Skip to main content

Local-first, privacy-preserving genealogy CLI with modular LLM providers.

Project description

AncestryLLM

AncestryLLM is a local-first platform for genealogy research tools. It combines deterministic RootsMagic and GEDCOM workflows with optional, explicitly selected LLM providers. The one-shot CLI and prompt-toolkit/Rich REPL are the only implemented product surfaces in 0.3.0. They derive commands from the same CommandSpec metadata and dispatch through the shared CommandExecutor into transport-neutral application services. The accepted local Electron and private FastAPI desktop architecture remains a later-roadmap adapter direction; it is unshipped and is not a public API.

Install and start

Python 3.12 through 3.14 and a working OS credential store are required. Install the isolated command with pipx:

pipx install ancestryllm
ancestry --version
ancestry --help

Install every optional LLM provider with pipx install 'ancestryllm[all-llm]'. Remote providers are never selected from installed packages or environment keys: every cloud call still requires an explicit profile and consent.

Run ancestry with no arguments for the prompt-toolkit/Rich interactive console. It is the only supported interactive console; the prompt stays responsive while background operations render live, sanitized spinner or completed-unit progress above it. One-shot and JSON output never emit terminal animation. The canonical command reference, examples, offline defaults, and privacy rules are in the CLI guide; see the console guide for interactive use and the file-ingress policy for per-format input limits and stable rejection codes.

Included modules

  • rootsmagic: immutable, bounded SELECT/CTE queries and deterministic GEDCOM export.
  • gedcom: merge, rooted subtree, quality analysis, incremental update, and rebase.
  • prompts: immutable prompt revisions with declared variables and output schemas.
  • people: curated research people, identifiers, facts, links, and provenance.
  • providers: explicit Ollama, OpenAI, Anthropic, Gemini, and OpenRouter profiles.
  • ocr: schema-validated extraction through the same provider boundary.
  • secrets: no-echo OS-keyring management; values never appear in status output.

Development

git clone https://github.com/sodejm/AncestryLLM.git
cd AncestryLLM
make setup
make test
make lint
make typecheck
make security
make sbom

make setup creates .venv and installs the checkout in editable mode with locked development and provider dependencies. The equivalent manual command is .venv/bin/pip install --editable '.[all-llm,dev]'; it is for contributors, not end-user installation.

The dependency graph is locked in uv.lock. Never commit real family trees, GEDCOM exports, databases, logs, reports, secrets, or research-person data.

Read the architecture, desktop ADR, CLI guide, privacy and consent, provider guide, GEDCOM compatibility, encrypted backups, bounded file ingress, and threat model.

Versioning follows Semantic Versioning 2.0.0. The versioning policy defines the CLI contracts covered by a release.

Interoperability status

Automated round-trip and preservation tests run in CI. Ancestry, Geni, and MyHeritage imports must still be manually smoke-tested for each release; this repository does not claim production interoperability until that checklist is completed and recorded.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ancestryllm-0.3.0.tar.gz (253.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ancestryllm-0.3.0-py3-none-any.whl (265.3 kB view details)

Uploaded Python 3

File details

Details for the file ancestryllm-0.3.0.tar.gz.

File metadata

  • Download URL: ancestryllm-0.3.0.tar.gz
  • Upload date:
  • Size: 253.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for ancestryllm-0.3.0.tar.gz
Algorithm Hash digest
SHA256 b6b3fd09989265a95b54bc8bb26d0eae7cba6b8d52946ed9f9066a36cab58eb8
MD5 fe32118ddd5353ecef959f897159ca72
BLAKE2b-256 fc5036eeea4617b3accec568b04ac51ebaadf09f4c34cf4815f8ec43627f0cc8

See more details on using hashes here.

Provenance

The following attestation bundles were made for ancestryllm-0.3.0.tar.gz:

Publisher: release.yml on sodejm/AncestryLLM

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file ancestryllm-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: ancestryllm-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 265.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for ancestryllm-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5b50520d3a1d3652529f9219aa2b00f329063fd5330302501fff2acf1869f274
MD5 744ef675fa999557976eedf8d0c9eef3
BLAKE2b-256 5e841da6409f286c6c7ad4d43d6f29b2570caef874578e5f093e6723b8ec841b

See more details on using hashes here.

Provenance

The following attestation bundles were made for ancestryllm-0.3.0-py3-none-any.whl:

Publisher: release.yml on sodejm/AncestryLLM

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page