PyPI Python License: MIT CI

Bhāratīya calendar infrastructure for developers — Panchang, festivals, muhurat, regional calendars, and batch computation.

Built on a Rust computation engine with Swiss Ephemeris precision. Not an astrology API. It answers: "What is happening in the Bhāratīya calendar right now, at this location?"

from datetime import date
from panchang import panchang, calendar, Location
delhi = Location(lat=28.6139, lng=77.2090, tz="Asia/Kolkata")
# Daily Panchang
today = panchang.compute(date.today(), delhi)
print(today.tithi.name) # "Shukla Dvitiya"
print(today.nakshatra.name) # "Pushya"
print(today.nakshatra.pada) # 3
print(today.sunrise) # 2026年03月03日 06:42:18+05:30
# Festival dates
festivals = calendar.compute_festivals(2026, delhi)
for f in festivals[:3]:
 print(f"{f.name}: {f.date}")
# Makar Sankranti: 2026年01月14日
# Vasant Panchami: 2026年02月01日
# Maha Shivaratri: 2026年02月15日

pip install panchang

Requires Python 3.11+. Wheels available for Linux, macOS, and Windows.

All 5 Panchanga elements with precise transition times (start/end to the second):

• Tithi (lunar day) — with Paksha (Shukla/Krishna)
• Nakshatra (lunar mansion) — with Pada (1-4)
• Yoga (Sun-Moon combination)
• Karana (half-tithi)
• Vara (weekday)

• Sunrise/sunset using Hindu rising model (disc center at horizon, Bhāratīya atmospheric refraction)
• Location-aware computation for any lat/lng/timezone

• Rahu Kalam, Yama Gandam, Gulika Kalam
• Abhijit Muhurat
• Choghadiya (16 windows per day — 8 day + 8 night)

55+ Hindu festivals astronomically computed for any year:

• Tithi-based: Diwali, Holi, Janmashtami, Ram Navami, Ganesh Chaturthi, Navaratri, ...
• Sankranti-based: Makar Sankranti, Pongal, Vishu, Bihu, ...
• Nakshatra-based: Onam (Thiruvonam)
• Ekadashi: All 24 per year with Smartha and Vaishnava dates
• Vrat dates: Pradosh, Sankashti Chaturthi, Amavasya, Purnima (~60 per year)

Festival definitions are data-driven (YAML, not hardcoded) with year-agnostic astronomical rules. Each resolved date includes a reasoning string explaining the determination.

8 regional calendar systems with proper era numbering:

• Solar: Tamil, Bengali, Malayalam, Kannada
• Lunar: Hindi, Marathi, Telugu, Gujarati
• Era support: Vikram Samvat, Shaka Samvat, Bangabda, Kollavarsham, Thiruvalluvar, 60-year Jovian cycle

• Both Amant (South Bhārat) and Purnimant (North Bhārat) systems
• Adhik Maas (intercalary month) and Kshaya Maas detection

Death anniversary date resolution — given a death date, computes the Shraddha date for any target year using the lunar tithi and month.

Full-year or date-range Panchang in a single call:

from panchang import batch, Location
delhi = Location(lat=28.6139, lng=77.2090, tz="Asia/Kolkata")
year_data = batch.compute_year(2026, delhi) # 365 days of Panchang

All computations use the Swiss Ephemeris (Moshier analytical model) with Lahiri/Chitrapaksha Ayanamsa — the Government of Bhārat standard.

Cross-validated against Drik Panchang for 2026年02月24日, Delhi:

All element names match exactly. Timing differences are 1-5 minutes due to sunrise geometric model variations.

Rust core + Python API. All astronomical math runs in Rust via PyO3, giving C-level performance with a Pythonic interface.

Python (pydantic models, typed API)
 └── Rust via PyO3 (panchang, festivals, muhurat, batch)
 └── Swiss Ephemeris C (planetary positions via FFI)

Performance (Rust benchmarks):

• Full Panchang: ~3.7 ms
• Sunrise: ~29 μs
• All 9 planets: ~7 μs

# Setup
uv venv
uv pip install -e ".[dev]"
# Build Rust extension
maturin develop --uv
# Run tests
uv run pytest tests/ -v
cargo test --manifest-path crates/panchang-core/Cargo.toml -- --test-threads=1
# Lint
uv run ruff check python/ tests/
cargo clippy --manifest-path crates/panchang-core/Cargo.toml -- -D warnings

Contributions welcome! Please open an issue first to discuss what you'd like to change.

# Run the full check suite before submitting
uv run ruff check python/ tests/
uv run pytest tests/ -v
cargo test --manifest-path crates/panchang-core/Cargo.toml -- --test-threads=1
cargo clippy --manifest-path crates/panchang-core/Cargo.toml -- -D warnings

MIT