Spelunking
Actively maintained
- Is it safe? We have not read the data policy of Spelunking yet. Read it on the official site before you upload anything.spelunking.ai ↗
- Is it free? We have not read the prices of Spelunking yet; they are next in our queue. Until then, the official site has them.spelunking.ai ↗
- What else does this? We have not measured alternatives for this one yet. If you know one, add it below.See ↓
not read yet
Use
- For
- Developers building AI agents that must handle decisions with genuine conflicts and no clear answer
- Activity
- Actively maintainedsite updated yesterday
- How it runs
- API
- Used for
- check an agent's reasoning against a published covenant
- obtain an offline-verifiable record of a deliberation
- escalate unresolved conflicts to a human reviewer
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantsspelunking.ai ↗
- MCP serverai.spelunking/hubverified in the MCP registry
- Stateanswers, 8 toolschecked 2026-10-23
- Address to connectspelunking.ai/mcp
- MCP docsspelunking.ai/.well-known/mcp.jsonthe vendor's page ↗
This card as JSON, for your agent →
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use Spelunking for?
Sign in to leave a noteWhat is Spelunking?
Returns the covenant directives bearing on a conflicted question, then checks an agent's written reasoning for missing steps and issues signed attestations.
Who is Spelunking for?
Developers building AI agents that must handle decisions with genuine conflicts and no clear answer
Do people use Spelunking?
Little sign of use.
Is Spelunking still maintained?
Actively maintained: site updated yesterday.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.