MoonshotAI
Featured
Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
signal-app
Signal is a local AI-powered investment research knowledge base desktop app that turns curated feeds, automated mining, and market/financial/hot topic clues into traceable cognitive cards for analysis, graph, review, factor validation, and decision support.
Stars
23
7-day growth
No data
Forks
1
Open issues
0
License
No data
Last updated
2026-07-19
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It focuses on building a personal cognitive repository for investment research using local AI, emphasizing traceability and a closed-loop workflow without connecting to broker APIs or executing trades.
Who it is for
- Individual investors
- Quantitative analysts
- Financial researchers
- Self-directed traders who want to systematize their research
Use cases
- Capture and organize market signals from news, earnings, and hot topics
- Build a knowledge graph of investment insights for review and validation
- Create a personal cognitive loop for factor analysis and decision support
- Offline local AI analysis without internet dependency for privacy
Strengths
- Local-first architecture ensuring data privacy and offline capability
- Supports multiple data sources (manual input, auto mining, market/financial clues)
- Provides structured cognitive cards with traceability for audit and review
- Includes real product downloads with checksum verification and detailed documentation
Considerations
- Currently only supports macOS platform
- Does not connect to broker APIs or automate trading (explicitly stated)
- Early version (0.1.3) with limited features and possible instability
README quick start
Signal 认知外脑
Signal 是本地 AI 投研认知库桌面应用。它帮助把投喂、自动挖掘和行情/财报/热点线索沉淀为可追溯的认知卡片，再用于分析、图谱、复核、因子验证和决策辅助。应用不连接券商接口，不自动下单，不构成投资建议。
产品架构
演示
下载
当前已收录 macOS 安装包：
| 平台 | 文件 | 建议 |
|---|---|---|
| macOS Intel + Apple Silicon | Signal_0.1.3_universal.dmg | 不确定芯片架构时优先用这个 |
| macOS Apple Silicon | Signal_0.1.3_aarch64.dmg | M1/M2/M3/M4 Mac |
| macOS Intel | Signal_0.1.3_x64.dmg | Intel Mac |
0.1.3 修复了认知库 Git Remote 配置、商品去重与筛选联动，以及本地 Claude/Codex/Trae 分析任务未自动提交的问题；安装包还会校验内置 tmux、财报/价格脚本与代码签名。0.1.2 仅保留作历史归档，不建议继续安装。
校验文件见 CHECKSUMS.txt，产物清单见 packages/manifest.json。
文档
仓库约定
packages/：安装包和静态分发产物。docs/：面向最终用户的使用文档。CHECKSUMS.txt：当前安装包的 SHA-256 校验和。packages/manifest.json：安装包的版本、架构、大小、来源路径和校验信息。
新增安装包时，只提交可直接分发的安装器或压缩包，不提交 target/deps、debug、incremental、node_modules 等构建缓存。
Related repositories
Similar projects matched by category, topics, and programming language.
xuchonglang
Featured
investing-for-beginners
A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.
Krishnagangwal
Featured
CS-Fundamentals
A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.