SilicAI
Copyright 2026 mageo services Ltd — Licensed under the PolyForm Noncommercial License 1.0.0. Commercial use requires a separate license.
Structured electronic component descriptions for AI-assisted circuit design.
Concept
Electronic component information lives in PDF datasheets — unstructured, hard for AI to consume. SilicAI defines a YAML schema that captures everything needed to design circuits correctly:
- Pin directions and functions (primary + all alternate functions)
- Power rails with per-pin and bulk decoupling requirements
- Required external components (filters, pull-ups, decoupling)
- Standard net definitions and electrical characteristics
The goal is to give AI tools the structured context they need to generate correct, production-ready schematics.
Structure
src/silicai/
validate.py Schema validation CLI
generate.py KiCad schematic generator
mcp_server.py MCP server for Claude Code integration
schema/ JSON Schema definitions
component.schema.json
circuit.schema.json
project.schema.json
defs/ Shared schema definitions
components/ Built-in component library (silicai-components submodule)
nets/ Standard net definitions (GND, VCC_3V3, ...)
tests/ Test suite
The component library is bundled as a git submodule (mageoch/silicai-components) and loaded automatically — no extra configuration needed. Additional component libraries can be declared in a project's pyproject.toml:
[tool.silicai]
component_libraries = [
{ path = "path/to/extra-components" },
]
Usage
# Clone with submodules
git clone --recurse-submodules git@github.com:mageoch/silicai.git
uv sync
# Validate a component or circuit file
silicai-validate path/to/component.yaml
# Generate a KiCad schematic from a circuit definition
silicai-generate path/to/circuit.yaml --output kicad/
# Run the MCP server
silicai-mcp --project-dir .
MCP Server
SilicAI exposes a Model Context Protocol server that lets Claude Code read component definitions and generate schematics. Add to your project's .mcp.json:
{
"mcpServers": {
"SilicAI": {
"type": "stdio",
"command": ".venv/bin/silicai-mcp",
"args": ["--project-dir", "."]
}
}
}
Documentation
Schema reference: mageoch.github.io/silicai
Status
v0.1.0 — public beta. Core schema, validation, KiCad generation, and MCP server are functional. Schema and component format may evolve before a stable 1.0 release.
Metadata
Release files for silicai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| silicai-0.1.0.tar.gz | 70.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| silicai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 163.8 kB
Release files / silicai-0.1.0.tar.gz
| Download URL | silicai-0.1.0.tar.gz |
|---|---|
| Size | 70.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2b95936beb833a910d11492d79b91e29cf0388bd82f6ec6b1020b377ecc7456d
|
|
BLAKE2b-256 checksum How to use checksums |
8669034b5ed10714ea844229415a3f012801c85830f020a36ee5bfb0a4b5d775
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 27, 2026.
Transparency logRelease files / silicai-0.1.0-py3-none-any.whl
| Download URL | silicai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 93.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d454952b8ccab54570dbf14a47ba13c788afb10109941a1b8c0c4c263faa8173
|
|
BLAKE2b-256 checksum How to use checksums |
5877c868a4315429b1e5f629585080d68b16c3c952b70370ddc1d8cf24fbe479
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Mar 27, 2026.
Transparency log