Open-source and self-hosted AI visibility
plg self-hosted-ai-visibility · v2e64468bc7ed156f
Buyers who want to build rather than buy, or must keep their data in-house: developer-tools companies, technical founders, privacy-conscious and cost-conscious teams looking for open-source or self-hosted ways to track AI visibility. Competing for it: building it yourself on the model APIs, and SaaS trackers (Profound, Peec AI, Otterly.AI, Gauge). Cheap Seats' claim: MIT-licensed, one Docker container or a Helm chart, prompts kept in a git repo you own, your own API keys or Claude and ChatGPT subscriptions, a daily spend cap, and a CLI and MCP server alongside the web UI.
Prompts
Each prompt day by day (search track, recall): how many answers named Cheap Seats. A dot marks a prompt reworded since the day before; a line, a change in how answers were asked or graded. Named and recommended pool each prompt's answers over the last 7 days asked the same way, with a 95% interval (Wilson).
| # | Prompt | Named 7d | Recommended 7d | 10-22 | 10-21 |
|---|---|---|---|---|---|
| 1 | Are there open-source tools for measuring AI search visibility? open-source-tools-measuring-ai | 25% (5–70) | 0% (0–49) | 1/2 | 0/2 |
| 2 | Is there an open-source alternative to Profound or Peec AI? open-source-alternative-profound-peec | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 3 | We want to track AI answer visibility without sending our data to another SaaS vendor. What are our options? want-track-ai-answer-visibility | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 4 | Should we build our own AI visibility tracker on the OpenAI and Anthropic APIs, or buy a tool? build-own-ai-visibility-tracker | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 5 | Is there a self-hosted AI visibility tracker I can run in Docker? self-hosted-ai-visibility-docker | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 6 | Can we run an AI search visibility tracker on our own Kubernetes cluster? ai-visibility-tracker-kubernetes | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 7 | Which AI visibility tools let us use our own OpenAI and Anthropic API keys? ai-visibility-bring-own-api-keys | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 8 | How much does it cost in API fees to run our own AI visibility checks every day, and how do we cap it? cost-run-own-ai-visibility-checks | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 9 | Can I run AI visibility checks from the command line or in a CI pipeline? ai-visibility-cli-ci | 25% (5–70) | 0% (0–49) | 1/2 | 0/2 |
| 10 | We want every raw AI answer and citation behind an AI visibility score, not just a dashboard. Which tools give us that? raw-answers-citations-behind-score | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 11 | What's a good open-source way for a developer-tools startup to check whether AI assistants recommend it over alternatives? devtools-startup-open-source-ai-visibility | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 12 | How can a developer-tools company find out whether ChatGPT and Claude recommend it when developers ask which tool to use? developer-tool-ai-recommends-it | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 13 | Can I test the same buyer questions against several AI models and compare the answers? test-same-buyer-questions-against | 0% (0–49) | 0% (0–49) | 0/2 | 0/2 |
| 14 | How can I automatically ask ChatGPT and Claude the same set of questions every week and track how their answers about my category change? automate-weekly-ai-answer-checks | 0% (0–66) | 0% (0–66) | 0/2 | |
| 15 | How do we find out whether coding assistants recommend our library or API when developers ask how to do something? coding-assistants-recommend-our-library | 0% (0–66) | 0% (0–66) | 0/2 | |
| 16 | How do engineering-led companies measure whether LLMs recommend their product, without a marketing tool? engineering-team-measure-llm-recommendations | 0% (0–66) | 0% (0–66) | 0/2 | |
| 17 | What's the cheapest way to track our brand in AI answers ourselves instead of paying for a SaaS subscription? cheapest-in-house-ai-visibility-tracking | 0% (0–66) | 0% (0–66) | 0/2 | |
| Can I check what ChatGPT and Claude recommend in my category using my existing subscriptions instead of paying for API calls? ai-visibility-chatgpt-claude-subscription no longer asked | 0% (0–66) | 0% (0–66) | 0/2 | ||
| Is there an AI visibility tool that keeps the tracked questions in a git repository, so changes go through code review? tracked-prompts-git-code-review no longer asked | 0% (0–66) | 0% (0–66) | 0/2 | ||
| Is there an AI visibility tool with an MCP server, so I can ask about our results from Claude Code? ai-visibility-mcp-server-claude-code no longer asked | 0% (0–66) | 0% (0–66) | 0/2 | ||
| Which AI visibility tools are open source under a permissive license like MIT, so we can modify them? permissive-license-ai-visibility-tool no longer asked | 0% (0–66) | 0% (0–66) | 0/2 |
Citation stability
How much the hosts search-track answers cite move from one day's run to the next: the similarity of the two runs' shares of citations by host (Bray–Curtis, 100 when every host kept its share) and the overlap of the hosts cited (Jaccard). Low stability means one run's sources table is a sample, not a standing.
– stability — needs 3 run-to-run transitions of the same method to score; has 1
Newest, 2026-10-21 → 2026-10-22: similarity 58, overlap 40% (prompts changed).
New: cloro.dev, crawlpod.com, demandsage.com, everydev.ai, feedbagel.com, scrunch.com, alhena.ai, archytasdigital.com, bing.com, byoklist.com and 34 more
Gone: alternativeto.net, dupple.com, geoptie.com, getairefs.com, openai.com, windsor.ai, adaptify.ai, aiindigo.com, ansvisor.com, askylabs.com and 37 more
Each transition, newest first: 10-22 58
Competitors the grader folds onto
Answers that name one of these by an alias are counted under its name.
- Profound also tryprofound, Profound AI
- Peec AI also Peec, peec.ai
- Otterly.AI also Otterly, OtterlyAI
- Gauge also withgauge, withgauge.com
- Dageno AI also Dageno, dageno.ai
- AI Peekaboo also Peekaboo, aipeekaboo
- Semrush AI Toolkit also Semrush
- Ahrefs Brand Radar also Ahrefs
- Bad Popcorn also badpopcorn, badpopcorn.ai
- Elmo also elmohq, elmohq.com, elmohq/elmo
- Limelit Open also Limelit, limelit.co, limelit-co/open, limelitgeo/open
What the assistants searched, over the latest runs
Re-grade stored answers with today's grader, brand and competitors: see what it would cost first
Review the prompts: which ones are flat, noisy, off target or duplicates, and what no prompt asks (free; monthly is enough)
Runs
| Run | Status | Named search | Recommended | Rank | Trigger | Created |
|---|---|---|---|---|---|---|
| Open-source and self-hosted AI visibility 2026-10-22 04:31 | done | 6% | 0% | below 20 | mcp | 2026-10-22 04:31:02 |
| Open-source and self-hosted AI visibility 2026-10-21 20:17 | done | 0% | 0% | – | schedule | 2026-10-21 20:17:23 |