AgentCanvas
AgentCanvas is the first visual orchestration canvas for Gemini 3.5 Flash sub-agent pipelines.
Core trick
Renders each Gemini sub-agent as a draggable node and streams every tool call to the canvas over SSE.
Description
AgentCanvas is the first visual orchestration canvas for Gemini 3.5 Flash sub-agent pipelines. Most multi-agent systems today are black boxes - you run code, agents execute, you see a final output with no visibility into what happened in between.
AgentCanvas changes that. Drag and drop Gemini agents onto a canvas, connect them into pipelines, define their roles and tools, and watch every tool call execute in real time with a live animated trace. Every agent handoff, every tool call, every output is visible as it happens.
Built entirely during the hackathon. Three demo pipelines included: Research (Scout → Analyst → Writer), Productivity (Planner → Scheduler → Communicator), and Engineering (Researcher → Engineer → Reviewer). Fully customizable add agents, define roles, draw connections, run any pipeline.
Tech stack: React frontend with live SSE streaming, FastAPI backend, Gemini 3.5 Flash for all agent execution.
README excerpt
# AgentCanvas ### Visual Multi-Agent Orchestration with Gemini 3.5 Flash Build, connect, and run Gemini sub-agent pipelines visually. Watch every tool call execute in real time with a live animated trace. **Built at Google I/O Hackathon 2026** --- ## What it does AgentCanvas lets you drag and drop Gemini agents onto a canvas, connect them into pipelines, and watch them execute in real time. Every tool call, every handoff, every output is traced live as it happens. - Visual canvas with draggable agent nodes - Connect agents by dragging ports - Live streaming execution with animated edges - Per-agent tool call trace in real time - Three built-in demo pipelines (Research, Productivity, Engineering) - Add and edit custom agents with custom roles and tools --- ## Demo Watch the pipeline execute in real time with live Gemini 3.5 Flash output and animated execution trace. **Research Pipeline** — Scout → Analyst → Writer  **Productivity Pipeline** — Planner → Scheduler → Communicator  **Engineering Pipeline** — Researcher → Engineer → Reviewer  ## Setup **Step 1: Clone the repo** ```bash git clone https://github.com/preeti13parihar/agentcanvas.git cd agentcanvas ``` **Step 2: Get your Gemini API key** Go to https://aistudio.google.com, click Get API key, copy it. **Step 3: Start the backend** ```bash cd backend pip install -r