pickfit

BrowseLocal AI tools

Contemplative Agent

Local-LLM agent that posts autonomously and proposes revisions to its prompt harness for human approval.

Tested on macOS and Linux

Use it

macOS arm64

You need first

  • Runtimes: Python 3.11+
  • At least 16 GB of RAM
  • Needs the network
  • Keys or accounts: Moltbook API key
  1. git clone contemplative-agent repo

    git clone https://github.com/shimo4228/contemplative-agent.git /tmp/ca-verify
  2. uv pip install -e . editable install

    cd /tmp/ca-verify && uv venv .venv && uv pip install -e .

Check that it works

/tmp/ca-verify/.venv/bin/contemplative-agent --version

The output should contain “contemplative-agent 2.14.0”.

First thing to try

MOLTBOOK_HOME=/tmp/ca-test-verify /tmp/ca-verify/.venv/bin/contemplative-agent init

Run contemplative-agent init first to set up the agent's home folder.

Linux x86_64

You need first

  • Runtimes: Python 3.11+
  • At least 16 GB of RAM
  • Needs the network
  • Keys or accounts: Moltbook API key
  1. Clone repository checkout

    rm -rf /tmp/ca-src && git clone --depth 1 https://github.com/shimo4228/contemplative-agent.git /tmp/ca-src
  2. Editable pip install from checkout

    cd /tmp/ca-src && pip install -e . --break-system-packages
Where the README and reality differ
  • README: uv pip install -e . (assumes current dir is the clone)
    What worked: git clone https://github.com/shimo4228/contemplative-agent.git first (to /tmp/ca-src), then run pip install -e . inside the checkout

Check that it works

contemplative-agent --help

The output should contain “dialogue”.

First thing to try

MOLTBOOK_HOME=/tmp/ca-a contemplative-agent init

Run contemplative-agent init first to set up the agent's home folder.

What it does

  • Post on Moltbook on its own using a local LLM
    Not tested
  • Propose changes to its constitution, identity and skills
    Not tested
  • Turn the episode log into patterns
    Not tested

How far pickfit got

macOS arm64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

Linux x86_64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Works offline

Good for

  • post and reply on Moltbook using a local LLM
  • propose changes to constitution, identity and skills
  • run two agents with different constitutions talking through local pipes

How pickfit tested it

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

macOS arm64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 2.14.0

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 2.13.0

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.