Existing businessAI agents

Pomerado-style "any website becomes an agent…

2 weeks ago · Scored 27 Oct 2026 · ID HBV-261027-01

Working title: Pomerado-style "any website becomes an agent tool" service for Latin American portals (gov.br, Receita, bank and invoice portals, Correios) — working name "Portal MCP"

Summary

BriefingVerifiedSelf-reportedHypothesisEstimate

Existing business benchmark. Pomerado (YC F26) (https://www.pomerado.ai). Launch: Repo created 5 Oct 2026 (Verified, GitHub API); Launch YC post ~25–26 Oct 2026 ("1 day ago" on the YC Launch page read 27 Oct, Verified). Age: ~3 weeks (repo); public launch ~2 days (as of 27 Oct 2026).…

Read the rest

Verified: GitHub 1,033 stars (API) / 1.0k (page), +199 on 25 Oct and +683 on 26 Oct (OSS Insight); YC Fall 2026 company page, team of 2; public pricing Free $0 (100 tool calls/day), Premium $50/month (1,000 calls/day), Business custom (pomerado.ai). Not found: revenue, paying-customer count, user count. Claims "2–4x faster, 10–1000x cheaper, +30% more reliable than browser use" are Self-reported. Passes: benchmark Pomerado (YC Fall 2026) is 22 days old with 1,033 GitHub stars, accelerating (+683 on 26 Oct, the peak and last full day; Verified), public paid plan $50/month (Verified, pomerado.ai pricing page), X 439 posts/7d rising from 3–4/day to 284 on 26 Oct (Verified). Weaknesses: the launch spike is only 2 days old (no proof it holds); no public revenue or user count (only stars and a price list); the space is crowded (Browser Use, Browserbase, Apify, Firecrawl, Composio, and Pomerado itself is free and open source under MIT); acting on logged-in LatAm portals (gov.br, banks, tax and invoice portals) needs custody of user credentials and 2FA, which clashes with the HBV rule of no security promises and with LGPD and site terms of use; POS 57. Stars: Total: 1.0k (github.com page text, public HTML read with curl 27 Oct 2026 ~07:03 BRT; the box browser was not used); gh API cross-check 1,033 at 07:02 BRT. Created 2026-10-05 (API only), MIT (page). 24h (26 Oct, last full UTC day): +683. 7d (20–26 Oct): +886 ≈127/day; prior 7d (13–19 Oct): +28; 7v7 = +3,064% (accelerating). 3v3 (24–26 Oct 884 vs 21–23 Oct 2) = accelerating. Since creation: 1,033 in 22 days ≈47/day, but 85% of all stars arrived on 25–26 Oct (YC launch). Peak day 26 Oct (+683, last full day) → not past peak. Daily series (OSS Insight analyze-recent-stars, fetched 27 Oct 06:57 BRT): 20 Oct 0 · 21 Oct 0 · 22 Oct 1 · 23 Oct 1 · 24 Oct 2 · 25 Oct 199 · 26 Oct 683 · 27 Oct partial 118. Not on github.com/trending daily or weekly at 06:58 BRT. All star numbers Verified (page text + API/OSS Insight); nothing estimated. X: 439 posts/7d (Rising +6100% 3v3 (24–26 Oct 372 vs 21–23 Oct 6; daily full UTC days 4, 2, 0, 3, 85, 284); peak 26 Oct 284; 26 Oct is 0% below peak; window 2026-10-20 10:30 UTC → 2026-10-27 09:50 UTC (X API recent counts, granularity day, pulled 27 Oct 2026 ~07:00 BRT; Mon 20 and Tue 27 are partial UTC days; full days Wed 21 → Mon 26; 3v3 = (24+25+26) vs (21+22+23); 24–25 Oct are a weekend)). Revenue hypothesis: ~$1K–$6K/month at month 6 (HYPOTHESIS).

DescriptionHypothesisModel

Turn Latin American websites that have no API (government, tax, banking, invoice and delivery portals) into ready-made tools that ChatGPT, Claude or any agent can call — a Pomerado copy aimed at LatAm portals. What the benchmark does: Pomerado builds a hosted API or MCP (Model Context Protocol, the standard way agents …

Read the rest

call tools) for any website from a single prompt, hosts it, stores logins with automatic 2FA and repairs the integration when the site changes (YC Launch page and pomerado.ai, read 27 Oct 2026). Why replicable: The core harness is MIT-licensed, so the build is a localisation and hosting job; the hard parts are keeping portal integrations alive and handling user logins safely. Monetization: Usage-based subscription: free tier, then per-tool-call plans in BRL/MXN; paid "portal packs" (tax, invoices, delivery) for accountants (Hypothesis; no approved price). Build: ~3–4 agent-weeks on top of the MIT harness, plus ongoing upkeep of each portal integration; stack: Pomerado MIT core (TypeScript) on Vercel/Fly; Postgres; Stripe + Pix; MCP server. GTM: SEO/GEO pages per portal ("MCP do e-CAC", "agente que emite nota fiscal"), listings in MCP directories, accountant communities.

Target customer

Personal-assistant users, accountants, small-business owners and agent builders in Brazil and Mexico who need agents to act on portals with no API (gov.br, e-CAC, NF-e/NFS-e portals, Correios, SAT in Mexico).

Pain

The core harness is MIT-licensed, so the build is a localisation and hosting job; the hard parts are keeping portal integrations alive and handling user logins safely.

Why this score

Why it scored lower: Credential custody and portal terms of use (security and LGPD exposure) in a crowded field where the benchmark itself is free and open source.

MoatHypothesis

Weak to moderate: A maintained library of LatAm portal tools (Portuguese/Spanish, local 2FA and certificates) is tedious work US players skip. Accountant community and SEO pages per portal. Status: Hypothesis.

Demand signals

X posts (7 days)

439

Signal trend

Rising +6100% 3v3 (24–26 Oct 372 vs 21–23 Oct 6; daily full UTC days 4, 2, 0, 3, 85, 284); peak 26 Oct 284; 26 Oct is 0% below peak

Web demandVerified

Launch YC page (ycombinator.com/launches/WSd-pomerado…), YC company page and pomerado.ai pricing read 27 Oct 2026 via web search (Verified page content); GitHub trending daily/weekly checked 06:58 BRT: not listed.

Market and competitors

TAM

Not sized this run — Scope: Global. Method: No third-party report fetched. (Basis: n/a)

SAMHypothesis

Not sized — Scope: Target markets above. Method: HBV assumption. (Basis: Hypothesis)

SOMHypothesis

~$12K–$72K ARR (Hypothesis) — Scope: Month-6 run-rate. Method: From revenue hypothesis ×12. (Basis: Hypothesis)

Competitors

Pomerado itself (free open-source core, $50/month hosted), Browser Use, Browserbase, Apify actors, Firecrawl, Composio, Kadoa, Browse AI; in Brazil, RPA vendors and API resellers for CNPJ/NF-e data (e.g. sheet row HBV-261022-H10 "Brazil Data for Agents", which covers public data, not logged-in portals).

Existing business

https://www.pomerado.ai

Business model

MonetizationHypothesis

Usage-based subscription: free tier, then per-tool-call plans in BRL/MXN; paid "portal packs" (tax, invoices, delivery) for accountants (Hypothesis; no approved price).

Revenue hypothesis (monthly)Hypothesis

~$1K–$6K/month at month 6 (HYPOTHESIS).

Traction and revenueVerifiedSelf-reported

Launch: Repo created 5 Oct 2026 (Verified, GitHub API); Launch YC post ~25–26 Oct 2026 ("1 day ago" on the YC Launch page read 27 Oct, Verified). Age: ~3 weeks (repo); public launch ~2 days (as of 27 Oct 2026). Verified: GitHub 1,033 stars (API) / 1.0k (page), +199 on 25 Oct and +683 on 26 Oct (OSS Insight); YC Fall 20…

Read the rest

26 company page, team of 2; public pricing Free $0 (100 tool calls/day), Premium $50/month (1,000 calls/day), Business custom (pomerado.ai). Not found: revenue, paying-customer count, user count. Claims "2–4x faster, 10–1000x cheaper, +30% more reliable than browser use" are Self-reported.

Jobs to be done

When I have to pull the same documents from government portals for 60 clients every month, I want to ask my AI assistant to do it on each portal for me, so I can close the month in hours instead of days.

HXC

Renata, 38, accountant in Belo Horizonte with 60 small-business clients (illustrative) · Spends hours a week on e-CAC, NFS-e and Simples Nacional portals; already uses ChatGPT. Buying signal: Pays for accounting software and RPA add-ons today.

Build and go-to-market

Tech stack

Pomerado MIT core (TypeScript) on Vercel/Fly; Postgres; Stripe + Pix; MCP server

GTM channels

SEO/GEO pages per portal ("MCP do e-CAC", "agente que emite nota fiscal"), listings in MCP directories, accountant communities

Risks

Main risk

Credential custody and portal terms of use (security and LGPD exposure) in a crowded field where the benchmark itself is free and open source.

All risksVerified

Value: Supported — 1,033 stars, +683 on 26 Oct; $50/month public price (Verified) | Usability: Attention — Users must hand over portal logins | Feasibility: High — Portals change and add captchas | Business Viability: High — LGPD, credential custody, terms of use

Next validation step

Do not build now. Re-check Pomerado stars and X on 3 Nov 2026 (does the spike hold?); look for any public paying-customer number; ask 5 Brazilian accountants whether they would let an agent log into e-CAC for them.

Sources

github.com
ycombinator.com
ycombinator.com
pomerado.ai
docs.pomerado.ai
OSS Insight analyze-recent-stars
X API counts (window above)

existingcopycatagent-servicesgithubmcplatambrazilmexicoglobal

Want the next one the day it is scored?

The score, the sources, the risks and the next step, by email.

ProductBots.ai

Like this idea? Turn it into a plan with ProductBots.ai.

ProductBots.ai is an Agentic Product OS: agents that do the product work with you, from discovery to plan. Download the briefing for this idea and use it as the starting point.

Open ProductBots.ai

Preview the briefing

# Briefing: Pomerado-style "any website becomes an agent tool" service for Latin American portals (gov.br, Receita, bank and invoice portals, Correios) — working name "Portal MCP"

Source: Startup Ideas HQ (HB Ventures), found 2026-10-27. ProductBots Opportunity Score: 57/100, evidence confidence 51%.
Evidence labels (Verified, Self-reported, Hypothesis) are kept as written by the researcher.

## Goal for ProductBots.ai
Turn this idea into a validated MVP plan and a first build. Start from the next validation step; do not assume unlabelled numbers are verified.

## What it is
Turn Latin American websites that have no API (government, tax, banking, invoice and delivery portals) into ready-made tools that ChatGPT, Claude or any agent can call — a Pomerado copy aimed at LatAm portals.

Existing business benchmark. Pomerado (YC F26) (https://www.pomerado.ai). Launch: Repo created 5 Oct 2026 (Verified, GitHub API); Launch YC post ~25–26 Oct 2026 ("1 day ago" on the YC Launch page read 27 Oct, Verified). Age: ~3 weeks (repo); public launch ~2 days (as of 27 Oct 2026). Verified: GitHub 1,033 stars (API) / 1.0k (page), +199 on 25 Oct and +683 on 26 Oct (OSS Insight); YC Fall 2026 company page, team of 2; public pricing Free $0 (100 tool calls/day), Premium $50/month (1,000 calls/day), Business custom (pomerado.ai). Not found: revenue, paying-customer count, user count. Claims "2–4x faster, 10–1000x cheaper, +30% more reliable than browser use" are Self-reported. Passes: benchmark Pomerado (YC Fall 2026) is 22 days old with 1,033 GitHub stars, accelerating (+683 on 26 Oct, the peak and last full day; Verified), public paid plan $50/month (Verified, pomerado.ai pricing page), X 439 posts/7d rising from 3–4/day to 284 on 26 Oct (Verified). Weaknesses: the launch spike is only 2 days old (no proof it holds); no public revenue or user count (only stars and a price list); the space is crowded (Browser Use, Browserbase, Apify, Firecrawl, Composio, and Pomerado itself is free and open source under MIT); acting on logged-in LatAm portals (gov.br, banks, tax and invoice portals) needs custody of user credentials and 2FA, which clashes with the HBV rule of no security promises and with LGPD and site terms of use; POS 57. Stars: Total: 1.0k (github.com page text, public HTML read with curl 27 Oct 2026 ~07:03 BRT; the box browser was not used); gh API cross-check 1,033 at 07:02 BRT. Created 2026-10-05 (API only), MIT (page). 24h (26 Oct, last full UTC day): +683. 7d (20–26 Oct): +886 ≈127/day; prior 7d (13–19 Oct): +28; 7v7 = +3,064% (accelerating). 3v3 (24–26 Oct 884 vs 21–23 Oct 2) = accelerating. Since creation: 1,033 in 22 days ≈47/day, but 85% of all stars arrived on 25–26 Oct (YC launch). Peak day 26 Oct (+683, last full day) → not past peak. Daily series (OSS Insight analyze-recent-stars, fetched 27 Oct 06:57 BRT): 20 Oct 0 · 21 Oct 0 · 22 Oct 1 · 23 Oct 1 · 24 Oct 2 · 25 Oct 199 · 26 Oct 683 · 27 Oct partial 118. Not on github.com/trending daily or weekly at 06:58 BRT. All star numbers Verified (page text + API/OSS Insight); nothing estimated. X: 439 posts/7d (Rising +6100% 3v3 (24–26 Oct 372 vs 21–23 Oct 6; daily full UTC days 4, 2, 0, 3, 85, 284); peak 26 Oct 284; 26 Oct is 0% below peak; window 2026-10-20 10:30 UTC → 2026-10-27 09:50 UTC (X API recent counts, granularity day, pulled 27 Oct 2026 ~07:00 BRT; Mon 20 and Tue 27 are partial UTC days; full days Wed 21 → Mon 26; 3v3 = (24+25+26) vs (21+22+23); 24–25 Oct are a weekend)). Revenue hypothesis: ~$1K–$6K/month at month 6 (HYPOTHESIS).

## Customer and pain
Target customer: Personal-assistant users, accountants, small-business owners and agent builders in Brazil and Mexico who need agents to act on portals with no API (gov.br, e-CAC, NF-e/NFS-e portals, Correios, SAT in Mexico).
Pain: The core harness is MIT-licensed, so the build is a localisation and hosting job; the hard parts are keeping portal integrations alive and handling user logins safely.

## Market and competitors
TAM: Not sized this run — Scope: Global. Method: No third-party report fetched. (Basis: n/a)
SAM: Not sized — Scope: Target markets above. Method: HBV assumption. (Basis: Hypothesis)
SOM: ~$12K–$72K ARR (Hypothesis) — Scope: Month-6 run-rate. Method: From revenue hypothesis ×12. (Basis: Hypothesis)
Competitors: Pomerado itself (free open-source core, $50/month hosted), Browser Use, Browserbase, Apify actors, Firecrawl, Composio, Kadoa, Browse AI; in Brazil, RPA vendors and API resellers for CNPJ/NF-e data (e.g. sheet row HBV-261022-H10 "Brazil Data for Agents", which covers public data, not logged-in portals).
Geography: Brazil and Mexico first; any country with API-less government portals (global version)

## Business model
Monetization: Usage-based subscription: free tier, then per-tool-call plans in BRL/MXN; paid "portal packs" (tax, invoices, delivery) for accountants (Hypothesis; no approved price).
Revenue hypothesis (monthly): ~$1K–$6K/month at month 6 (HYPOTHESIS).

## Build and go-to-market
Build effort (agent-weeks): ~3–4 agent-weeks on top of the MIT harness, plus ongoing upkeep of each portal integration
Time to first revenue: ~6–10 weeks
Tech stack: Pomerado MIT core (TypeScript) on Vercel/Fly; Postgres; Stripe + Pix; MCP server
GTM channels: SEO/GEO pages per portal ("MCP do e-CAC", "agente que emite nota fiscal"), listings in MCP directories, accountant communities

## Risks and next step
Main risk: Credential custody and portal terms of use (security and LGPD exposure) in a crowded field where the benchmark itself is free and open source.
Next validation action: Do not build now. Re-check Pomerado stars and X on 3 Nov 2026 (does the spike hold?); look for any public paying-customer number; ask 5 Brazilian accountants whether they would let an agent log into e-CAC for them.

## Sources
https://github.com/Pomerado/pomerado; https://www.ycombinator.com/launches/WSd-pomerado-the-faster-cheaper-and-more-reliable-alternative-to-browser-use; https://www.ycombinator.com/companies/pomerado; https://pomerado.ai/; https://docs.pomerado.ai/quickstart/try-without-a-key; OSS Insight analyze-recent-stars; X API counts (window above)

Research, not investment advice. Numbers keep the label they were published with.

Summary

Briefing✓Verified◐Self-reported○Hypothesis≈Estimate

Description○Hypothesis≈Model

Target customer

Pain

Why this score

Moat○Hypothesis

Demand signals

X posts (7 days)

Signal trend

Web demand✓Verified

Market and competitors

TAM

SAM○Hypothesis

SOM○Hypothesis

Competitors

Existing business

Business model

Monetization○Hypothesis

Revenue hypothesis (monthly)○Hypothesis

Traction and revenue✓Verified◐Self-reported

Jobs to be done

HXC

Build and go-to-market

Tech stack

GTM channels

Risks

All risks✓Verified

Next validation step

Sources

BriefingVerifiedSelf-reportedHypothesisEstimate

DescriptionHypothesisModel

MoatHypothesis

Web demandVerified

SAMHypothesis

SOMHypothesis

MonetizationHypothesis

Revenue hypothesis (monthly)Hypothesis

Traction and revenueVerifiedSelf-reported

All risksVerified