惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

IT之家
IT之家
A
About on SuperTechFans
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
N
Netflix TechBlog - Medium
Microsoft Security Blog
Microsoft Security Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 三生石上(FineUI控件)
博客园 - 聂微东
博客园 - Franky
D
Docker
Martin Fowler
Martin Fowler
Engineering at Meta
Engineering at Meta
The Cloudflare Blog
人人都是产品经理
人人都是产品经理
Last Week in AI
Last Week in AI
U
Unit 42
F
Fortinet All Blogs
H
Help Net Security
Blog — PlanetScale
Blog — PlanetScale
Microsoft Azure Blog
Microsoft Azure Blog
罗磊的独立博客
P
Proofpoint News Feed
月光博客
月光博客
G
Google Developers Blog

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - SpecStudio-net/Aspectarian: personal Jyotiṣa asp...
SpecStudioHN · 2026-06-16 · via Hacker News: Show HN

A personal Vedic astrology transit app. Enter your natal chart once; Aspectarian computes active transit contacts using Parāśaran dṛṣṭi and yuti (sign-based, no orbs) and generates an interpretation via Claude. Includes a 30-day calendar, Vimśottarī daśā display, transit duration indicators, and aṣṭakavarga-informed readings.


Prerequisites

  • macOS (tested on macOS 12+, Intel and Apple Silicon)
  • Python 3.12 or later — download from python.org
  • Anthropic API key — get one at console.anthropic.com
  • Xcode Command Line Tools — required to compile system libraries. The setup script checks for this automatically and opens the installer if needed. You can also install in advance by running xcode-select --install in Terminal.

Installation

  1. Unzip the archive and open Terminal inside the folder:

  2. Run the setup script (creates a virtual environment and installs all dependencies):

    This takes about a minute on first run. You will see "Setup complete" when it finishes.


Running

Then open http://localhost:7842 in your browser.

On first launch, you will be taken through the setup wizard:

  1. Name — your display name
  2. API key — your Anthropic API key (stored securely in macOS Keychain; never written to disk)
  3. Birth data — date, time (UTC), and place of birth
  4. Preferences — default reading window, language, theme

After setup, Aspectarian opens directly to your transit reading.


What's included

Path Contents
engine/ Ephemeris computation, contacts, daśā, aṣṭakavarga, calendar
context/ System prompt assembly, symbol map
session/ LLM client, NDJSON streaming, reading storage
reports/ Day / week / month report logic
storage/ SQLite models and async queries
ui/ FastAPI app + Vanilla JS frontend
ephemeris/ephe/ Swiss Ephemeris data files (required)
data/ GeoNames city database for birth place search
symbol_map.json Jyotiṣa interpretation framework
config.py All configuration (overridable via env vars)

Configuration

All settings have sensible defaults. Override by setting environment variables before running:

Variable Default Description
CLAUDE_MODEL claude-sonnet-4-6 Anthropic model
CLAUDE_MAX_TOKENS 8192 Max output tokens per reading
PORT 7842 Local server port
HOST 127.0.0.1 Bind address (localhost only)
DB_PATH aspectarian.db Path to user database
HISTORY_MAX_READINGS 5 Past readings included in LLM context

Example — run on a different port:


Data and privacy

  • All computation runs locally — ephemeris, contacts, daśā, aṣṭakavarga.
  • Your birth data and reading history are stored in aspectarian.db (SQLite, local only).
  • Your API key is stored in macOS Keychain via the system keyring.
  • Transit readings are sent to the Anthropic API (Claude) for interpretation. No data is stored by Anthropic beyond standard API logging.

Stopping the server

Press Ctrl-C in the Terminal window running ./run.sh.