pickfit

BrowseDeveloper CLIs

TokenTracker

Drop-in Python wrapper and CLI that logs LLM API calls to local SQLite and reports costs.

Tested on Linux

Use it

Linux x86_64

  1. install toktally via uv tool

    uv tool install toktally

Check that it works

tokentracker --help 2>&1

The output should contain “dashboard”.

First thing to try

cat > /tmp/tt_stub.py <<'PY'
import json
from http.server import BaseHTTPRequestHandler, HTTPServer
class H(BaseHTTPRequestHandler):
    def do_POST(self):
        n = int(self.headers.get('Content-Length', 0))
        body = self.rfile.read(n) if n else b''
        try:
            data = json.loads(body or b'{}')
        except Exception:
            data = {}
        model = data.get('model', 'gpt-4o-mini')
        resp = {"id":"chatcmpl-test","object":"chat.completion","created":1700000000,"model":model,"choices":[{"index":0,"message":{"role":"assistant","content":"Hello!"},"finish_reason":"stop"}],"usage":{"prompt_tokens":10,"completion_tokens":5,"total_tokens":15}}
        out = json.dumps(resp).encode()
        self.send_response(200)
        self.send_header('Content-Type','application/json')
        self.send_header('Content-Length',str(len(out)))
        self.end_headers()
        self.wfile.write(out)
    def log_message(self, *a): pass
HTTPServer(('127.0.0.1',8765), H).serve_forever()
PY
cat > /tmp/tt_track.py <<'PY'
from tokentracker import OpenAI, summary, recent
client = OpenAI(api_key="test-key", base_url="http://127.0.0.1:8765/v1")
r = client.chat.completions.create(model="gpt-4o-mini", messages=[{"role":"user","content":"Hello!"}])
print("REPLY:", r.choices[0].message.content)
s = summary(days=30)
print(f"TRACKED calls={s['total_calls']} cost={s['total_cost_usd']}")
for c in recent(limit=1):
    print(f"RECENT model={c['model']} tokens={c['total_tokens']} cost={c['cost_usd']}")
PY
echo stub-and-track-written
python3 /tmp/tt_stub.py
rm -f /tmp/tt_usage.db && TOKENTRACKER_DB=/tmp/tt_usage.db uv tool run --from toktally python /tmp/tt_track.py 2>&1

Run tokentracker dashboard to see your logged LLM spending.

What it does

  • Track LLM API costs automatically
    How to use it
    1. In your Python code, import the client from TokenTracker instead of the OpenAI package: from tokentracker import OpenAI.
    2. Make API calls as usual; each call is logged to a local SQLite database.
    3. Use summary(days=30) or recent(limit=1) from tokentracker to read back calls and costs.
    Tested
  • View spending in a command-line dashboard
    How to use it
    1. Run tokentracker dashboard to see API calls and costs.
    Tested
  • Set spending budgets and check them
    How to use it
    1. Set a budget with tokentracker budgets set monthly --limit <amount>.
    2. Run tokentracker budgets check to see spend against each budget.
    Tested

How far pickfit got

Linux x86_64

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

Good for

  • see LLM spending by model and day
  • enforce spending budgets in CI
  • project future spend from recent usage
  • find spend spikes and cheaper-model savings
  • compare cost of workload across other models

An alternative to AgentOps and LangSmith.

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 0.2.1

Differences the test machine hit

  • README: pip install toktally
    In the test: uv tool install toktally for isolated env
  • README: drop-in OpenAI client calling real API
    In the test: used local stub OpenAI server at 127.0.0.1:8765 and TOKENTRACKER_DB=/tmp/tt_usage.db so no API key or network needed

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.