Skip to main content

Laura

Laura is a TUI workspace that provides your agent with an API over the TUI, allowing your agent to dynamically tile panes while you pair-program.

Laura demo

Your agent can open the file you're discussing, the plan you're following, the diff you just made, or tail logs of your running service. Laura supports every coding agent CLI and agents learn how to use the CLI through agent skills.

Laura lets you:

  • Stay in the flow - view a file, a plan, a diff, or a log right in the TUI, without switching windows between the terminal, IDE, and browser.
  • Compose the TUI - your agent tiles the workspace from your natural-language conversation through the laura CLI and skills — panes dwindle automatically, each open splitting off the newest.
  • Pick your coding agent CLI - Laura hosts a shell your agent runs inside without abstraction, so every CLI and model is compatible.
  • Interact in every pane - comment on any file pane and submit the inline review into the chat.
  • Learn while staying focused - your agent shows and explains concepts live, step by step.

How it works

Laura runs your agent CLI in a PTY and provides a set of agent skills you or your agent invoke. The skills instruct the agent on how to use the laura CLI, which drives the TUI over a small line-based protocol on a per-agent socket. See the protocol reference to learn more.

Quickstart

1. Install Laura. Requires Rust (stable); installs a laura binary:

cargo install laura-tui --locked   # Rust
uv tool install laura-tui          # uv/pip

Both drop a laura binary on PATH. Or from a clone: cargo build --release --locked → target/release/laura.

2. Install the skill so your agent knows how to drive laura. In Claude Code:

/plugin marketplace add thomaseleff/laura-tui
/plugin install laura@laura-tui

3. Start Laura and run the interactive demo:

laura -- claude "/laura:demo"

4. Pair-program. Chat as you normally would with your coding agent. Ask your agent to show you a file, a plan, or a diff using the /laura skill.

File panes reload when their file changes. Markdown renders with terminal styling; other files show their content with syntax colours, and lines changed since git HEAD are marked in the gutter.

Experimental features are opt-in: set the feature's variable before starting Laura. laura --help lists them, and laura ready tells your agent which ones are on in its tab. See the CLI reference.

Editor panes (experimental). Start Laura with LAURA_EXPERIMENTAL_EDITOR=1 and nvim on PATH (restart the terminal after installing Neovim), and laura open --edit <path> runs Neovim in a pane next to the chat. It doesn't take focus: press Ctrl+P and its id to edit. Ctrl+L flips the pane to its file view to comment and submit an inline review, and back to Neovim. On first start, Laura asks whether Neovim should use its theme, so the two views match. See the CLI reference.

See the tutorial for a first session and navigating the TUI for the keys. Reference lives in the CLI reference for the verb set, the protocol reference for the wire format, and the agent reference for the recipes your agent drives on your behalf.

License

MIT — see LICENSE.

Metadata

Release files for laura-tui 0.11.0

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

Built distributions (wheels)

Table of built distributions (wheels) for laura-tui 0.11.0
File
laura_tui-0.11.0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details
laura_tui-0.11.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl Python 3 none Linux glibc 2.17+ x86-64 Details
laura_tui-0.11.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl Python 3 none Linux glibc 2.17+ ARM64 Details
laura_tui-0.11.0-py3-none-macosx_11_0_arm64.whl Python 3 none macOS 11.0+ ARM64 Details
laura_tui-0.11.0-py3-none-macosx_10_12_x86_64.whl Python 3 none macOS 10.12+ x86-64 Details

Total release size: 7.7 MB

Release files / laura_tui-0.11.0-py3-none-win_amd64.whl

Download URL laura_tui-0.11.0-py3-none-win_amd64.whl
Size 1.5 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
b009dad361a12b33db64183905bf04949248372ba202da29d5bbd93ec26b782d
BLAKE2b-256 checksum
How to use checksums
35c03d2ba984ba9da8e650280e47ba6b6a6bcc6881ca7b8675ce64fe9e673293
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.

Transparency log

Release files / laura_tui-0.11.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL laura_tui-0.11.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size 1.7 MB
Tags Linux glibc 2.17+ x86-64 Python 3
SHA-256 checksum
How to use checksums
b557dcbbb79dbd3ff6fcbf8ef3279364441dfd26bf11a2e239bef1ba21687270
BLAKE2b-256 checksum
How to use checksums
f4775d80adf7368a56b6d7396a0d6a355ecb78b4dddcc2dd06ef1c620f0aa7f5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.

Transparency log

Release files / laura_tui-0.11.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

Download URL laura_tui-0.11.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Size 1.6 MB
Tags Linux glibc 2.17+ ARM64 Python 3
SHA-256 checksum
How to use checksums
88222cfe0b352aa24759f20077486524514a2f68b7e7e60044370f0b22993102
BLAKE2b-256 checksum
How to use checksums
375a5050a798fe35b0179055f9c59bd0dcde47a158d6dc7362562f3401b25a4c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.

Transparency log

Release files / laura_tui-0.11.0-py3-none-macosx_11_0_arm64.whl

Download URL laura_tui-0.11.0-py3-none-macosx_11_0_arm64.whl
Size 1.5 MB
Tags Python 3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
187305321509765f0d901d7470beadde09535e9cc956fc928233e81fac842d08
BLAKE2b-256 checksum
How to use checksums
04c2f6ec8aea9f535bc01a8861cfa424bfb355d00482578114b392da9f86328e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.

Transparency log

Release files / laura_tui-0.11.0-py3-none-macosx_10_12_x86_64.whl

Download URL laura_tui-0.11.0-py3-none-macosx_10_12_x86_64.whl
Size 1.5 MB
Tags Python 3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
6a51c8deae2bca903f448561f0d70623cdccb480f599ad6336cf83ccfc416f16
BLAKE2b-256 checksum
How to use checksums
3ab50a1668dd8e8de94609e30ae05d686b57a363a889177a2ebd1eee6261212e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.

Transparency log

Security for laura-tui 0.11.0

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.

Full provenance

All 5 files in this release have been uploaded with provenance metadata.

Select from 5 files

Attestation for laura_tui-0.11.0-py3-none-win_amd64.whl

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.

Transparency log

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.

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