Skip to main content

WebUI for AgentMake AI; AgentMake AI: a software developement kit for developing agentic AI applications that support 16 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

Project description

# agentmakestudio

AgentMake AI Studio - Web UI built for working with [AgentMake AI](https://github.com/eliranwong/agentmake)

![Image](https://github.com/user-attachments/assets/3e8dbe05-855d-4c0a-a581-bc262443b452)

# Install

> pip install –upgrade agentmakestudio

To support Vertex AI:

> pip install –upgrade “agentmakestudio[genai]”

# Export Path

To export Path for running AgentMake and AgentMake Studio, assuming you install agentmakestudio in a virtual environment ai, e.g.:

` cd python3 -m venv ai source ai/bin/activate pip install --upgrade "agentmake[studio,genai]" echo export "PATH=$PATH:$(pwd)/ai/bin" >> ~/.bashrc `

# Configurations

To configure AgentMake AI backends, like API keys, run:

> ai -ec

# Run

> agentmakestudio

Open http://localhost:32123 in a web browser.

# Run with Custom Port

For example, use port 33333

> agentmakestudio –port 33333

Open http://localhost:33333 in a web browser.

# Auto Run

Below is an example bash script that runs agentmakestudio automatically:

https://github.com/eliranwong/agentmakestudio/blob/main/README.md

You may place the content script in, e.g. ~/.bashrc

# Usage

Enter your prompt and get a response.

Use the menu items to specify [agentic components](https://github.com/eliranwong/agentmake#introducing-agentic-components) optionally.

The following shortcuts are supported for specifying agent, tool, system, instruction in a single turn. These shortcuts work only if there is no agent being selected in the menu and you declar a shortcut at the beginning of your prompt:

  • agent - @@ followed by an agent name, e.g. @@reasoning

  • tool - @ followed by a tool name, e.g. @magic

  • system - ++ followed by a system name, e.g. ++auto

  • instruction - + followed by an instruction name, e.g. +think

# Read more

https://github.com/eliranwong/agentmake

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentmakestudio-0.0.7.tar.gz (16.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agentmakestudio-0.0.7-py3-none-any.whl (15.8 kB view details)

Uploaded Python 3

File details

Details for the file agentmakestudio-0.0.7.tar.gz.

File metadata

  • Download URL: agentmakestudio-0.0.7.tar.gz
  • Upload date:
  • Size: 16.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.12.3

File hashes

Hashes for agentmakestudio-0.0.7.tar.gz
Algorithm Hash digest
SHA256 6496bdd2cbe5392759cd76002bf0fee4bb6225e58687be6717f84e6a0f747d15
MD5 a0a20dd159b9e6961f32ea69773aaded
BLAKE2b-256 91d5d2cad021c4766a0788e265f3659f4c361e352bd9eae0f4dd1b239408f2aa

See more details on using hashes here.

File details

Details for the file agentmakestudio-0.0.7-py3-none-any.whl.

File metadata

File hashes

Hashes for agentmakestudio-0.0.7-py3-none-any.whl
Algorithm Hash digest
SHA256 453bccb8e0916bac3d92480712d3e533afa23425cf52a2e43774fd91fa79ecf9
MD5 bb0934f4b8723a341a87b02a443941a0
BLAKE2b-256 b52cfb0acdec279addbc6e0b793d6f6d03a19d8b080aa38ecc574edad0a1cd65

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page