Skip to main content
Gentui: generative UI for your terminal

A terminal interface for prototyping agents really quickly.
Point it at any AG-UI backend and get streaming chat, the model's chain of thought,
tables, charts and human approval, with no frontend to build.

CI Docs PyPI PyPI Downloads Python Textual AG-UI Tested with Strands Agents uv License: MIT Status PRs welcome Stars Last commit


Get started

pip install gentui                               # or: uv tool install gentui
gentui http://localhost:8000/agent               # your AG-UI endpoint
gentui --demo                                    # no backend yet? watch a tour of every feature

Requires Python 3.12 or newer.

No server needed for Strands or LangChain agents: run them inside Gentui in a few lines.

from gentui import GentUI

GentUI.from_strands(agent).run()      # pip install 'gentui[strands]'
GentUI.from_langchain(agent).run()    # pip install 'gentui[langchain]'

Documentation

Full docs, with search: rahrajlat.github.io/Gentui

I want to… Read
install it and try the demo Getting started
see every command-line flag Command-line reference
use slash commands, themes and the event inspector Commands
save a session and play it back Record and replay
run the same prompts every time Run a set of prompts
diff two runs side by side Compare runs
score runs with my own judge model Judges
change config, CSS and colours Customising
add widgets, commands or event hooks Plugins
build my own backend in any language Backend contract
talk to an agent on Amazon Bedrock AgentCore AgentCore Runtime
run a Strands agent in my own process, no server Native Strands agents
run a LangChain / LangGraph agent in my own process Native LangChain agents
open the UI in a web browser In the browser
understand the internals How it works

See it

Gentui feature tour: AgentCore launch, slash commands, chain of thought, memory, plan, approval, output, table, chart, event inspector, themes

Record and replay

Save any session to JSON, then play it back with pause, a seek bar and speed control. No agent, no network. Read more

Gentui replay: play, pause, rewind with the seek bar, open the chain of thought, charts and approvals drawn as they were live

Compare runs and judge them

Run the same prompts against two versions of your agent, diff the results side by side, and let a judge (Ollama built in, or your own function) score each prompt. Export it all, charts included, to one HTML page. Read more

Gentui compare mode: two runs side by side as a diff, a prompt picker, and a judge panel with a match score and comment for each prompt

Status

Gentui is alpha: tested with the Strands Agents framework over AG-UI and with AgentCore Runtime; other setups are untested. The details are in Development and status.

Support the project

If Gentui saves you time, please star the repo on GitHub ⭐. It helps other people find it, and it is the easiest way to say thanks.

Contributing

Issues and pull requests are welcome. Please run the tests (uv run pytest -q) before opening a PR, and add a test with any behaviour change. See Development and status.

License

MIT. Free to use, modify and distribute, including the example backend.

Metadata

Release files for gentui 0.1.9

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gentui 0.1.9
File Size Uploaded Provenance
gentui-0.1.9.tar.gz 74.7 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for gentui 0.1.9
File Interpreter ABI Platform
gentui-0.1.9-py3-none-any.whl Python 3 none any Details

Total release size: 168.0 kB

Release files / gentui-0.1.9.tar.gz

Download URL gentui-0.1.9.tar.gz
Size 74.7 kB
Tags Source
SHA-256 checksum
How to use checksums
307c96f72ffb453b72aaffc1e2a3415ba06ff94f0527c538edf13e0c448e1232
BLAKE2b-256 checksum
How to use checksums
2a692ee7576340dbe678ab7484418a59969351f1b90dcda65b724318fd48b69d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.22 {"installer":{"name":"uv","version":"0.12.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / gentui-0.1.9-py3-none-any.whl

Download URL gentui-0.1.9-py3-none-any.whl
Size 93.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cfb8f8a182eb167452679811efb0e67610475964e42466da18ec7bc1f1871d25
BLAKE2b-256 checksum
How to use checksums
e28e3567aeee85b5f4a9ddb8f2e5640f92f2de86a27b97cea927a174b28abdda
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.22 {"installer":{"name":"uv","version":"0.12.22","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for gentui 0.1.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page