Skip to main content

Easily browse and resume previous conversations.

Project description

llm-convos

PyPI Changelog Tests License

A plugin for LLM that lets you browse, search, and resume past conversations interactively.

Installation

llm install llm-convos

Usage

llm convos

This opens an interactive list of your recent conversations. Use / to navigate, and q or Esc to quit.

From the picker you can:

  • Press Enter to resume the selected conversation
  • Press s to show the full conversation rendered as markdown in your terminal
  • Press w to write the conversation to a markdown file (prompts for a filename, pre-filled with the conversation ID)

Pass -c N/--context N to print the last N exchanges before resuming, so you have context for where you left off.

Show a conversation directly

llm convos show <conversation-id>

Renders the full conversation as markdown in your terminal. Pass -o/--output to write to a file instead:

llm convos show <conversation-id> -o transcript.md

Modes

Flag Behavior
(default) Interactive list, inline (doesn't take over the full screen)
-m preview Interactive list with a scrollable preview pane below
-m plain Non-interactive table, useful for scripting

Plain mode is used automatically when stdout is not a tty.

Searching

llm convos -s asyncio

Filters conversations to those containing the search term in any prompt or response. In interactive mode the matching excerpt is shown (with the term highlighted) instead of the first prompt.

Options

llm convos:

-n, --limit INTEGER      Max conversations to show (-1 for all) [default: 20]
-s, --search TEXT        Filter by prompt/response text
-m, --mode [interactive|preview|plain]
                         Display mode
-d, --database FILE      Path to log database (default: llm's logs.db)
-c, --context INTEGER    Exchanges to print before resuming [default: 0]

llm convos show <conversation-id>:

-o, --output FILE        Write markdown to this file instead of printing
-d, --database FILE      Path to log database (default: llm's logs.db)

Keyboard shortcuts

Key Action
/ Navigate the conversation list
Ctrl+↑ / Ctrl+↓ Jump to top / bottom of list
k / j Scroll the preview pane up/down
gg / G Jump to top / bottom of preview pane
/ Search / filter conversations (pre-filled with current search term)
Enter Resume selected conversation
s Show selected conversation as markdown in terminal
w Write selected conversation to a markdown file
q / Esc Quit

Custom database path

If you keep your LLM logs at a non-default path, pass it explicitly:

llm convos -d /path/to/logs.db

The LLM_USER_PATH environment variable is also respected automatically.

Development

git clone https://github.com/daturkel/llm-convos
cd llm-convos
uv run pytest

To run LLM with your in-development version of the plugin:

uv run llm convos

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

llm_convos-0.1.0.tar.gz (14.8 kB view details)

Uploaded Source

Built Distribution

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

llm_convos-0.1.0-py3-none-any.whl (12.2 kB view details)

Uploaded Python 3

File details

Details for the file llm_convos-0.1.0.tar.gz.

File metadata

  • Download URL: llm_convos-0.1.0.tar.gz
  • Upload date:
  • Size: 14.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for llm_convos-0.1.0.tar.gz
Algorithm Hash digest
SHA256 b586f5faf8b5d6c8bcd44bb1fcf7d47f2cd7d0459e8ab20b3981cc599d578bde
MD5 f48602ec8498df4e506fb74ad93175e0
BLAKE2b-256 5d91f523a7e9025c7e9ed64c0187fbf57c9a957cd07331fd5d48c72bf6f4d798

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_convos-0.1.0.tar.gz:

Publisher: publish.yml on daturkel/llm-convos

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file llm_convos-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: llm_convos-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 12.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for llm_convos-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 86f4bb95301458b3948ecf757a5129d98b015759f82003f64c38e11d433f133d
MD5 27417f5e4b726ed8b8f01d77f8b9ac0f
BLAKE2b-256 d08fa251c76f9ac3adbf2ddf9ab2ca50f2b95027302101091f03c62f2defe8e4

See more details on using hashes here.

Provenance

The following attestation bundles were made for llm_convos-0.1.0-py3-none-any.whl:

Publisher: publish.yml on daturkel/llm-convos

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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