# askround

AI visibility · CLI + MCP · Agent Workbench

People ask assistants which tool to use, and the makers never see the answer. askround asks OpenAI, Gemini, Anthropic and Perplexity the same question through their APIs, with web search, several times each, and reports how many runs named your product, at which position, the rivals beside it and what was claimed, each fact traced to its passage. Its MCP server lets a coding agent ask them itself.

- Platform: Python ≥3.11
- Licence: Apache-2.0
- Product site: https://alegauss.github.io/askround/
- Documentation: https://alegauss.github.io/askround/docs/
- Source: https://github.com/alegauss/askround

## Install

Claude Code:

```
/plugin marketplace add alegauss/askround
/plugin install askround@askround
```

From source:

```
git clone https://github.com/alegauss/askround.git
cd askround
pip install .
```

## What comes next

From docs/ROADMAP.md at b39ba6f.

Nothing is open on this product's roadmap right now.

## Recently shipped

- 2026-11-12 · AR43: The site is not built to be read by assistants, and askround never measures whether they name askround itself
- 2026-11-12 · AR42: There are no docs pages: install, a first session in Claude Code, the MCP tools and the CLI reference live nowhere
- 2026-11-12 · AR41: Nothing builds and deploys the site when it changes
- 2026-11-12 · AR40: askround has no public site: nowhere to see what a round reports, install it or read the docs
- 2026-11-12 · AR38: askround is not wired into a project the way roadkeep is: one install that every clone and every surface gets
- 2026-11-12 · AR37: Nothing measures how many tokens each MCP response costs the agent, so outputs grow unnoticed
- 2026-11-12 · AR36: An agent asking the same question again the same day pays for the same round twice
- 2026-11-12 · AR35: A round takes minutes of searched calls, longer than an MCP call should block the agent

All entries: https://alegauss.github.io/changelog/askround/
