KLayout + Python + MCP

klink

An AI-native control plane for KLayout. It turns a running KLayout GUI into a layout kernel driven by external Python, MCP clients, and AI agents — geometry-first: mark intent on geometry, let algorithms complete the wiring, and decide "done" with structured geometry and LVS, not a screenshot that "looks right". It is an early-stage, experimental open-source project — try it and send feedback.

Install Browse 190+ tools See the tutorials

Package: klayout-klink Python 3.10+ KLayout 0.30.x tested Apache-2.0 open source Alpha · early stage

More than a chat plugin

klink's core method is geometry-first: geometry comes first, you mark intent on it (Port for connectivity, Anchor for routing constraints), routing algorithms complete the wiring, and structured queries plus live LVS decide "done". The human keeps GUI freedom; the agent reads, writes, moves, records, routes, and verifies real geometry.

Concept

The geometry-first idea

Mark intent → algorithms route → structured verification. Ports/Anchors are the input to routing; the mechanism layer stays process-agnostic.

Read the core idea → Agent

MCP tool surface

klink-mcp exposes the same catalogue to Claude Code, Codex and others — 190+ tools across 15 domains, navigated by klink.find_tools.

See the MCP Reference → Verify

Structured verification

Routing, LVS, DRC and geometry queries return structured reports. "Done" is ok, overlap/hit counts, LVS match=True — never how a screenshot looks.

Verification habits →

A first result in 30 seconds

The public release ships examples that need no private GDS. Run an offline demo first, then connect a live KLayout. Full steps on Quickstart.

install & run

python -m pip install klayout-klink
klink init my-chip
cd my-chip
python example_template/nanodevice/ebl_wraparound.py

Install the Python package

The PyPI package brings the klink core + its two bundled Rust kernels; starter demos are copied into your project by klink init, and refreshed later with klink update — your own files are never touched.

Install the KLayout plugin

Copy klink_plugin/ into KLayout's salt dir and restart. The plugin runs 8765 RPC and the 8082 klive display.

Connect an agent

Run python -m klink.mcp, using a profile to select read/write/verify/escape or a specific domain.

The control path

A thin plugin hugs KLayout; the heavy intelligence runs in external Python. The two sides talk only over RPC. Detail on Architecture.

control path

Agent (Claude Code / Codex)
  → MCP server   (python -m klink.mcp)
  → klink client (NDJSON over TCP)
  → KLayout plugin (in-process RPC)
       RPC:            127.0.0.1:8765+
       klive-compat:   127.0.0.1:8082

Sessions are ports, equal peers

Each KLayout window binds a port (8765, 8766…) as a session. No port has a privileged role — you always say which one.

Process purity

klink holds no process constants. Layers, sizes and devices are passed in from your pdk.py; a missing fact returns an instructive error with a next_action.

Interaction capabilities for human + agent

A set of interaction capabilities that let a human and an agent collaborate on one live KLayout. Full detail on Workflows.

SEND selection memory

The toolbar SEND records a selection as a stable id (e.g. sel_0006) so an agent resolves "this area", "that one" — by order not age, journaled and never lost.

SEND memory →

L-Edit bridge, both ways

A load-as-source macro + file-exchange RPC: read selections/whole cells, exchange with KLayout, and work T-Cells in both directions (incl. writing back native parametric T-Cells) — accepted only byte-exact.

L-Edit Bridge →

One agent, many KLayouts

One MCP bridge drives many KLayout windows; label, resolve, and switch the target session.

Sessions →

Cross-session transfer

Two-phase and confirmation-safe: prepare + dry-run on the target, then commit — a wrong target is caught at dry-run.

Transfer →

8082 klive display

A drop-in klive replacement: any gdsfactory c.show() hard-coded to localhost:8082 pushes into KLayout unchanged, with a selectable target in multi-session mode.

klive compat →

Record → replay script

Record manual GUI edits and RPC edits into a replayable script, plus a standalone pya variant that runs inside KLayout with no klink.

Recorder →

Escape hatch

exec.python runs controlled pya for what typed RPCs don't cover yet; it still schedules the recorder and layout-diff detection.

Escape hatch →

Capabilities, by domain

klink is a general geometry-first control plane. Below are some current capabilities grouped by domain, each backed by a runnable example script (all with no private GDS). The project is still early and experimental, so coverage will keep changing. Per-example measured detail on Examples.

EBL nanodevice

EBL nanodevices

Electron-beam-lithography device generation: EBL wraparound, Hall bar, with writefield planning, patches and geometry validation. Offline EBL measures 40 electrodes / 0 violations / 0 overlaps.

See EBL / Hall bar → Neural electrode

Neural electrodes

Parametric neural-electrode probe: pad/via geometry → Ports → corridor anchors → tapered-hybrid routing, self-contained with no GDS. 4 rows: 48 ports / 24 nets / overlap 0.

See neural electrode → New materials

Material flake detection

Detect material flakes from a microscope image (needs cv2+numpy), or read a precomputed traces.json, commit them as polygons and derive contact Ports. Built on KlayoutClaw priors.

See nanodevice tools → Imaging

Cross-sections · 3D · SEM · Blender

One klink_visual_stack_v1 declaration plus your own .pyxs recipe yields process cross-sections and per-step films (with a z ruler), a 3D model with a self-contained offline web viewer, SEM-style top views, and paper-grade Blender renders. The starter is a four-transistor CMOS row and an eleven-step planar CMOS flow.

See the imaging tutorial → Silicon photonics

Silicon photonics

Take an ordinary gdsfactory MZI script into klink in one call; after a GUI drag, one photonics.reroute re-routes optics (incl. sbend / all_angle / dubins) and metal together.

See the gdsfactory MZI → Digital P&R

Custom-device digital P&R → LVS

Fit a device from synthetic exemplars, place, detailed-route, verify with live LVS. Measured routed 94/94, LVS match=True, 173 devices; the device-agnostic netlist flow is structdevice.*.

See the fit-device demo → Region · intent

Regions & executable layout intent

Circle an area and tile any existing cell into it with a unique number label per copy: region.claim claims + intent.prepare previews + intent.apply commits + intent.regenerate atomically swaps. Measured region 14000 µm², placed 31 (4 rejected), regenerate relabels the whole array to S201..S231.

See the layout intent tutorial →

190+ tools, 15 domains

Plugin RPCs + MCP local tools, each with function, parameters and examples (exact counts on the MCP Tool Reference). The catalogue is generated from the live plugin's method registry — no hand-maintained list that can drift.

Connection / view Sessions / transfer Geometry / cells Selection / SEND Ports / anchors Routing backends DRC / LVS Custom device Imaging Nanodevices Photonics L-Edit Bridge Escape hatch

Open the MCP Tool Reference

Documentation map

Not sure where to start? Pick a path by your goal.