MassGen

We're excited to release MassGen v0.1.51, focused on Reviewing Coordination & Change Documents! 🚀 Review modal with multi-file diff visualization. Decision journal system for multi-agent coordination traceability. Changedoc-anchored evaluation checklists with gap reports. Drift conflict policy for safer change application. `--cwd-context` CLI flag. Release notes: https://lnkd.in/gc-pyz9t Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams — Run agents in parallel where they share workspaces, vote on the best solution, and reach consensus, or use decomposition mode to break complex tasks into subtasks owned by individual agents with a presenter synthesizing the final result. Both modes support unique personas, refinement, and subagent spawning. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Interactive TUI (Default) & Web UI — Watch agents collaborate in real-time through an interactive Textual Terminal UI (Normal/Planning/Execute via Shift+Tab), collapsible tool batching, timeline streaming, and keyboard shortcuts. Also available: browser-based Web UI with React frontend for visual workflows.👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.50, focused on Improved Planning Mode! 🚀 Chunked plan execution for safer long-form task completion with progress checkpoints. Skill lifecycle management with consolidation, organizer, and previous-session skill loading. Iterative planning review modal. Responsive TUI mode bar. Worktree improvements with branch accumulation and cross-agent diff visibility. Release notes: https://lnkd.in/gWbNfmg5 Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams — Run agents in parallel where they share workspaces, vote on the best solution, and reach consensus, or use decomposition mode to break complex tasks into subtasks owned by individual agents with a presenter synthesizing the final result. Both modes support unique personas, refinement, and subagent spawning. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Interactive TUI (Default) & Web UI — Watch agents collaborate in real-time through an interactive Textual Terminal UI (Normal/Planning/Execute via Shift+Tab), collapsible tool batching, timeline streaming, and keyboard shortcuts. Also available: browser-based Web UI with React frontend for visual workflows.👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.49, focused on Coordination Quality! 🚀 Log analysis mode now built into the TUI for in-app run analysis. Fairness gate prevents fast agents from dominating, and checklist voting brings structured quality evaluation. Plus: automated testing infrastructure, persona generation now in TUI mode bar, and bug fixes. Release notes: https://lnkd.in/gsNgjnvG Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams — Run agents in parallel where they share workspaces, vote on the best solution, and reach consensus, or use decomposition mode to break complex tasks into subtasks owned by individual agents with a presenter synthesizing the final result. Both modes support unique personas, refinement, and subagent spawning. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Interactive TUI (Default) & Web UI — Watch agents collaborate in real-time through an interactive Textual Terminal UI (Normal/Planning/Execute via Shift+Tab), collapsible tool batching, timeline streaming, and keyboard shortcuts. Also available: browser-based Web UI with React frontend for visual workflows.👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.48, adding Decomposition Mode! 🚀 A new coordination mode that decomposes tasks into subtasks assigned to individual agents, with a presenter agent synthesizing the final result. Plus: Worktree isolation for safe file writes with review modal, quickstart wizard Docker setup, and bug fixes. Release notes: https://lnkd.in/g2KrtQJk Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams (in parallel) — Agents with unique personas share workspaces, answer each other's questions, generate and refine solutions, vote on the best solution, and can spawn subagents for multi-level coordination. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Interactive TUI (Default) & Web UI — Watch agents collaborate in real-time through an interactive Textual Terminal UI (Normal/Planning/Execute via Shift+Tab), collapsible tool batching, timeline streaming, and keyboard shortcuts. Also available: browser-based Web UI with React frontend for visual workflows.👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.47, adding Codex Backend Support! 🚀 OpenAI Codex CLI is now a fully supported backend with local and Docker execution, OAuth and API key authentication. A new NativeToolMixin provides shared native tool handling across CLI-based backends (Codex and Claude Code). Plus: TUI theme system refactored to palette-based architecture, per-agent voting sensitivity, and bug fixes. Release notes: https://lnkd.in/gY95cpBe Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams (in parallel) — Agents with unique personas share workspaces, answer each other's questions, generate and refine solutions, vote on the best solution, and can spawn subagents for multi-level coordination. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Interactive TUI (Default) & Web UI — Watch agents collaborate in real-time through an interactive Textual Terminal UI (Normal/Planning/Execute via Shift+Tab), collapsible tool batching, timeline streaming, and keyboard shortcuts. Also available: browser-based Web UI with React frontend for visual workflows.👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.46, featuring real-time subagent TUI streaming! 🚀 Subagents now display in interactive preview cards that expand to full timeline views, with a major TUI event architecture refactor for better maintainability and consistency. Release notes: https://lnkd.in/g4e5XAEp Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams (in parallel) — Agents with unique personas share workspaces, answer each other's questions, generate and refine solutions, vote on the best solution, and can spawn subagents for multi-level coordination. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Interactive TUI (Default) & Web UI — Watch agents collaborate in real-time through an interactive Textual Terminal UI (Normal/Planning/Execute via Shift+Tab), collapsible tool batching, timeline streaming, and keyboard shortcuts. Also available: browser-based Web UI with React frontend for visual workflows.👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.45, featuring TUI (Textual Terminal) as the default display mode! 🚀 All users now get the superior interactive terminal UI by default, with automatic migration for existing configs. Setup and quickstart wizards by default work via textual ui, and documentation has been enhanced to highlight the TUI experience. Release notes: https://lnkd.in/ggYkx7Te Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams (in parallel) — Agents with unique personas share workspaces, answer each other's questions, generate and refine solutions, vote on the best solution, and can spawn subagents for multi-level coordination. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Interactive TUI (Default) & Web UI — Watch agents collaborate in real-time through an interactive Textual Terminal UI (Normal/Planning/Execute via Shift+Tab), collapsible tool batching, timeline streaming, and keyboard shortcuts. Also available: browser-based Web UI with React frontend for visual workflows.👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.44, featuring Execute Mode for plan selection in the TUI! 🔄 Cycle through Normal → Planning → Execute modes via Shift+Tab, browse and select from existing plans, and automatically preserve context paths between planning and execution phases. Enhanced case studies page with setup guides for first-time users. Release notes: https://lnkd.in/gh-j3b3T Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams (in parallel) — Agents with unique personas share workspaces, answer each other's questions, generate and refine solutions, vote on the best solution, and can spawn subagents for multi-level coordination. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Real-Time Web UI & Terminal Dashboards — Watch agents collaborate live through a browser-based React UI or interactive terminal dashboards, complete with coordination event visualizations. 👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.43, featuring Tool Call Batching in the TUI! 🚀 Consecutive MCP tool calls are now grouped into collapsible tree views—see filesystem operations batched with timing info, expand to view details, and enjoy cleaner final answer presentation with reasoning separated from results. Experience it: massgen --display textual Release notes: https://lnkd.in/g647MbeQ Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams (in parallel) — Agents with unique personas share workspaces, answer each other's questions, generate and refine solutions, vote on the best solution, and can spawn subagents for multi-level coordination. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Real-Time Web UI & Terminal Dashboards — Watch agents collaborate live through a browser-based React UI or interactive terminal dashboards, complete with coordination event visualizations. 👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt

We're excited to release MassGen v0.1.42, featuring Human Input Queue! 🚀 Guide your agents in real-time—inject feedback mid-stream while they work, keeping them on track without interrupting their flow. Plus, a comprehensive TUI Visual Redesign brings a modern "Conversational AI" aesthetic to the terminal. Experience it: massgen --display textual Release notes: https://lnkd.in/gPmBNabn Feature highlights: 🧠Supports diverse backends — Access a wide range of open-source and proprietary models (local, Gemini 3, GPT-5.2, GPT-5.1-Codex, Claude, GLM, and other enterprise backends) and agents (AG2, AgentScope, Claude Code, LangGraph, and smolagents). 👉 More Info: https://lnkd.in/gdXw-ZiN 🤖Build collaborative multi-agent teams (in parallel) — Agents with unique personas share workspaces, answer each other's questions, generate and refine solutions, vote on the best solution, and can spawn subagents for multi-level coordination. 👉 More Info: https://lnkd.in/gTH5prec 📋Task planning & execution — Agents create structured plans separating "what to build" from "how to build it", execute saved plans, and verify work at logical checkpoints with persistent storage and execution tracking. 👉 More Info: https://lnkd.in/gy5qtbau 🛠️Work with files, apps, and projects — With MCP tools and agent skills, agents can read/write files, browse websites, connect to apps, use computers, and edit existing project files with a robust permission system. 👉 More Info: https://lnkd.in/gXaCJfkq 💾Session continuity — Multi-turn conversations with context compression, session resumption, and evolving skills that persist and improve across sessions. 👉 More Info: https://lnkd.in/gQuhFtuh 🖼️Multi-modal support — Agents can understand and generate files, videos, images, and audio collaboratively. 👉 More Info: https://lnkd.in/gHNVdTKa 🐳Code execution — Each agent can run commands (with Docker support, if installed) and use code mode for efficient filesystem-discoverable tools with large token reduction. 👉 More Info: https://lnkd.in/gDy5imFE 🖥️Real-Time Web UI & Terminal Dashboards — Watch agents collaborate live through a browser-based React UI or interactive terminal dashboards, complete with coordination event visualizations. 👉 More Info: https://lnkd.in/gxWNKCB6 🪪Trace workflows — Orchestration logs, workspace history, cost tracking, and optional Logfire integration make agent behavior easy to understand and debug. 👉 More Info: https://lnkd.in/gecFJE2z 📤Session sharing — Export multi-turn sessions to GitHub Gist and view them in the MassGen Viewer web app with artifact previews. 👉 More Info: https://lnkd.in/gsBjn7Zt