Most enterprises don’t have an AI strategy problem, they have an AI execution problem. Even with proven ROI from successful pilots, agents often remain fragmented and unable to integrate with core business processes. That changes today with AG2.ai. Powered by AgentOS, we transform fragmented experiments into a coordinated, production-ready AI workforce. The winners of 2026 won't be the companies with the most AI pilots, they'll be the ones with the most scalable orchestration. Ready to build your AI workforce? 👉 ag2.ai #EnterpriseAI #AgenticAI #OpenSource

AG2 1.1.0 adds support for a different kind of model, TypeSafe's Jev. Jev doesn't do your typical text generation. You send it state and a question, and it answers: yes or no, which option, what score. TypeSafe calls it a System One model which means fast, structured judgment of the kind a knowledgeable person makes in a few seconds. It's blazing fast, which matters when you just need a specific, structured answer back. Which team handles this ticket. Is this safe to run. How severe is this. We've built it into AG2 natively, so a decision agent looks like any other agent. You describe the answer you want as a type, and that type is the question: router = Agent("router", config=TypeSafeConfig(), response_schema=Department) Back comes a real Department, not a string you have to parse and hope about — and on the message metadata, the probabilities across every option and the model's confidence. You decide how to branch. New to Jev? TypeSafe's announcement is worth reading: typesafe.ai/blog/introducing… Also in 1.1.0: security fixes — please upgrade. Get stuck in 👇 docs.ag2.ai & github.com/ag2ai/ag2/release… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource #Jev

AG2 v1.0.0 is out. A ground-up rewrite focused on a production-ready agentic framework: - An event stream as the substrate - An agent harness for long-running work - A multi-agent Network, in one process or across machines - Realtime voice with barge-in - MCP (client and server), A2A, AG-UI, NLIP, ACP - Evaluations for shipping reliable agents - Built to be built on — bring your own adapter, sandbox, skill or provider pip install ag2 AG2 Classic (ConversableAgent) moves to github.com/ag2ai/ag2-classic, docs at classic.docs.ag2.ai. Still maintained. v1.0 isn't a drop-in upgrade, so install autogen or pin classic rather than tracking ag2>=1.0. We also shipped AG2 Assistant, an open-source assistant running on the v1.0 engine — permission-first, with a panel that shows the raw event stream as it works. We use it daily. And because no model has v1.0 in its training data yet, ag2-skills gives your coding agent 20+ Agent Skills for building with AG2 properly: npx skills add ag2ai/ag2-skills Thank you to everyone who contributed, filed issues, tested the betas, and kept building on AG2 along the way. We're looking forward to what you build on v1.0. github.com/ag2ai/ag2 github.com/ag2ai/ag2-assista… github.com/ag2ai/ag2-skills #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

AG2 v0.13.3 is here! 🛣️ 🔬 Beta framework (autogen.beta) 🌐 NEW: Cross-process Network: agents in separate processes can now share channels (WsLink data plane + frame RPC control plane) 🤖 NEW: background_agent_tool: run an agent in the background while the parent continues 🏖️ NEW: Sandbox protocol + LocalSandbox 🧪 Eval: optional reference answer for Agent-as-a-judge and Pairwise judge ⚙️ Classic framework 🔧 AutoPattern TerminateTarget fix 🔧 OpenAI 2.41.0 moderation field sync 🎮 Try the Network in the Playground: playground.ag2.ai/network/ 🙌 Thanks to our contributors! Release: github.com/ag2ai/ag2/release… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource #Network

AG2 v0.13.2 is here! 🛣️ 🔬 Beta framework 🧪 NEW: Agent Evaluations + threshold() scorer for pass/fail gating — try it live at playground.ag2.ai 📁 xAI File API support ⚙️ Classic framework 🤖 NEW: Anthropic V2 + Bedrock V2 clients (UnifiedResponse architecture) 🛡️ Security: CVE fix in ContextExpression (GHSA-9fvw-gr53-m7fw) 🚫 Shell operators blocked in readonly mode 🔧 Tool registration, DeepResearchAgent, LlamaIndex 0.13, MCP StdioConfig fixes 🐟 Framework-wide: TinyFish Search & Fetch tools (Beta extension + Classic experimental) 🙌 Thanks to our contributors, including 4 first-timers! Release: github.com/ag2ai/ag2/release… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

AG2 v0.13.1 is here! 🛣️ 🔬 Beta framework (autogen.beta) ⚡ New: xAI (Grok) provider 🙌 Dynamic Agents (agent creating agents on-the-fly) 🌐 Network: named views, workflow finish tool, consistent envelope rendering 🖥️ AG-UI: reasoning messages both ways + multimodal user content 🚦 ConditionalMiddleware + dynamic_agent tool factory ⚙️ Classic framework 🔧 Fixes: RemoteAgent (A2A), fast_depends + **kwargs tools, Responses image costs, async LangChain tools 🔁 Framework-wide: OpenAI SDK 2.x migration 🙌 Thanks to our contributors! Release: github.com/ag2ai/ag2/release… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

The AG2 Network is a multi-agent runtime where the channel between agents holds the conversation state. So what happens when the hub process restarts? The conversation survives exactly - envelope for envelope, same order, same state. 🔄 This post covers: ✅ The write-ahead log: append to disk first, fan out second ✅ Hub restart: agents reconnect to the same channel and continue ✅ Three identity records: Passport, Resume (ranked by real track record), SKILL.md ✅ The audit log: append-only record of everything hub-wide Same durability contract as Postgres, Kafka, etcd. See what survives 👇 docs.ag2.ai/latest/docs/blog… #AG2 #AI #MultiAgentSystems #AIAgents

🎭 Part 2 of our Network series walks through three dials is now available , each with runnable code: ✅ Time: built-in expectations (acks_within, reply_within, max_silence) ✅ Visibility: audience addressing for private side-channels ✅ Routing: ContextEquals, ToolCalled, dynamic Handoff returns Find the right orchestration and control for your agentic workflows. Get stuck in 👇 docs.ag2.ai/latest/docs/blog… #AG2 #AI #MultiAgentSystems #AIAgents

The new AG2 Network released beta is built around one design choice: the channel between agents is the primitive. Not the agent, not the graph. 🌐 The channel holds the state. The hub is a thin stateless router; restart it, every channel comes back from a persisted state. 🎭 Four conversation shapes ship today, each with runnable code: ✅ consulting: 1↔1, one round ✅ conversation: 1↔1, free-form ✅ discussion: N-party round-robin ✅ workflow: declarative graph with handoffs Get stuck in 👇 docs.ag2.ai/latest/docs/blog… #AG2 #AI #MultiAgentSystems #AIAgents

With OpenAI's GPT Realtime 2 and Thinking Machines' interaction models research preview, natural human-to-agent voice is being realised. On our path to v1.0, we've introduced realtime voice into AG2 Beta — ready for human-to-multi-agent voice interactions. 3 lines of code → a full-duplex voice agent with GPT Realtime 2 🎙️ AG2 Beta's LiveAgent: ✅ One bidirectional realtime session ✅ Built-in VAD + barge-in ✅ Same @agent.tool as a text Agent ✅ OpenAI + Gemini providers Blog with code samples 👇 docs.ag2.ai/latest/docs/blog… #AG2 #AI #VoiceAI #AIAgents #Realtime

AG2 v0.13.0 — a mega release! 🚀 🌐 NEW: Multi-Agent Network — channels (not agents) are the unit. Four built-in choreographies (consulting, conversation, discussion, workflow) + bring your own orchestration. Federation with Passport+Visa. 🎙️ NEW: LiveAgent — full-duplex realtime voice with VAD + barge-in (OpenAI + Gemini) Plus, A2A v1.0 and MCP arrive in Beta. 🎮 Journey through Network now in our Playground: playground.ag2.ai/network/ Release: github.com/ag2ai/ag2/release… 🙌 Thanks to our contributors! #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

AG2 v0.12.3 is here! 🛣️ 🤝 A2A v1.0 spec compatibility — Remote agents with Agent2Agent 🏖️ Beta: SandboxCodeTool — safe code execution in Daytona or Docker 🔍 Beta: Search tools — PerplexitySearchToolkit, Exa 🔧 OpenAI image handling + Gemini fixes 📔 V1.0 Contribution Policy Release: github.com/ag2ai/ag2/release… Roadmap: docs.ag2.ai/latest/docs/user… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

AG2 v0.12.2 is here! 🏗️ The Agent Harness lands in Beta — turning stateless LLM loops into stateful agents that: 🧠 Remember across sessions 📁 Organize their own knowledge (virtual filesystem) ✂️ Manage their own context window 🤝 Share findings with peers Plus: 🔍 PerplexitySearchTool in Beta 🔑 Workload Identity for OpenAI 🔧 Gemini, Redis & AG-UI fixes Release: github.com/ag2ai/ag2/release… New Beta Playground examples: playground.ag2.ai Roadmap: docs.ag2.ai/latest/docs/user… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

Excited to have @daytonaio join in supporting the AG2 Hackathon 🚀 They’ve added $3,000 in credits to the prize pool for the best project. Build and ship real multi-agent systems in a day. May 3 - NYC Free + food 🍕 Spaces are limited: luma.com/42lzgbrz

AG2 v0.12.1 is here! 🛣️ 👥 Community feedback win: PerplexitySearchTool stays (no longer deprecated)! ☁️ Beta: Google Vertex AI support 📁 Beta: Files API client, multi-part ToolResult, Toolkit merging 🔍 New search tools: Tavily, Exa, DDGS 🎯 Advanced orchestration with step events 📦 Docker moved to extra 🙌 Thanks to our contributors! Release: github.com/ag2ai/ag2/release… Roadmap: docs.ag2.ai/latest/docs/user… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

Join us for our AG2 Hackathon in NYC on May 3! Build and present a multi-agent AI project in one day using AG2 Beta - our brand new next-gen multi-agent framework. Hear from IBM Fellow Dinesh Verma, join a hands-on AG2 workshop, then build alongside top engineers and founders. 🏆Prizes for best builds + AG2 credits, swag, and your work featured across the AI community. Free to attend. Food included 🍕. Limited spots - register now: luma.com/42lzgbrz Can't wait to see the next gen AI agent builders in action 🚀

AG2 v0.12.0 – The Path to v1.0 begins! 🛣️ 🚀 Beta → v1.0 journey kicks off ⚠️ Deprecation notices (removed in v0.14) — community feedback window open! 🔬 Beta: Toolkits, Tasks, Observer API, AG-UI, Multimodal input, AgentSpec 🧰 New tools: FilesystemToolset, LocalShellTool, Skills 🎉 DaytonaCodeExecutor + NLIP 🛡️ CVE-2025-69872 fixed Roadmap: docs.ag2.ai/latest/docs/user… Release: github.com/ag2ai/ag2/release… 🙌 Share your feedback! #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource

93% of API teams hit integration walls (Postman 2025). That's why we partnered with Arcade.dev: AG2 agents now connect to 8,000+ tools with zero credential management. One function call. OAuth handled. Gmail example live: docs.ag2.ai/latest/docs/blog… #AG2 #AI #Arcade #OAuth #MCP #Gmail

Your agents can reason and act. But can they express? Most agents are limited to conversational responses. Users need cards, forms, dashboards, and interactivity. Google's A2UI gives agents a visual vocabulary. AG2's new A2UIAgent generates rich, interactive UI — rendered natively on any platform. One agent. Every surface. ag2.ai/blog/a2ui

AG2 v0.11.5 is here! 🚀 🖥️ AG2 CLI – build, run, and test multi-agent applications agents directly from the terminal. Empowers your coding assistant! 🖥️ A2UIAgent – A2UI for agentically built and dynamic frontends 🔬 Beta advances: Telemetry, ResponseSchema, RedisStream, WebFetchTool, tool-scoped middleware, MemoryTool, Image Generation, Shell Tool 📔 Arcade.dev integration blog + release roadmap 🙌 Thanks to our contributors! Release: github.com/ag2ai/ag2/release… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource #A2UI #CLI

AG2 v0.11.3 & v0.11.4 are here! 🚀 🎉 AG2 Beta — ground-up redesign for production agents: streaming, multi-provider LLM support, typed tools with DI, middleware pipeline, first-class testing 🐟 TinyFish agentic web scraper 🔍 QuickResearchTool for parallel web research 🛡️ Security hardening: shell injection, path traversal, credential redaction 🔄 Mistral V2 + Gemini streaming 🙌 Thanks to our contributors! Release: github.com/ag2ai/ag2/release… #AG2 #AI #MultiAgentSystems #AIAgents #OpenSource #Beta