results · five real systems

five agentic systems, shipped or shipping.

most early-stage ai studios cannot show a single shipped agentic system on their portfolio page. saulera ships with five — across personal ai, smb platforms, consumer commerce, native mobile, and public-sector mobility. each card states what was built, what it took, and where the public source lives.

honesty principle

cards are framed as built / shipping / in-use — not as paid client engagements. each links to its public source repo so a prospect can dig in. overclaiming dies in the discovery call; we'd rather catch it before then.

01
fredis — personal ai advisor & second brain.
shipping · in daily use
flagship · 24-skill agentic stack
source · private repo

what it is

a personal ai advisor with a 24-skill stack, persistent obsidian-vault memory, and slack / gmail / google workspace / hubspot / github integrations. operates in advisor mode — every output goes to a draft for human review, nothing auto-sends. built and running since early 2026.

agentic capabilities

  • 24-skill stack with role-based personas — invoked contextually per request.
  • advisor-mode safety boundary — drafts only, no send-authority on any external channel.
  • persistent vault memory auto-loaded at session start.
  • heartbeat / reflection / synthesis sdk loops for proactive scanning, memory consolidation, weekly synthesis.
  • hooks-based safety enforcement — pretooluse blockers and session snapshots.

stack

python claude agent sdk mcp / fastmcp tailscale serve https obsidian markdown vault hetzner vps scheduled cron (heartbeat / reflection / synthesis)
why it matters

the flagship proof. a working agentic advisor with persistent memory, integration breadth, and a non-trivial safety model — the exact shape of system saulera builds for clients. we don't pitch agentic systems. we run on one.

02
email innovation hub — centralised email platform with 9 ai agents.
built · ip cleared
9-agent platform · qa gates · rag
source · github.com/linardsb/merkle-email-hub

what it is

a centralised email development platform — build, preview, qa, and export production html emails from a single workspace. cms-agnostic, security-first, gdpr-compliant. designed for email teams of 5–50 developers across multiple esps. built on personal time and stack; ip cleared.

agentic capabilities

  • nine specialised ai agents — scaffolder (brief → maizzle html) · dark mode · content (subject lines / preheaders / ctas) · outlook fixer (mso + vml) · accessibility auditor (wcag aa) · personalisation (liquid / ampscript) · code reviewer · knowledge (rag q&a) · innovation.
  • ai orchestrator routes between claude and openai providers via configurable provider abstraction.
  • rag pipeline with pgvector embeddings and hybrid search.
  • websocket real-time chat wires the ai agents into the editor surface.
  • 10-point qa gate — html validation, css support, file size, link validation, spam score, dark mode, accessibility, fallback handling, image optimisation, brand compliance.
  • zero-trust api — jwt hs256, rbac (admin / developer / viewer), row-level security on postgres, aes-256 secret encryption, audit trails, brute-force lockout.

stack

fastapi (async) next.js 16 react 19 postgres + pgvector redis maizzle (node) tailwind / shadcn docker compose alembic vertical slice arch
why it matters

production-grade backend, modern frontend, and multi-agent orchestration in one coherent product. direct evidence saulera ships agentic platforms — not just point automations.

03
gerboni — ai-assisted e-commerce for latvian heraldry.
live · operating
commerce · pydantic ai · stripe
source · github.com/linardsb/GERBONI

what it is

an online shop selling t-shirts featuring the coats of arms (ģerboņi) of major latvian cities, with a 24/7 ai customer-support agent built into the storefront. cultural-heritage product on a modern ai-native commerce stack.

agentic capabilities

  • pydantic ai agent powered by claude sonnet 4 — handles product discovery, order assistance, customer queries 24/7.
  • ai-driven product recommendations based on browsing history.
  • admin analytics panel — sales, orders, products, users.

stack

next.js 16 react 19 typescript tailwind v4 (oklch) zustand radix ui fastapi sqlalchemy 2.0 postgres 16 stripe docker · k8s
why it matters

a small, complete, commerce-grade build with a real revenue surface, real payment integration, and embedded ai as a product feature. proof saulera can ship category-specific commerce tooling end-to-end — not just internal workflows.

04
ugoki — ai-coached health & wellbeing app, ios + android.
mvp shipped · investor re-engaged
native · ai coach · healthkit
source · github.com/linardsb/ugoki-iOS-Android-app

what it is

a mobile wellness app combining intermittent fasting, hiit workouts, and ai coaching for time-constrained professionals. a 15–20 minute daily routine for sustainable health optimisation. mvp shipped; 2026 re-engagement from walking ventures.

agentic capabilities

  • ai coach with constitutional ai guardrails, cross-session memory, and skill-based prompt routing.
  • bloodwork analysis — biomarker parsing from uploaded pdfs with trend tracking.
  • pubmed research hub with ai summaries relevant to user goals.
  • health-device sync — apple healthkit + google health connect.
  • gamification system wired into the ai's coaching context.

stack

python 3.12 fastapi sqlalchemy 2.0 pydantic 2.0 pydantic ai claude 3.5 sonnet / haiku expo sdk 52 react native tamagui zustand tanstack query fly.io postgresql cloudflare r2 expo push
why it matters

cross-platform native delivery (ios + android via expo), ai woven into product ux rather than bolted on, plus health-data integrations. evidence saulera ships mobile + ai together — a combination most generalist studios cannot.

05
vtv — unified cms & ai agent service for riga city-bus operations.
built · public push pending
civic · gtfs · bilingual lv / en
source · local repo (public push pending)

what it is

a fastapi + pydantic ai agent service paired with a next.js 16 / turborepo cms frontend for riga's municipal bus system. gtfs-compliant, swappable llm provider, bilingual (latvian + english), 4-role rbac. source repo to be made public before launch.

agentic capabilities

  • single pydantic ai agent with 9 tools — no routing logic, no orchestration overhead.
  • five read-only transit tools — advise, don't decide.
  • four obsidian-vault tools with dry-run previews.
  • swappable llm provider via single env var — anthropic, ollama, openai, groq, openrouter.
  • openai-compatible streaming chat endpoint.

stack

python 3.12 fastapi 0.120 pydantic ai sqlalchemy 2.0 async postgresql 18 alembic mypy + pyright (strict) ruff pytest uv next.js 16 react 19 tailwind v4 shadcn/ui auth.js v5 next-intl turborepo + pnpm 75 tests < 1.2s
why it matters

civic and mobility scale, regulated-sector requirements (gtfs, rbac, safety guardrails on tool execution), bilingual delivery — evidence saulera ships agentic systems for public-sector and regulated clients, not only commercial smbs.

seen one that looks like the system you'd want built?

30 minutes. one workflow. honest answer either way. the case study with your name on it gets written next.

book a build review