SaSame
Services
Gold Rush
Gold RushRoadmap
Gold Rush →
ProofWhere We StandFor AI Agents
Contact
Services
Gold Rush
Gold RushRoadmap
ProofWhere We StandFor AI Agents
Contact
SaSame

A Romanian/EU micro-studio selling the picks, sieves and surveys of the agent-economy gold rush. No track record and no paying clients yet — under a 30-day public kill-test.

Ecosystem

  • Gold Rush
  • Roadmap
  • Services
  • Proof

Company

  • Where We Stand
  • For AI Agents
  • Contact
  • Privacy

For Machines

  • Public MCP
  • Agent Card
  • llms.txt
  • agent-proof.json

Contact

  • consulting@srl-sasame.com
  • Operator
    SaSame SRL · Romania (EU) · CUI 50731520
Where We Stand

© 2026 SaSame SRL. All rights reserved.

XFacebookInstagramTikTokThreadsTelegram

Proof · machine-verifiable, not testimonials

No client logos. No quotes. Just endpoints you can call yourself.

Most company “proof” pages are testimonials and case studies. We have none of those — no paying clients yet, so nothing to quote. Instead, every claim here links to a live endpoint an agent or a human can re-run, and every number is labelled verified or unverified. If a thing is not independently checkable, we say so on this page.

Living Gate
MEASURINGDay 0/30
external pulse: none yet · decision 2026-07-17
External AI Reach
102hits· 15 IPs
discovery / reach — NOT demand
Verified Services
0external· 3 total
external providers = 0; rest are SaSame's own
as of 2026-06-17 · source: funnel.json · market.json
VerifiableProof 01 · the live MCP control plane

A public MCP toolbelt you can connect and call right now.

SaSame runs a public Model Context Protocol endpoint over streamable-http. You do not have to take our word for what it does — POST a tools/list request and call the free preview tools yourself. Per our honesty rules we do not advertise a fixed tool number (the count is currently inconsistent across our own sources); the only number we trust is what the live server returns when you ask it.

Public MCP endpoint

https://live-vps.sasame.online/public-mcp

Transport: mcp-streamable-http. Free preview tools + x402-paid full deliverables.

Tool count: 127 tools as reported by the live server at 2026-06-17 22:03:40Z.

Open the endpoint →

Reproduce it (free)

curl -s -X POST \
  https://live-vps.sasame.online/public-mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tools/list","params":{}}'

The response lists the current tools. Free tools return real data with no key.

Why no fixed number? Across our own sources the count has read differently (live tools/list, our llms.txt, a prior internal audit). Until they reconcile, publishing any one figure would be a number that does not trace to a stable source — so we query it live and label the timestamp, or omit it.

Self-test (reproducible)Proof 02 · agent-proof.json liveness

The services actually run. Here is the live self-test.

agent-proof.json is a script that re-invokes the real services and records HTTP status, latency and returned content. It currently passes 5/5 checks (100%). Read this honestly:

self-test; independently reproducible by calling the endpoints — NOT third-party verified.This is SaSame's own script calling SaSame's own endpoints. It proves the services are live and functional — not that a third party audited them, and not that anyone is paying for them. It is reproducible: open the JSON, then call the same endpoints and compare.

Liveness checks

5 / 5

passed · 100%

operator: SaSame SRL (Romania, CUI 50731520)

OCR service

Free preview + x402 full text

Paid: 0.02 USDC (x402, base-sepolia)

Free preview endpoint →

Deep Research (paid)

x402 per-call deliverable

Price: 0.50 USDC (x402)

Paid research endpoint →

as of 2026-06-17 · source: agent-proof.json

VerifiableProof 03 + 04 · open source & the research library

The code is public; the free research tools return real data.

Public GitHub repository

github.com/shigeki7777/sasame-mcp

The MCP server source is public. You can read what the tools actually do rather than trust a description — the strongest form of “proof” for a developer or an agent evaluating a vendor.

Open the repository →

Public repo (HTTP 200). We do not claim stars, forks or downloads — go look.

Research library (free tools via MCP)

The public MCP exposes free preview research tools that return real data with no API key — verifiable by simply calling them:

  • ·web_research — web search preview
  • ·pubmed_lookup — biomedical literature preview
  • ·ecosystem_search — agent / MCP registry search
Call the MCP →

Tool names listed are returned by the live agent-proof.json self-test; the live tools/list is the authoritative set.

Our own measurement (sampled)Proof 05 · the Observatory dataset

We measured the gold rush. Most of it is fool's gold.

The Observatory samples public agent registries and publishes a machine-readable dataset. The evidence points one way: most listings register and never produce — “ghosts”. This is SaSame's own measurement, sampled — not a complete census, not a complete census, and the raw dataset is linked so you can check it.

Registries indexed

8,117

+ 27,359 (second registry)

reported totals across two registries

Mass-producer concentration

70% / 54%

from a single domain (orbisapi.com) in samples

a few producers dominate — the “ghost” signature

Cross-registry overlap

~1%

of the union appears in both

any single registry is a biased lens

Census — indexed vs verified

11,068 / 0

auto-indexed / verified members

auto-indexed from public registries, UNVERIFIED, NOT members; verified members = 0

Low overlap => the two registries see largely DIFFERENT slices of the market. A single source is a biased lens.

as of 2026-06-17 · source: observatory-multi-latest.json · as of 2026-06-17 · census.json

What this page does NOT prove

The honest edges of the proof. We will not let you misread it.

Reach is not demand

External AI reach is 102 crawler/registry hits from 15 distinct IPs (external AI crawler/registry hits — discovery / reach, NOT demand). That is discovery, not buying. External tool calls = 0, engagement = 0, paid = 0.

Self-test is not third-party verification

The 5/5 agent-proof result is self-test; independently reproducible by calling the endpoints — NOT third-party verified. It proves the services run; it does not prove an external party audited or paid for them.

Indexed is not membership

The Census shows 11,068 auto-indexed listings but 0 verified members. We do not count indexed listings as users, customers or members — and neither should you.

AI autonomously hiring an unknown vendor — UNPROVEN

Knowledge-ledger finding 0004 = REFUTED at present: there is no externally verifiable example (mid-2026) of an AI agent autonomously discovering and paying a no-track-record vendor via llms.txt / registry / x402. We surface proof of capability, not proof of demand — because the latter does not exist yet.

The whole bet is under a public kill-test: LIVING GATE verdict MEASURING, Day 0/30, decision 2026-07-17. A page full of capability proof with zero external pulse by then is a REFUTED_SHRINK, not a win. as of 2026-06-17 · source: funnel.json.

Don't trust the page. Call the endpoints.

Connect the MCPRead agent-proof.jsonWhere we actually stand →