Touchstone
not read yet
Use
- For
- Teams and developers running AI agents who need tamper-evident records of what their agents did
- Used for
- Debug an agent after a crash by replaying its signed event log
- Prove an agent's actions in a dispute with a counterparty
- Give a regulator a verifiable audit trail of automated decisions
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantstouchstone.cv ↗
- MCP servercv.touchstone/touchstoneverified in the MCP registry
- Stateanswers, requires sign-inchecked 2026-10-26
- Address to connecttouchstone.cv/mcp
- OpenAPI spec15 pathsthe spec ↗
- API docstouchstone.cv/developersthe 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.
Figure and bar: visits/mo, estimate · year: online since
- #1
Lapu AI
Desktop agent that automates multi-step tasks across your apps without controlling your mouse or keyboard.
52ActiveFrom ≈ $22/mo2026 - #2
Seclai
Runs LLM agents as workflows that chain model calls, screen inputs and outputs, retry bad output, and log per-step traces and costs.
33ActiveFrom $15/mo - #3
AgentPMTMCP · sign-in
Builds agents and repeatable workflows that chain model calls with external tools, run on schedules, and log every tool call.
14ActiveFrom $0.01 per use - #4
AqtaMCP · open
Checks each AI agent action against your rules and a person's prior approval, then signs the allowed or refused decision as a verifiable record.
12ActiveContact sales2026 - #5
TandemMCP · open
Runtime that checks each agent action against data scope, tool policy and approval rules before it executes, and logs the decision.
5Active - #6
MaindexMCP · sign-in
Stores a shared memory graph that AI agents and teammates read and write via MCP or REST, with provenance on each fact.
4ActiveFrom $14.99/mo
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 Touchstone for?
Sign in to leave a noteWhat is Touchstone?
Records a signed, hash-chained, externally anchored log of an agent's actions so the record can be verified offline without trusting the vendor. It is listed in the Atlas under Agents.
Who is Touchstone for?
Teams and developers running AI agents who need tamper-evident records of what their agents did
Do people use Touchstone?
Little sign of use.
What are alternatives to Touchstone?
In Agents, by use: Lapu AI, Seclai, AgentPMT, Aqta, Tandem, Maindex.
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
Cookies
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.