Research & Analysis✨gemini🤖claude💬gpt🌐universal
Terminal 1: start the API server
Autonomous Engine for Theoretical & Hands-on Exploration in Research
Quick Start
Install this Skill
npx skills add Science-Discovery/Aether<h1 align="center">Aether</h1> <p align="center"><em>Autonomous Engine for Theoretical & Hands-on Exploration in Research</em></p> <p align="center">An AI research assistant for researchers, built on <a href="https://github.com/anomalyco/opencode">OpenCode</a>.</p> <p align="center"><a href="https://aether.aiphys.cn/">🌐 aether.aiphys.cn</a></p> <p align="center"> <a href="README.md">English</a> | <a href="README.zh.md">简体中文</a> | <a href="README.zht.md">繁體中文</a> </p> --- ## Overview Aether is a feature-rich AI research assistant platform, running on a local client/server architecture. It offers two usage modes: - **Web Browser Version**: Starts a local HTTP server and provides a full interactive interface through the browser — more stable - **Electron Desktop Version**: Native desktop window with a smoother experience (may still have some instability) Both modes share the same local data and sessions. Mobile access (WeChat / Feishu / QQ) is also supported. ### Key Features - **Ready to use**: Download the installer script from the official website, or download the archive from Releases — built-in default model settings included - **Full coding capabilities**: Fully inherits OpenCode's coding capabilities — code execution, LSP code intelligence, file and terminal operations, covering the entire daily development workflow - **25+ AI providers**: Supports Anthropic, OpenAI, Google Gemini, AIhubmix, DeepSeek, Z\.AI, Kimi, Qwen, and other mainstream platforms, plus any OpenAI-compatible API - **20+ built-in Skills**: Literature review, paper writing, deep research, arXiv search, peer review, research grant writing, document generation, and more — ready to use out of the box - **Skill self-evolution**: After completing a task, the Agent automatically reviews the conversation history and solidifies successful experiences into reusable Skills (copy-on-write writes, security scanning, version snapshots), forming a continuous learning loop - **MCP protocol support**: Integrates Model Context Protocol — connect local or remote MCP servers to extend the toolset - **Knowledge base (RAG)**: Vector-index PDF and text documents, with semantic search that injects only relevant context, significantly reducing token usage - **PDF reading mode**: Read PDFs directly in the Web UI with highlights, bookmarks, notes, and AI-assisted translation and Q&A - **PDF to Markdown**: AI-driven multi-stage pipeline that converts PDF papers into high-quality editable Markdown (with formula and image extraction) - **Markdown translation**: AI-powered Markdown document translation that automatically preserves LaTeX formulas - **Voice input**: Speech-to-text powered by multimodal models, automatically removing filler words and correcting technical terms - **Git integration**: View branches, commit history, diffs, and file changes in the UI - **Scheduled tasks**: Supports cron expressions, fixed intervals, and one-time scheduled tasks for automating research workflows - **Memory mechanism**: AI automatically persists user preferences and interaction experiences to a local memory file, reused across sessions without repetition - **Session sharing**: Generate shareable links with real-time conversation sync --- ## Installation & Launch ### Installer Script (Recommended) Download the installer script for your platform from the [official website](https://aether.aiphys.cn/) for one-click installation with automatic updates. After installation, simply launch from your system applications. ### Manual Installation Download the archive for your platform from the [Releases page](https://github.com/Science-Discovery/Aether/releases). #### Web Browser Version Extracted directory layout: ``` aether ← CLI binary (aether.exe on Windows) web/ ← Frontend static assets (must stay alongside the binary) install.sh/.command/.bat ← Installation script (‼️ creates desktop shortcuts, app entries, etc.) Aether.sh / .command / .vbs ← Launchers aether-icon.* ← App icon ``` It is recommended to run the installation script first. After installation, you can launch Aether from your system applications: **Windows**: Right-click `install.bat` → Run as administrator (or run it in a terminal). After installation, launch from the desktop shortcut or Start Menu. **macOS**: In the extracted directory: ```bash chmod +x install.command # first time only ./install.command ``` If prompted with "cannot be opened because the developer cannot be verified" or "is damaged": ```bash xattr -cr ./install.command ./aether ./Aether.command ``` Then right-click `install.command` and select "Open" to proceed with installation. After installation, launch from `/Applications/Aether.app` or Launchpad. **Linux**: ```bash chmod +x install.sh # first time only ./install.sh ``` After installation, launch Aether from the system application launcher. (⚠️ Note: The shell script shortcut previously created on the desktop is now depreca ... (truncated)
Repository
62stars
16forks
Details
Related Skills
More research & analysis skills you might like
pr-improver
Research & AnalysisRuns an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branch touched. Reviews are performed by an installed PR-review skill (default: pr-review-toolkit's review-pr). Use to fix review findings on a branch before opening or updating a pull request ('clean up this branch', 'fix this PR until review passes', 'run review-and-fix on my changes'). NOT for a one-time review — run the PR-review skill directly.
🤖claude🌐universal
7.5k
643
View
code-improver
Research & AnalysisRuns an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names: any installed skill or agent. Keeps a cross-round findings ledger, escalates when fixes stop converging, and guards scope mechanically. Use when asked to 'improve this code until review passes', 'run an improvement loop with <reviewer>', or to iterate review-and-fix with a specific reviewer. For skills prefer the skill-improver entry; for a branch prefer pr-improver.
🤖claude🌐universal
7.5k
643
View
skill-improver
Research & AnalysisRuns an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes stop converging, and a mechanical scope guard. Reviews are performed by the plugin-dev skill-reviewer agent. Use to fix skill quality issues, iteratively refine a skill, or resume a loop after an escalation ('fix my skill', 'improve this skill until it passes review', 'skill improvement loop'). NOT for a one-time review — use the plugin-dev skill-reviewer agent directly.
🤖claude🌐universal
7.5k
643
View
audit-augmentation
Research & AnalysisAugments Trailmark code graphs with external audit findings from SARIF static analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x binary-analysis graph exports. Maps findings to graph nodes by file and line overlap, creates severity-based subgraphs, and enables cross-referencing findings with pre-analysis data (blast radius, taint, etc.). Use when projecting SARIF results onto a code graph, overlaying weAudit annotations, importing binary graph findings, cross-referencing Semgrep, CodeQL, or binary-analysis findings with call graph data, or visualizing audit findings in the context of code structure.
🌐universal
7.5k
643
View