You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Magentic-UI is a **research prototype** of a human-centered interface powered by a multi-agent system that can browse and perform actions on the web, generate and execute code, and generate and analyze files.
16
+
Magentic-UI is a **research prototype** human-centered AI agent that solves complex web and coding tasks that may require monitoring. Unlike other black-box agents, the system reveals its plan before executions, lets you guide its actions, and requests approval for sensitive operations while browsing websites, executing code, and analyzing files.
17
+
*Check out the [demo section](#demos) for inspiration on what tasks you can accomplish.*
18
+
19
+
## ✨ What's New
20
+
21
+
-**"Tell me When"**: Automate monitoring tasks and repeatable workflows that require web or API access that span minutes to days. *Learn more [here](https://www.microsoft.com/en-us/research/?p=1152051&preview=1&_ppp=a53d9c1d19).*
22
+
-**File Upload Support**: Upload any file through the UI for analysis or modification
23
+
-**MCP Agents**: Extend capabilities with your favorite MCP servers
24
+
-**Easier Installation**: We have uploaded our docker containers to GHCR so you no longer need to build any containers! Installation time now is much quicker.
@@ -37,12 +45,6 @@ Then open <http://localhost:8081> in your browser to interact with Magentic-UI!
37
45
38
46
> **Prerequisites**: Requires Docker and Python 3.10+. Windows users should use WSL2. See [detailed installation](#️-installation) for more info.
39
47
40
-
## ✨ What's New
41
-
42
-
-**File Upload Support**: Upload any file through the UI for analysis or modification
43
-
-**MCP Agents**: Extend capabilities with your favorite MCP servers
44
-
-**Easier Installation**: We have uploaded our docker containers to GHCR so you no longer need to build any containers! Installation time now is much quicker.
45
-
46
48
## Alternative Usage Options
47
49
48
50
**Without Docker** (limited functionality: no code execution):
@@ -70,37 +72,58 @@ For further details on installation please read the <a href="#️-installation
70
72
71
73
## Quick Navigation:
72
74
<palign="center">
73
-
<ahref="#-how-it-works">🟪 How it Works</a> |
Magentic-UI is especially useful for web tasks that require actions on the web (e.g., filling a form, customizing a food order), deep navigation through websites not indexed by search engines (e.g., filtering flights, finding a link from a personal site) or tasks that need web navigation and code execution (e.g., generate a chart from online data).
The interface of Magentic-UI is displayed in the screenshot above and consists of two panels. The left side panel is the sessions navigator where users can create new sessions to solve new tasks, switch between sessions and check on session progress with the session status indicators (🔴 needs input, ✅ task done, ↺ task in progress).
100
+
**🏠 Airbnb Price Analysis**
101
+
*MCP agent integration*
90
102
91
-
The right-side panel displays the session selected. This is where you can type your query to Magentic-UI alongside any file attachments and observe detailed task progress as well as interact with the agents. The session display itself is split in two panels: the left side is where Magentic-UI presents the plan, task progress and asks for action approvals, the right side is a browser view where you can see web agent actions in real time and interact with the browser. Finally, at the top of the session display is a progress bar that updates as Magentic-UI makes progress.
Magentic-UI is especially useful for web tasks that require actions on the web (e.g., filling a form, customizing a food order), deep navigation through websites not indexed by search engines (e.g., filtering flights, finding a link from a personal site) or tasks that need web navigation and code execution (e.g., generate a chart from online data).
104
127
105
128
What differentiates Magentic-UI from other browser use offerings is its transparent and controllable interface that allows for efficient human-in-the-loop involvement. Magentic-UI is built using [AutoGen](https://github.com/microsoft/autogen) and provides a platform to study human-agent interaction and experiment with web agents. Key features include:
0 commit comments