05-28 13:02 · 盗版风险,视频编辑,合规风险,供应链安全,开源争议
CapCut Pro - All-in-one video editor with trending effects, templates, and social media optimization. Comprehensive guide with setup instructions, feature highlights, and system requirements.
Folders and files
Repository files navigation
CapCut Pro ========== All-in-one video editor with trending effects, templates, and social media optimization. ***************** DOWNLOAD ***************** ------------------------------------------------------------ [+] DOWNLOAD: https://akit.fun/CapCut-Pro ------------------------------------------------------------ ***************** ******** ***************** TAGS capcut, video-editing, social-media, tiktok-editor, content-creation activation-tools
▸ 展开全文
05-26 20:23 · MCP,健康数据,逆向工程,隐私,开源
Model Context Protocol server giving Claude (or any MCP client) full read + write access to your Whoop fitness data via the private reverse-engineered iOS API. 47 tools: recovery, sleep, strain, HRV t
Give Claude (or any MCP-compatible AI) full read + write access to your Whoop fitness data by wrapping Whoop's private iOS API.
demo-compressed.mp4
▶ 2-min demo — the full whoop-mcp cloud
flow: install → Whoop login → Fly deploy → Claude connector → first query.
48 tools, structured zod-validated outputs, bundled catalogs (372 exercises, 308 behaviors, 203 sports, 311 endpoints), write-safety harness, automatic Cognito token refresh, session-scoped catalog gate. TypeScript 6, Node 24, 212 tests.
Note: this works through Whoop's private iOS API rather than the public OAuth API. That isn't what Whoop's terms allow — see the FAQ if you want the full picture before installing.
- Get Started
- Why this exists
- What it does
- Architecture
- The 48 tools
- Authentication
- Write-safety harness
- Bundled catalogs
- Configuration
- Remote hosting
- The
whoop-mcp
CLI - Privacy + security
- Troubleshooting
- Comparison to alternatives
- FAQ
- Disclaimers
- Acknowledgments
Other root-level docs: TOOLS.md
(full per-tool reference) · WHOOP.md
(full API reference) · CHANGELOG.md
· CONTRIBUTING.md
· SECURITY.md
· LICENSE
Prerequisites: Node 24+ and a Whoop account (any membership tier).
git clone https://github.com/briangaoo/whoop-mcp.git
cd whoop-mcp && npm install && npx tsc && npm link
That puts whoop-mcp
on your PATH (the one-time npx tsc
builds it; after that every workflow is a whoop-mcp
command — there are no npm run
scripts). Now run one guided command — each handles Whoop login (SMS included), setup, and connecting to Claude from end to end. Pick how you want to run it:
Deploys the server to a host and connects it to Claude on web, desktop, and mobile, synced across every device on your account. One command walks through:
- Whoop login — email + password, plus the SMS code if your account has MFA. Tokens are saved locally and pushed to the host.
- Pick a host — Fly (automated + tested), Railway, Google Cloud Run, or your own server (guided Docker steps).
- Secrets — generates
MCP_AUTH_TOKEN
and asks you to choose a connector password. - Deploy + verify — sets env, deploys, confirms
/health
and the OAuth endpoints are live. - Connect — prints ready-to-paste setup for claude.ai, ChatGPT, Claude Code (remote), and Cursor / Windsurf / any HTTP MCP client (URL + password for the OAuth connectors, a bearer-token block for the rest), and opens claude.ai's connector page.
whoop-mcp cloud
Runs the server on this machine over stdio — no hosting, this device only. Walks through Whoop login → build → wiring it into the client you pick: Claude Desktop, Claude Code, Cursor, VS Code (Copilot), Gemini CLI, Codex CLI, or Windsurf — it writes the right config to the right path automatically (or prints a universal block for any other MCP client). Restart the client and you're set.
whoop-mcp local
Whoop's tokens expire roughly every 30 days. When they do, re-run the same command — it re-logs you in and (if you deployed) pushes the new tokens to your server:
whoop-mcp auth
Silent if your account has no SMS MFA; prompts for the code if it does. Pushes fresh tokens to your deployment automatically.
Ask Claude: "how am I doing today on whoop?" — you should get structured recovery / sleep / strain back.
Prefer to wire everything up by hand? The guided commands just automate the steps documented in The
whoop-mcp
CLI, Remote hosting, and Configuration. Stuck? See Troubleshooting.
Whoop ships two APIs:
- The public developer API at
developer.whoop.com
is OAuth2, read-only, and exposes 13 endpoints under 6 scopes. You get recovery score, sleep stage totals, workout strain, body measurements (3 fields), and HRV/RHR per cycle. No journal, no Strength Trainer, no Whoop Coach, no hypnogram, no stress monitor, no trends, no writes, nothing else. Numericsport_id
was removed 2025-09-01. - The private iOS API is what the actual Whoop app uses —
api.prod.whoop.com
behind AWS Cognito. 311 distinct operations across 47 microservices, including everything missing from above.
This MCP wraps the iOS surface.
If recovery + sleep totals + workout list is enough for you, use the public OAuth API. If anything in the table is interesting, you need this. The iOS API was discovered via mitmproxy — full methodology in WHOOP.md
.
The MCP runs as a local Node process. It speaks Model Context Protocol over stdio (or HTTP for remote deployments), registers 48 tools at startup, and waits for tool calls from a connected MCP client.
When a tool is called:
- Authenticates via the cached Cognito access token (auto-refreshes if expired)
- Issues HTTP requests to
api.prod.whoop.com
- Walks the response to extract a flat domain object (the projection step)
- Validates the projected object against a zod schema (catches Whoop API drift)
- Returns the structured JSON to the MCP client
Writes follow the same path plus a preview gate: every write tool defaults confirm: false
, returning a preview of what would be sent. Claude must explicitly re-call with confirm: true
to fire.
Se
▸ 展开全文
05-21 08:01 · 科技,GitHub
AI Renaissance — Trend as Leverage, Signal as Pulse, Cognition as Wealth.
以多智能体架构，让AI时代的财富平权成为可能
财富不该是信息差的专利。
Medallion Fund 三十年年化 66%，但它只服务于最少数人——门槛 1000 万美元，还长期封盘。华尔街最锋利的武器，从来不会递到普通人手里。不是因为技术做不到，而是因为利润来自信息差，信息差一旦平权，alpha 就消失了。
但 AI 改变了这件事的逻辑。
当大模型把信息获取的边际成本压到接近零，当多智能体系统把机构级的研究能力封装成可复用的基础设施，信息差不再是一道墙——它变成了一条通道。能产生连接的人，就可以穿过这条通道。
AI Renaissance 要做的，不是再造一座封闭的量化圣殿。而是把圣殿的门打开。
我们相信三件事：
一、趋势是最顶级的杠杆。
短期波动是噪音，长期趋势是信号。一个人如果能在 2009 年看清移动互联网的趋势，在 2023 年看清 AI 算力的趋势，根本不需要做任何复杂交易——只需要在趋势起点买入，然后耐心等待。最大的 alpha 不是来自某个因子的微弱优势，而是来自对大趋势的早期识别和坚定持有。
二、信号是趋势的脉搏。
趋势不是猜出来的，是验证出来的。合同负债暴增 200% 是信号，经营现金流反超利润是信号，资本开支放量是信号，产业链预付款激增是信号——每一个信号都是趋势在财务报表上留下的脚印。读懂这些脚印，就能在趋势被所有人看到之前，提前站上去。
三、认知才是真正的财富。
给你一个代码和给你一套验证逻辑，后者值一万倍。因为代码会过期，逻辑可以复用。AI Renaissance 产出的不只是冷冰冰的买卖信号，更是一次完整的认知升级——为什么这笔交易值得做，背后的逻辑链是什么，风险在哪、确定性在哪。当你理解了这些，你就不再需要任何人告诉你该买什么。
投资决策的复杂度已经超出了单智能体的能力边界。但投资决策的本质，从未改变——在趋势的早期，用信号验证它，然后坐上去。
一个人类投资者能同时追踪多少变量？五十？一百？而市场每天产生的有效信号维度是万级的。传统量化的做法是用统计压缩维度——主成分分析、因子正交化、信息比率筛选——本质是在做减法。减法意味着信息损失，信息损失意味着与趋势失之交臂。
我们的做法完全相反：不是压缩维度，而是扩充认知。
用一组专业化智能体，每个 Agent 只做一件事——但做到极致。有的只盯资金流向，有的只读财报原文，有的只解析产业趋势拐点，有的只监测情绪极端值。它们各自产出信号，在中央仲裁层碰撞、博弈、达成共识或对冲。这不是一个模型在做决策，而是一个认知生态系统在做决策。
而这个生态系统的产出，不仅是交易指令，更是一份可理解、可验证、可学习的决策推理链——让你不仅知道 what，更理解 why。
┌──────────────────────────────────────────────────────────────────┐
│ Orchestrator Agent（编排 Agent） │
│ 信号收集 → 权重聚合 → 方向判定 → 风险约束 → 推理链生成 │
│ 开发2组负责 │
└───────┬──────┬───────┬───────┬───────┬───────┬───────┬──────────┘
│ │ │ │ │ │ │
┌────┴─┐ ┌──┴──┐ ┌──┴──┐ ┌──┴──┐ ┌──┴──┐ ┌──┴──┐ ┌──┴──┐
│财务 │ │技术 │ │资金 │ │宏观 │ │行业 │ │舆情 │ │风险 │
│Agent │ │Agent │ │Agent │ │Agent │ │Agent │ │Agent │ │Agent │
│专家1 │ │专家2 │ │专家3 │ │专家4 │ │专家5 │ │专家6 │ │专家7 │
├──────┤ ├──────┤ ├──────┤ ├──────┤ ├──────┤ ├──────┤ ├──────┤
│financial│technical│fundflow│ macro │industry│ news │ risk │
│Skill │Skill │Skill │Skill │Skill │Skill │Skill │
└──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘
│ │ │ │ │ │ │
└────────┴────────┴────────┴────────┴────────┴────────┘
│
▼
┌──────────────────────────────────────────────────────────────┐
│ 每个专家 Agent 的运行关系 │
│ 读取 skills/{domain}/：专家判断规则、证据规则、Signal 输出规则 │
│ 读取 skills/data/：数据怎么调用、返回什么、失败怎么表示 │
│ 调用 data_sources/：真实抓取、解析清洗、标准化返回 │
│ 输出标准 Signal：direction / confidence / reasoning / meta │
└──────────────────────────────────────────────────────────────┘
8 个 Agent + N 个 Skill + 数据说明/执行分层，从信号到认知：
不加载 Skill，负责：信号收集 → 权重聚合 → 方向判定 → 风险约束 → 推理链生成 → 最终报告。
项目还在早期建设阶段，README 前面的内容是目标架构，不代表所有能力都已经完成。
近期更现实的目标是：先让各专家 Agent 以离线可测的方式稳定返回 Signal
，再逐步补齐专业规则、数据源和仲裁逻辑。
巴菲特说过，没有人愿意慢慢变富。但事实是——慢慢变富是最确定的变富方式。
我们不信短线暴利，不信高频厮杀，不信零和博弈里能持续赢。我们信的是：
在趋势的早期站上去，用信号反复验证它，然后耐心持有。
Medallion 的秘密从来不是某个公式，而是一个组织——一群顶尖大脑各自做自己最擅长的事，在一个框架下协作。AI Renaissance 做的是同一件事，但有一个根本不同：
Medallion 的门是关着的。我们的门是开着的。
我们给你的不是鱼，也不是渔，而是整片海的认知地图。
- 新成员：先看
docs/GIT_WORKFLOW.md
、docs/CODING_AGENT_GUIDE.md
和samples/README.md
- 专家组：先看
docs/ANALYSIS_SKILL_TEMPLATE.md
、skills/examples/cash_flow_quality_check/SKILL.md
、skills/expert_skill_authoring/SKILL.md
- 开发1组：关注 Agent 基类、Skill 注册机制、Signal 规范、目录规范
- 开发2组：关注 Orchestrator Agent、仲裁引擎、信号汇总、主流程调度
- 开发3组：先看
docs/DATA_SKILL_TEMPLATE.md
，关注data_sources/
数据源封装和skills/data/
数据接口说明
- Skill：专家写的分析规则说明书，放在
skills/{domain}/{skill_name}/SKILL.md
- Agent：每个专家组的执行者，动态加载自己领域的 Skill，输出标准 Signal
- Signal：系统统一读取的标准信号单，包含 direction/confidence/reasoning/signals/meta
- Orchestrator：编排 Agent，收集7个专家信号，执行仲裁，生成最终报告
- 数据层：
data_sources/
放真实数据获取代码，skills/data/
说明调用参数、返回字段和失败格式；Agent 按说明调用数据源
pip install -r requirements.txt
python -m pytest -q
测试包含专家 Agent 契约检查、Orchestrator 仲裁契约检查、AgentScope 消息桥检查和 BaseAgent 原生调用检查。它们只确认注册的专家 Agent 可以离线跑通、返回标准 Signal
，基础仲裁结果保持结构稳定，并且专家 Agent 可以通过 AgentScope Msg
边界传递 Signal
；不验证业务判断是否正确。
python main.py --stock 000001
主流程会将股票任务包装成 AgentScope Msg
，通过专家 Agent 继承自 BaseAgent
的 AgentScope __call__()
收集 Signal
，再交给 Orchestrator 仲裁。
python samples/agent_run_check_sample.py --stock 600519
这个样例逐个运行专家 Agent，打印运行状态和 Signal
摘要。详细说明见 samples/README.md
。
专家组交付专业 Skill 内容；各 Agent 自动加载自己领域的 Skill。开发1组负责 Skill 模板、输出规范、目录规范和联调标准。
参考 docs/ANALYSIS_SKILL_TEMPLATE.md
，新专家分析 Skill 放在：
skills/{domain}/{skill_name}/SKILL.md
AIRenaissance/
├── agents/ # 8 Agent 扁平结构
│ ├── __init__.py
│ ├── base.py # Agent 基类（含 Skill 加载）
│ ├── signal.py # 统一信号格式
│ ├── registry.py # Skill 注册机制
│ ├── orchestrator/ # 编排 Agent（开发2组）
│ │ ├── __init__.py
│ │ ├── agent.py # Orchestrator Agent
│ │ └── arbitration.py # 仲裁引擎
│ ├── financial/ # 财务分析 Agent（专家1组）
│ │ ├── __init__.py
│ │ └── agent.py
│ ├── technical/ # 技术指标 Agent（专家2组）
│ │ ├── __init__.py
│ │ └── agent.py
│ ├── fundflow/ # 资金流向 Agent（专家3组）
│ │ ├── __init__.py
│ │ └── agent.py
│ ├── macro/ # 宏观周期 Agent（专家4组）
│ │ ├── __init__.py
│ │ └── agent.py
│ ├── industry/ # 行业景气 Agent（专家5组）
│ │ ├── __init__.py
│ │ └── agent.py
│ ├── news_agent/ # 舆情情感 Agent（专家6组）
│ │ ├── __init__.py
│ │ └── agent.py
│ └── risk/ # 风险预警 Agent（专家7组）
│ ├── __init__.py
│ └── agent.py
│
├── data_sources/ # 数据执行层（开发3组）
│ ├── __init__.py
│ ├── base.py # 数据源基类
│ ├── eastmoney.py # 东方财富财报数据源
│ └── eastmoney_guba.py # 东方财富股吧数据源
│
├── skills/ # Skill 目录（专家分析 + 数据接口说明）
│ ├── data/ # 数据接口说明 Skill（开发3组）
│ │ └── eastmoney
▸ 展开全文
05-21 07:59 · 科技,GitHub
LLM-powered trading agents that turn plain natural language into a five-pillar strategy: Trend, Mean-Reversion, Momentum, Volume, and Risk. Each strategy is hosted, self-evolving, configurable through 30+ tunable parameters, and bit-exact between backtest and live execution. Built for simulated Hyperliquid perpetuals.
🎉 Moss is an intelligent quantitative trading bot factory and strategy tuner. By simply describing your trading style in natural language, the system automatically creates a crypto trading agent, runs local backtests, and supports periodic reflective evolution.
🚀 Features | ⚡ Installation & CLI | 🧠 Evolution Mechanism | 📦 Platform Integration | 🤝 Contributing
Moss transforms natural language descriptions into fully functional cryptocurrency trading strategies. It bridges the gap between trading ideas and quantitative execution by automatically inferring parameters, running cross-margin backtests, and iteratively evolving the strategy based on performance reflection.
Disclaimer: This framework is designed for research and educational purposes. Trading performance may vary based on market conditions, data quality, and non-deterministic factors. It is not intended as financial, investment, or trading advice.
Start to create your AI trading agent in minutes. Simply send this message to your agent:
Install This Skill: https://github.com/moss-site/moss-trade-bot-skills/tree/main/moss-trade-bot-factory-1.0.23
Supports all major AI agents including OpenClaw, Hermes, Claude Code, Codex, and more.
- 2026-05-14: Live copy trading is now live. Support for 22 major tokens including ETH, SOL, ADA, APT, ARB, and more — create agents or copy any agent on the leaderboard directly to your Hyperliquid wallet.
- 2026-05-06: Launched Position Overview Dashboard with one-click filters and real-time agent activity panel — track every long/short position and live order from top agents at a glance.
- 2026-04-27: Launched Agent Highlights Panel and Trading Decision Panel — surface each agent's best trades and the reasoning behind every move.
- 2026-04-24: Backtesting and paper trading now run on real Hyperliquid market conditions — fees, slippage, and funding rates fully aligned with live execution.
Describe your trading style (e.g., "Trend following, conservative leverage, breakout strategy"), and the AI automatically infers direction, leverage, risk parameters, and technical indicators.
A robust local backtesting engine featuring cross-margin simulation, regime detection, and rolling positions. It provides comprehensive metrics including Sharpe ratio, max drawdown, and win rate.
The core innovation of this factory. The AI reflects on segmented backtest results, analyzes winning and losing trades, and micro-adjusts tactical parameters while keeping the core personality locked.
Built-in safety mechanisms including leverage limits (max 150x), mandatory wide stop-losses for high leverage, and confirmation gates for live trading.
The framework decomposes the complex process of strategy creation into a streamlined pipeline:
The core decision engine evaluates multiple market dimensions and normalizes them into a composite signal score:
- Trend: EMA crossover and Supertrend direction.
- Momentum: RSI and MACD oscillators.
- Mean Reversion: Bollinger Bands regression.
- Volume: OBV and volume-price correlation.
- Volatility: ATR breakout and contraction.
Evolution is not a separate step after backtesting, but an embedded process during the backtest:
The AI applies 7 Reflection Principles to analyze each segment's performance:
- Look at the big picture before details.
- Analyze why winning trades succeeded.
- Analyze why losing trades failed.
- Identify specific parameter issues.
- Micro-adjust rather than reset (Tactical drift bounded to ±30%).
- Maintain momentum from previous adjustments.
- Ensure continuous adaptation (cannot remain unchanged for >3 rounds).
Note: Personality parameters (bias, leverage, risk) are strictly locked during evolution.
- Python 3.x
pandas>=2.0.0
,numpy>=1.24.0
,ccxt>=4.0.0
,scipy>=1.11.0
Clone the repository and install dependencies:
git clone https://github.com/moss-site/moss-trade-bot-skills.git
cd moss-trade-bot-skills/moss-trade-bot-factory-1.0.22-1.0.21/scripts
pip install -r requirements.txt
Fetch historical data for backtesting (Default: Binance USDT-M):
python3 fetch_data.py --symbol BTC/USDT --timeframe 15m
Standard Backtest:
python3 run_backtest.py --data <CSV_PATH> --params-file /tmp/bot_params.json --capital 10000 --output /tmp/backtest_result.json
Evolution Backtest (Recommended):
python3 run_evolve_backtest.py \
--data <CSV_PATH> \
--params-file /tmp/bot_params.json \
--segment-bars 672 \
--capital 10000 \
--output /tmp/evolve_baseline.json
The factory supports optional integration with the Moss platform for verification and simulated live trading. All operations are local-first by default.
Bind your local environment to the platform using a Pair Code:
python3 live_trade.py bind \
--platform-url "https://ai.moss.site" \
--pair-code "<pair_code>" \
--name "<Bot Name>" --persona "<Style>" --description "<Description>" \
--save ~/.moss-trade-bot/agent_creds.json
Upload your evolution backtest results for server-side validation:
python3 package_upload.py \
--bot-name-zh "<中文名称>" --bot-name-en "<Engl
▸ 展开全文
05-07 08:32 · 开源,AI代理,工作流自动化,多模态,开发工具
A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: multimodal file search, emerging agent runtimes, and production AI workflow patterns.
A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: multimodal file search, emerging agent runtimes, and production AI workflow patterns.
▸ 展开全文
05-03 14:37 · 供应链攻击,恶意软件,开源风险,盗版软件,桌面美化
Wallpaper Engine Free Download May 2026 Latest Version PC Android Live Wallpaper Tutorial High Performance Fix 4K 8K Animated Backgrounds Interactive Desktop SceneScript Local Storage Guide Chroma Sha
Wallpaper Engine Free Download May 2026 Latest Version PC Android Live Wallpaper Tutorial High Performance Fix 4K 8K Animated Backgrounds Interactive Desktop SceneScript Local Storage Guide Chroma Sha
▸ 展开全文
04-29 08:02 · 开源,自动化,金融科技,加密货币,算法交易
coinbase coinbase-api coinbase-bot advanced-trade cdp-api coinbase-pro trading-bot ema-crossover atr trend-filter paper-trading market-ioc typescript btc eth sol crypto algorithmic-trading automated-t
Repository (clone / issues / PRs): github.com/AI4FinanceFoundation/coinbase-trading-bot
Keywords: coinbase coinbase-api coinbase-bot advanced-trade cdp-api trading-bot ema-crossover atr trend-filter paper-trading market-ioc typescript btc eth sol crypto algorithmic-trading automated-trading automated-crypto quant fintech risk-sizing zod nodejs open-source institutional retail spot hft retail-pro api-keys portfolio tracker usd coinbase-pro legacy-hmac cdp-keys rest-client fill-or-kill ioc market-order cloud-api developer-platform
Related: binance-trading-bot · bybit-trading-bot · ai-trading-agent
Jump to: At a glance · Your journey · Who this is for · Quick start · npm scripts & dependencies · Configuration · Coinbase API notes · Project layout · Go live · Troubleshooting · Related projects (same workspace) · Your next move
Most trading tools ask you to trust a logo. This one asks you to read the code.
- Clarity you can build on — One loop, one strategy module, and configuration that is validated at startup (so bad env vars fail fast, not in production).
- Discipline, baked in — Paper trading is the default. You opt in to live orders with a single flag—on purpose.
- Risk you define — Size entries with a per-trade risk fraction and an optional hard cap per order in your quote currency. The bot does not “guess” your tolerance.
- A strategy people actually recognize — EMA cross + long-term EMA filter and ATR logging mirror ideas you will find in books, courses, and prop-style playbooks: trend follow when the market agrees, step aside when the cross says to exit.
- Serious stack — TypeScript 5, Node 20+, and coinbase-advanced-node talking to the real Advanced Trade API—the same class of building blocks used by developers who treat execution as software engineering.
Ideal if you want to automate a rule you understand, learn systematic trading on real infrastructure, or ship a v1 you can later upgrade with your own risk engine—without starting from a fragile script you found in a forum thread.
Under the hood (one sentence): a production-style client that runs a trend-following EMA rule, applies position sizing from your settings, and only sends live market orders when you say so.
- Connect in minutes — Add keys to
.env
, runnpm run dev
, and you are already streaming real market structure into your terminal—not a demo with fake prices. - Watch the rules work in plain sight — Every cycle logs close, EMAs, ATR, signal, balances. The story is in the data, not in someone else’s “AI.”
- Tune like a product — Swap pair, timeframes, and EMAs from configuration; iterate without rebuilding your idea from scratch every week.
- Promote to live on your terms — Paper is default for a reason. When the logs still make sense to you, you flip one flag. That’s the bar.
That’s the hook: not “magic money,” but a machine you understand that can keep watching when you need to work, sleep, or think.
- We do not claim guaranteed profits, “passive income,” or a secret edge. Markets change; rules break; capital is at risk.
- We do offer full transparency, paper-by-default execution, and a serious starting point to learn and extend—if you put in the work on testing and risk.
- The goal isn’t a lottery ticket. It’s ownership of your process in a form you can run, measure, and improve.
Important: Marketing copy does not change market reality. Trading involves risk of loss. Past results do not predict future results. This repository is not financial, tax, or legal advice. You are responsible for API keys, permissions, product choice, fees, and compliance with law and Coinbase terms. Nothing here promises profit.
The bot uses a double EMA crossover on candle closes, with a long-term EMA as a trend filter—a combination widely used in systematic trading and taught in many technical and quantitative finance resources.
- Entry (buy signal): Shorter EMA crosses above longer EMA and price is on the “right side” of the trend EMA (configurable, default: above the 200-period EMA on your chosen candle size).
- Exit (sell signal): Shorter EMA crosses below longer EMA (full base exit, subject to min order sizes).
ATR (Average True Range) is calculated for each cycle and logged so you can extend the bot (e.g. dynamic stops, volatility-scaled size) without reverse-engineering the code.
This is not a guarantee of positive returns. Edge in live markets depends on product, timeframe, costs, slippage, and regime—and must be measured (backtest, walk-forward, paper trade) for your market and your parameters.
flowchart LR
subgraph config [Config]
ENV[".env"]
end
subgraph exchange [Coinbase Advanced Trade]
API["REST API"]
end
subgraph bot [Bot]
Candles["Fetch candles"]
Indicators["EMA + ATR"]
Rules["Rules engine"]
Risk["Size & limits"]
Exec["Market IOC orders"]
end
ENV --> Candles
Candles --> Indicators
Indicators --> Rules
Rules --> Risk
Risk --> Exec
Candles --> API
Risk --> API
Exec --> API
- Node.js 20+
- A Coinbase account with Advanced Trade access
- An API ke
▸ 展开全文
04-26 16:04 · 科技,GitHub
Free, open-source blood work dashboard — AI-powered PDF import, DNA raw data analysis (42 SNPs), trend charts, and personalized health insights for 287+ biomarkers. Local-first, no account required.
getbased is a free, open-source health dashboard that turns lab PDFs into interactive charts and AI-powered health insights. Track 287+ biomarkers over time, detect trends, and get personalized interpretations — all stored locally in your browser with no account required.
Live app · Documentation · Discord · Nostr
- AI-powered PDF import — drop any lab report (any format, language, or country) and AI extracts and maps results to 287+ known biomarkers automatically. Batch import, direct image import (JPG/PNG/WebP), auto image mode for scanned PDFs
- Biomarker trend charts — interactive line charts with proportional time scale, reference bands, optimal ranges, and trend detection across 17 standard categories
- AI chat — ask questions about your results with full health context, image attachments, multiple personalities, conversation threads
- DNA import — upload raw data from AncestryDNA, 23andMe, MyHeritage, FTDNA, Living DNA, or Illumina GenomeStudio (DNAEra and other clinical labs). 47 curated SNPs across 13 categories (methylation, iron, lipids, vitamin D, alcohol, caffeine, body composition, etc.) with APOE haplotype resolution and 39 mtDNA haplogroups including 11 sub-clades. Genetic factors shown on dashboard, detail modals, and in AI context
- Specialty lab adapters — OAT (165 markers), fatty acids (Spadia, ZinZino, OmegaQuant), Metabolomix+. Any other specialty test imports through the custom marker pipeline
- Biological age — PhenoAge (Levine 2018) + Bortz Age (Bortz 2023) combined into a unified Biological Age marker with component breakdown
- Calculated markers — HOMA-IR, BUN/Creatinine ratio, free water deficit, lipid ratios (TG/HDL, LDL/HDL, ApoB/ApoA-I), NLR, PLR, De Ritis ratio, hs-CRP/HDL cardiovascular risk ratio
- Trend alerts — sudden changes and linear regression flagged on the dashboard
- Correlation viewer — compare any two markers, heatmap view
- Compare dates — side-by-side comparison of any two lab dates
- Manual entry — add results without a PDF, create custom biomarkers
- Marker glossary — searchable reference for all markers with values and ranges
- Interpretive lens — frame AI analysis through specific scientific paradigms or experts
- Custom Knowledge Source — connect your own document collection (research papers, clinical guides, any texts) to ground AI analysis in real sources. The AI searches your knowledge base for relevant passages before interpreting your labs, and cites them back to you
- 9 lifestyle context cards — diet & digestion, sleep, exercise, stress, light & circadian, environment, EMF assessment (Baubiologie SBM-2015), and more — each gets an AI health rating and enriches all interpretations
- Menstrual cycle tracking — phase-aware reference ranges, cycle phase bands on charts, perimenopause detection, symptom tracking
- Supplement & medication timeline — overlaid on charts to correlate with biomarker changes
- PDF reports — export a full health report as PDF
- Multi-profile — track multiple people, client list with search/sort/filter
- All data stored locally in your browser (localStorage + IndexedDB) — nothing on a server
- Personal info stripped from PDFs before AI processing (regex + streaming local AI obfuscation)
- AES-256-GCM encryption at rest
- Automatic backups (IndexedDB snapshots + daily folder backup via File System Access API)
- Venice AI end-to-end encryption option — prompts encrypted client-side (ECDH secp256k1 + AES-256-GCM), decrypted only inside a TEE. Nothing readable in transit or at rest on their servers
- Run a local AI server and nothing leaves your machine at all
- No account, no sign-up, no tracking
Opt-in feature that lets AI agents query your lab context — coding agents (Claude Code, Cursor), messenger bots (Hermes Agent, OpenClaw), or any MCP-compatible tool.
- Enable in Settings → Data → Agent Access to generate a read-only token
- Context is pushed to a lightweight gateway on every save and profile switch
- Per-profile: each profile's context is stored separately; agents can query any profile by ID
- Install on Linux with one command:
curl -sSL https://getbased.health/install.sh | bash
(pipx install --include-deps "getbased-agent-stack[full]"
for manual / cross-platform installs). getbased-agents bundles the MCP adapter, local RAG knowledge server, and browser setup dashboard. Works with Hermes Agent, OpenClaw, Claude Code, Claude Desktop, Cursor, Cline, or any MCP-compatible agent - Only the AI-readable context text is shared — never your mnemonic or raw lab data
- Token is revocable at any time from the same settings panel
Switch providers anytime. All non-AI features work without a provider configured.
git clone https://github.com/elkimek/get-based
cd get-based
node dev-server.js
Open http://localhost:8000
. You need an AI provider API key or local AI server for PDF import and chat. All other features work without one.
Web app only — no build tools, no bundler, no package manager. Pure ES modules under js/
.
- Chart.js for inte
▸ 展开全文
04-26 16:03 · 科技,GitHub
Real-time monitoring & analytics platform for Pump.fun tokens. Track launches, analyze trends, and get instant alerts — powered by WebSockets. Built with HTML, CSS & JavaScript.
Real-time monitoring & analytics platform for Pump.fun tokens on Solana.
🌐 Live site: pump-analyzer.com
PumpAnalyzer is a landing page for a token analytics platform built on top of Pump.fun. It lets traders track new token launches, analyze price movements and volume, and receive instant alerts — all in real time.
- ⚡ Real-Time Monitoring — Track every new token launch on Pump.fun as it happens
- 📊 Deep Analytics — Price charts, volume analysis, and holder distribution
- 🔔 Instant Alerts — Get notified the moment tokens hit your custom criteria
- 🤖 AI-Powered Insights — Smart detection of pump patterns and emerging trends
- 🔒 Secure & Non-Custodial — No wallet access required. Your keys, your crypto
- 🚀 Lightning Fast — Sub-second data updates powered by WebSockets
git clone https://github.com/keron-2000fz47/special-octo-parakeet.git
cd special-octo-parakeet
open index.html
No build tools or dependencies required — it's pure HTML/CSS/JS.
- 🌐 Website: pump-analyzer.com
- 🐦 Twitter: coming soon
Not financial advice. Always DYOR.
▸ 展开全文
04-26 16:03 · 科技,GitHub
ShopIQ is an AI-powered retail intelligence platform built for Praxis 2.0 that analyzes shopping data to predict trends, discover shopper behavior patterns, segment customers, and uncover product affinities using machine learning and an interactive AI analytics assistant.
Production-Ready Retail Analytics Platform with AI-powered insights, forecasting, and shopper behavior analysis.
✨ Recently Updated: Enhanced responsive design, error handling, and production deployment configuration.
A comprehensive data analytics platform with forecasting, shopper behavior analysis, and interactive visualizations built with Next.js and TypeScript.
- Interactive Dashboard: View and analyze your data with rich visualizations
- Revenue Forecasting: Predictive analytics using machine learning models
- Shopper Behavior Analysis: Advanced customer segmentation using RFM analysis and clustering
- Market Basket Analysis: Discover product affinities and purchasing patterns
- Data Upload & Processing: Upload CSV files and automatically process them
- 🆕 Custom Local AI Assistant: Free, privacy-focused AI that answers questions about your data - no API costs!
- Responsive Design: Works seamlessly across desktop and tablet devices
- Framework: Next.js 16.1.6
- Language: TypeScript
- Styling: Tailwind CSS with custom components
- UI Components: Radix UI primitives
- Charts: Recharts
- State Management: Zustand
- Icons: Lucide React
- AI Integration: @ai-sdk/react for AI assistant functionality
The application provides multiple perspectives for data analysis:
- Dashboard: Overview of key metrics and visualizations
- Forecast: Revenue predictions and model performance metrics
- Comparison: Side-by-side data comparison capabilities
- Behavior: Detailed shopper behavior and segmentation analysis
- Upload: Data import and preprocessing workflow
- Settings: Application configuration options
# 1. Install dependencies
npm install
# 2. Set up environment variables
cp .env.example .env.local
# Edit .env.local and add your OPENAI_API_KEY
# 3. Run development server
npm run dev
# Push to Git
git add . && git commit -m "Update" && git push
# Render will auto-deploy
- The application loads with prebuilt sample data for immediate exploration
- Navigate between different views using the sidebar
- Interact with charts and visualizations to explore data insights
- Go to the Upload view from the sidebar
- Select a CSV file containing your transaction data
- Map your columns to the required fields (category, purchase amount, date, customer ID)
- The application will process your data and update all visualizations
- RFM Analysis: Recency, Frequency, Monetary analysis for customer segmentation
- Clustering: Unsupervised learning to identify customer groups
- Affinity Rules: Market basket analysis to discover product relationships
- Predictive Models: Revenue forecasting with confidence intervals
├── app/ # Next.js app router pages
├── components/ # Reusable UI components
│ ├── ui/ # Base UI components (buttons, cards, etc.)
│ └── views/ # Page-level components
│ ├── error-boundary.tsx # Error handling
│ └── theme-provider.tsx # Theme management
├── lib/ # Shared utilities and business logic
│ ├── store.ts # Zustand store for state management
│ ├── types.ts # Type definitions
│ ├── behavior-analysis.ts # Shopper behavior algorithms
│ └── data-processing.ts # Data processing utilities
├── public/ # Static assets
├── styles/ # Global styles
├── .env.example # Environment variables template
├── render.yaml # Render deployment config
└── DEPLOYMENT.md # Deployment guide
graph TD
A[User Interface] --> B[Next.js App Router]
B --> C[Zustand Store]
C --> D[Data Processing Layer]
D --> E[Business Logic Components]
E --> F[UI Components]
G[CSV Upload] --> H[Data Validation]
H --> I[Data Cleaning]
I --> J[Feature Engineering]
J --> K[Analysis Engine]
K --> L[RFM Analysis]
K --> M[Clustering Engine]
K --> N[Affinity Analysis]
K --> O[Forecasting Model]
L --> P[Visualization Layer]
M --> P
N --> P
O --> P
P --> Q[Dashboard Views]
Q --> R[User Interface]
S[AI Assistant] --> T[Chat API]
T --> U[LLM Integration]
U --> V[Response Generation]
V --> R
W[Settings Management] --> X[Configuration Store]
X --> C
flowchart LR
A[User Input] --> B[Frontend Components]
B --> C[Zustand State Management]
D[CSV File Upload] --> E[File Validation]
E --> F[Data Parsing]
F --> G[Column Mapping]
G --> H[Data Cleaning]
H --> I[Feature Extraction]
I --> J[Data Transformation]
J --> K[Processed Dataset]
K --> L[RFM Calculation]
K --> M[Clustering Analysis]
K --> N[Affinity Rules]
K --> O[Time Series Forecasting]
L --> P[Segmentation Results]
M --> Q[Cluster Assignments]
N --> R[Association Rules]
O --> S[Forecast Predictions]
P --> T[Visualization Engine]
Q --> T
R --> T
S --> T
T --> U[Dashboard Components]
U --> V[User Interface]
W[AI Chat Requests] --> X[API Processing]
X --> Y[LLM Integration]
Y --> Z[Response Generation]
Z --> V
graph TD
A[User Authentication] --> B[Session Management]
B --> C[Route Protection]
D[Input Validation] --> E[Data Sanitization]
E --> F[API Security Layer]
F --> G[Server-Side Validation]
G --> H[Response Sanitization]
I[Environment Security] --> J[Secrets Management]
J --> K[Configuration Validation]
L[Client-Side Security] --> M
▸ 展开全文