# anthropics/commerce-agents

> Reference blueprint for building shopping and merchant agents on Claude: a customer-facing shopping agent and a back-office merchant agent, with runnable examples in retail, travel, telecom, and entertainment.

- Magnitude: 1.6 out of 10 — Steady
- Stars: 3,208 total · Not enough measurements today
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-09-01 · Last push: 2026-10-02
- GitHub: https://github.com/anthropics/commerce-agents · Homepage: https://claude.com/solutions/commerce · Page: https://gitnova.dev/en/r/anthropics/commerce-agents

## Useful for

- Run the retail demo and open the storefront on localhost:3000 to test the shopping agent
- Scaffold your own agent with /scaffold-commerce-agent against your stack
- Run the merchant agent and approve each staged change via the y/N console

## Why it’s here

- There are not enough fresh counter measurements for today's UTC day. The gain is unknown.
- The repository is 40 days old and already has 3,208 stars.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 629
- Issues and pull requests: 37
- Watchers: 21
- Average over the last week: 10 per day
- Usual pace: 26 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 12, 10, 14, 7, 10, 14, 8, 4, 14, 8, 10, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-28 2.3, 09-29 2.2, 09-30 2.1, 10-01 1.8, 10-02 1.6, 10-03 1.6, 10-04 1.4, 10-05 1.7, 10-06 1.7, 10-07 1.4, 10-08 1.3, 10-09 1.8, 10-10 1.7, 10-11 1.6

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-11 00:07 UTC, updated every 30 minutes.