pickfit

BrowseLocal AI tools

ellmos BACH

Local-first text OS for LLM agents with SQLite memory, tools, scheduler and orchestration.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python 3.10+
  1. npm install -g ellmos-codecommander-mcp ellmos-filecommander-mcp

    npm install -g ellmos-codecommander-mcp ellmos-filecommander-mcp
  2. git clone https://github.com/ellmos-ai/bach.git /tmp/bach for python CLI

    git clone https://github.com/ellmos-ai/bach.git /tmp/bach
Where the README and reality differ
  • README: npm install -g ellmos-codecommander-mcp installs binary ellmos-codecommander-mcp
    What worked: binaries are installed as ellmos-codecommander and ellmos-filecommander in ~/.local/bin (symlinks to dist/index.js)

Check that it works

cd /tmp/bach && python bach.py --version 2>&1

The output should contain “BACH v3.15.0”.

First thing to try

cd /tmp/bach && python bach.py --startup 2>&1

From the cloned bach folder, run python bach.py --startup to start.

What it does

  • Manage tasks with priorities and deadlines
    How to use it
    1. Add a task with python bach.py task add "<your text>".
    2. List your tasks and their priorities with python bach.py task list.
    Tested
  • Work on its own, learn and organize itself
    Not shown working
  • Coordinate complex tasks using expert agents
    Not shown working
  • Automate scheduled jobs and workflows
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 1 of 4 features work
  4. Works offline

Good for

  • Manage tasks with prioritization, deadlines and tags
  • Store facts and lessons in structured SQLite memory
  • Run scheduler-driven automation jobs and workflows

An alternative to OpenClaw.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 3.15.0

Differences the test machine hit

  • README: pip install -e . installs BACH
    In the test: pip install fails without GitHub auth for private deps (assistant-core etc. git+https clone error 128); however python bach.py --version/startup/task/agent/scheduler work directly after git clone without pip install
  • README: ellmos-filecommander-mcp --help
    In the test: MCP servers are stdio JSON-RPC servers that block on start and print 'ellmos FileCommander MCP Server gestartet' instead of showing help

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.