spanish with the 27.2 software updates released on 26 October 2026.

Claude Enterprise turns on unified chat and Cowork by default on November 16
Anthropic made its combined chat and Cowork experience generally available for Claude Enterprise. Eligible organisations get it automatically on 16 November unless admins opt out.

Users say Claude Opus 5.5 now refuses to help root smart TVs
Claude users report Opus 5.5 stopping on smart TV rooting and reverse engineering. Anthropic has not confirmed a change, but its own cyber safeguards already block most exploit work.

Google open-sources Elephant-Goldfish, a plugin that stress-tests AI coding plans
Google's Apache 2.0 Elephant-Goldfish Model plugin has a long-memory AI session draft a design document and fresh, zero-context subagents attack it before any code is written.

Unitree Go2 flaw lets a forged AI reply run root commands on the robot dog
CVE-2026-115995 lets anyone who can pose as the Go2 voice assistant's cloud model turn a set_volume call into root shell commands. VulDB rates it 9.6, and the fixed firmware is unclear.

Google lets you create and fill Gemini Notebooks from a Gemini chat
Gemini Notebook, formerly NotebookLM, is now a connected app in Gemini. Mention it in a chat to create notebooks, add sources or query them. It is on by default outside the EEA.

