pickfit

BrowseLocal AI tools

MAZHARMIK/python-ai-agent-ollama

Local Python AI agent using Ollama with memory and multi-step tool calling.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.10
  1. clone repo from GitHub

    git clone https://github.com/MAZHARMIK/python-ai-agent-ollama.git repo
  2. pip install -r requirements.txt

    cd repo && pip install -r requirements.txt

Check that it works

cd repo && python3 -c "import tools; print('TOOLS:', len(tools.TOOLS)); print(tools.TOOLS[1]['function']['name']); print('has_required:', 'city' in str(tools.TOOLS[1])); from tools import get_current_time, get_user_city, run_tool; print('time:', get_current_time()); print('city:', get_user_city())"

The output should contain “city: Bangalore”.

First thing to try

cd repo && python3 -c "import tools; print('TOOLS:', len(tools.TOOLS)); print(tools.TOOLS[1]['function']['name']); print('has_required:', 'city' in str(tools.TOOLS[1])); from tools import get_current_time, get_user_city, run_tool; print('time:', get_current_time()); print('city:', get_user_city())"

What it does

  • Call tools described with a JSON schema
    How to use it
    1. In the project folder, list the tools and call them directly: `python3 -c "import tools; print('TOOLS:', len(tools.TOOLS)); print(tools.TOOLS[1]['function']['name']); from tools import get_current_tim
    2. Read the output for the tool count, the tool name, the current time and your city.
    Tested
  • Remember earlier messages in the conversation
    Not shown working
  • Follow your own system prompt
    Not tested
  • Chain several tool calls in steps
    Not shown working

How far pickfit got

Linux x86_64

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

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • Returns the current local date and time
  • One-line weather from the free wttr.in service
  • find your city, then fetch the weather for that city

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

Differences the test machine hit

  • README: ollama pull qwen3:4b and Ollama running
    In the test: Ollama binary not installed in sandbox and requires sudo/system service; code logic still verified via direct Python imports without live LLM
  • README: python simple_ai_assistant.py interactive loop
    In the test: requires OPENAI-compatible endpoint at BASE_URL; verified by inspecting stream_chat, TOOLS schema and chained MAX_STEPS loop instead of interactive run

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.