Cirona launch — An AI workbench for analog IC engineers

An out-of-the-box
AI-native development platform for analog IC design — Cirona

Cirona Desktop is an AI workbench for analog circuit design that runs on your PC. Built for engineers who burn most of their day on testbenches, sizing iterations, and corner verification.

Runs locally Multi-LLM (incl. CN models) Pack repo GPL-3.0

After the recent surge of AI coding tools, the industry has applied general-purpose agents to chip design and published widely on the topic. Research labs have built domain-specific agents for chip design too. Important work — meaningful exploration toward bringing AI into chip work. But what engineers really care about is: when can we actually use any of this conveniently?

We're shipping something different: an out-of-the-box, AI-native development platform for analog circuit design — Cirona.

What Cirona is · What it solves

Cirona addresses these engineer pain points

Today
Cirona
EDA toolchain install and configuration is painful
One-stop integrated environment, simple setup
Bridging AI and the EDA toolchain is hard
Drop in an API key, start working
Tuning LLMs for circuit-design domain is high-effort
Built-in analog-aware orchestration
Design experience binds to people, hard to transfer
Design experience packs up
Commercial PDKs are off-limits to individuals
Ships with vpdk (note)
Codex / Claude Code are essentially code-domain agents
An agent built for the analog IC design domain
Frontier LLMs unreachable in air-gapped networks
Cirona supports multiple LLMs (incl. CN models), can run offline

Note: vpdk = virtual PDK. Across foundries, the key device parameters of each generation (Vth / μCox / Vsat) tend to be similar — only the exact numbers differ. Real PDKs cannot be redistributed for legal reasons. We provide vpdk as a generic reference. A circuit designed on vpdk maps to a real foundry process with the same topology, sizing approach, and bias strategy — only fine parameter tweaks needed.

How to use

One OTA, from spec to schematic

Step 1
One-line spec

Open Cirona. Type one SPEC line in the right-hand chat panel.

DC gain ≥ 70 dB, GBW 50 MHz, phase margin > 60°, load cap = 1 pF, power < 500 µW; process vpdk180nm, Vdd = 1.8 V
Cirona · Welcome
Cirona welcome screen
Cirona · Project tree
Cirona project folder tree
1 / 2
Step 2
AI derives topology and sizing

AI looks up the Pack knowledge base, traces from SPEC back to per-device W/L.

Cirona looks up the OTA design flow inside the Pack knowledge base. The AI picks a topology from the SPEC, back-solves gm from GBW, back-solves current from power, allocates headroom by transistor role, and so on — getting W/L from the table.

Every formula and reasoning step is grounded. The user can interrupt and adjust at any point.

Cirona · Architecture select (1/2)
AI topology selection 1
Cirona · Architecture select (2/2)
AI topology selection 2
Cirona · Device sizing
OTA sizing derivation
1 / 3
Step 3
Schematic output

The netlist is auto-written. Click the schematic toggle.

The netlist renders into a schematic automatically, so the engineer can review the actual circuit.

Cirona · FC-OTA schematic
FC-OTA schematic, auto-rendered
Step 4
Simulation

Once the engineer signs off the schematic, Cirona writes the testbench and runs simulation.

When simulation finishes, every device's gm, ID, Vds, Vov appears in a table — saturation status visible at a glance. Bode plots, transient waveforms, node voltages all show up where you expect them.

Cirona · AC result
AC simulation: per-device DC operating point and small-signal metrics
Cirona · DC simulation
DC simulation
Cirona · Bode plot
Bode plot: gain and phase
1 / 3
Step 5
Iterate / optimize

Sweeping 10 variables used to mean writing a wrapper and babysitting a batch run overnight.

Now one sentence:

Run an 80-trial optimization, maximize GBW, DC gain ≥ 70 dB, PM > 60°, 4-way concurrency.

Built-in Bayesian / CMA-ES / NSGA-II multi-objective optimizers. You see the achievable frontier of “gain vs power vs bandwidth” — not a single point.

Cirona · PVT corner sweep
Cirona PVT corner sweep
Step 6
Capture the experience

Just finished a Two-Stage Miller with zero-nulling resistor? Click Pack Creator.

This run's netlist, bias strategy, and the traps you hit get bundled into a Pack. Next time the same topology comes up, install your Pack and the AI delivers the design seamlessly.

Cirona executes ~80% of the work: sizing derivation, testbench writing, parameter optimization, data wrangling. But the key calls stay with the engineer: architecture direction, spec tradeoffs, what to verify. Every intermediate artifact surfaces in reviewable form: schematics, tables, Bode plots.

Cirona is the assistant that handles the tedious work. The engineer's thinking is still at the core.

Integrated demos

The current build ships with 4 demos

#
Circuit
Process
VDD
AI Provider
Result
01
PNP Brokaw Bandgap
vpdk180nm
1.8 V
Sonnet 4.6 / DeepSeek-v4-pro
✅ 5/5 PASScross-provider
02
Folded-Cascode OTA
vpdk180nm
1.8 V
Sonnet 4.6
✅ 5/5 PASS
03
2-stage Miller OTA
vpdk55nm
1.2 V
DeepSeek-v4-pro thinking
⚠️ 4/5 PASS + 1 marginal
04
PMOS-pass LDO
vpdk55nm IO Device
1.8 V → 1.2 V
Sonnet 4.6
✅ 11/11 PASS
Product feature

Packs — bottle the design experience

The greybeard analog wizard at your company — three decades of experience, head full of analog circuit know-how and traps, like: an architecture that breaks under a process change; LDO instability driven by output-current-dependent zero/pole shifts; a bandgap startup yield bug from a poorly designed startup circuit; the SDM-ADC capacitor-array mismatch fix.

None of it was ever written down. The day he retires, all of it walks out with him.

With Packs, an engineer's experience is preserved — permanently.

What is a Pack? Pack is short for knowledge package — a collection of circuit knowledge, design flow, and experience.

A Pack is organized as a directory. For example, the folded-cascode_ota Pack contains overview.md (what the topology is), design_flow.md (the design flow), reference_designs/ (reference netlists), failure_playbook.md (failure cases + diagnoses), lessons.yaml (historical lessons), skills/ (Pack-specific skills).

Cirona · Pack overview
Pack overview: directory structure and dependencies

A Pack is not a Skill

Skills are a hot concept in the AI space right now. A Skill is a prompt template describing how to do a class of work — generic, decoupled from industry and process. That paradigm fits general-purpose agents. It doesn't survive contact with analog IC.

Skill generic methodology template
Pack analog IC domain knowledge package
What it solves
Describes how to do a class of work
Loads the full design experience for one specific topology
Bound to
Not industry, process, or topology
Process, topology, corner behavior
Contents
System prompt fragments
Design flow + reference netlists + failure cases
Distribution
Inlined into the prompt
Like an npm package: declared deps, versioned, independently published
Who can contribute
Anyone who's written a generic prompt template
An analog engineer who has actually swept corners and hit traps on this topology

Cirona also supports analog-design Skill integration

The current build includes Analog Design Flow, Device Sizing, Netlist Review, SDAS (Spec-Driven Architecture Screening), and more — accessible from the Skill panel on the left of the UI. You can drop in your own Skills too.

Cirona · Skill panel
Skill plugin panel
Cirona · Device Sizing
Device Sizing Skill detail
1 / 2

How Packs are built

The simplest path: after finishing a design, type into the chat window — “Please bundle this design method and flow into a Pack.” Cirona walks you through the rest, dropping the Pack into your local working directory.

Open-source Pack community

One engineer ships a Pack for a new topology — every agent with that Pack installed gains a new capability. A thousand engineers each contributing one Pack — the agent gains a thousand capabilities.

This is what we care about most. The Pack repo is hosted on GitHub under GPL-3.0 — source fully open, derivative Packs stay open-source so the community keeps compounding. We hope it becomes an open-source community where everyone contributes Packs and AI's analog circuit design ability keeps growing.

We've already written the first batch of Packs (OTA family / LDO / Bandgap / Comparator). The next round of Pack library expansion is in progress — covering ADC / PLL / more OTA variants (class-AB, three-stage opamp, etc.). Contributions are welcome.

Product roadmap

Cirona product roadmap

  1. Now · Win-1.0

    Cirona Desktop (Windows)

    • 4 base analog circuit demos: OTA family (FC-OTA / Two-Stage) / LDO / Bandgap
    • 6-LLM-provider switching (Anthropic / DeepSeek / Gemini / GLM / Kimi / MiniMax)
    • Schematic display, simulation waveform display
    • Pack / Skill / Hook multi-source loading, contributable and distributable
    • Modern optimizers (Bayesian / CMA-ES / NSGA-II multi-objective Pareto frontier) + PVT corner sweep
    Current
  2. On the way · Linux-1.0

    Cirona Desktop (Linux)

    Linux environment + HSpice / Spectre simulators + Virtuoso integration.

    In progress
  3. On the way · Enterprise

    Cirona Enterprise

    On-prem LLM deployment, customized to enterprise requirements.

    Planned
How to download

Get Cirona

Runs locally. Bundled SPICE simulator, mainstream open-source PDKs included.

Windows desktop Current

v1.0.0-rc9.18 · 2026

  • Windows 10 / 11, x64
  • ≥ 8 GB RAM recommended
  • Bundled NgSpice / ACS simulator
  • Includes vpdk180nm / vpdk55nm reference processes
Linux desktop In progress

Linux-1.0

  • Ubuntu 22.04+ / Fedora 40+
  • HSpice / Spectre integration
  • Virtuoso bridge
GitHub Pack repo GPL-3.0

(TBD)

  • OTA family / LDO / Bandgap / Comparator at launch
  • Source fully open — read, modify, derive freely
  • Contributions welcome
About

NX-Si AI

Take AI in the analog IC vertical from “looks like it works” to “does it right, repeatedly.”