pickfit

BrowseDeveloper CLIs

AgentChanti

Multi-agent coding assistant that plans, writes, reviews and tests code via local or cloud LLMs.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.10
  • System packages: Git
  • Keys or accounts: cloud API key
  1. Install agentchanti via uv tool

    uv tool install agentchanti
Where the README and reality differ
  • README: kb commands listed as `agentchanti kb embed` / `agentchanti kb search "query"` with no `kb index` step mentioned
    What worked: run `agentchanti kb index` in the project directory before `kb embed`/`kb search`; search must also run from the indexed project directory (index is CWD-scoped)

Check that it works

agentchanti --help 2>&1

The output should contain “AgentChanti — Multi-Agent Local Coder”.

First thing to try

mkdir -p ragdemo && cat > ragdemo/calc.py <<'EOF'
def add(a, b):
    """Add two numbers."""
    return a + b

class Calculator:
    """Simple calculator."""

    def multiply(self, a, b):
        """Multiply two numbers."""
        return a * b
EOF
echo created && ls ragdemo
cd ragdemo && agentchanti kb index 2>&1
cd ragdemo && agentchanti kb search "multiply numbers" 2>&1

In your project folder, run agentchanti kb index to index the code, then use agentchanti kb search to query it.

What it does

  • Find relevant code in your project with built-in RAG
    How to use it
    1. Go to your project folder and run agentchanti kb index to index the code.
    2. Run agentchanti kb search "<your query>" to list matching functions, classes and methods.
    Tested
  • Build software from a plain English task
    Not tested
  • Plan, write, review and test coding tasks
    Not tested
  • Generate and run unit tests to check code
    Not tested

How far pickfit got

Linux x86_64

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

Good for

  • build software from a plain English task description
  • generate and run unit tests to verify code
  • break a coding task into actionable steps

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 30 Oct 2026
  • Version 0.13.0

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.