OpenTrade

Automated crypto research and market intelligence for traders and analysts.

OpenTrade helps you scan the market, run deep diligence on any token, turn fragmented crypto data into portfolio-ready investment memos, and deploy a live agent. Use it to research a single asset, build thesis-driven screens, compare relative-value trades, or construct custom portfolios.

What You Can Do

• Research any token — generate an institutional-style memo with fundamentals, technicals, news, sentiment, risks, catalysts, and a trade plan.
• Scan the market — find deep value, cashflow yield, AI exposure, momentum breakouts, oversold quality, or unlock-short candidates.
• Build custom portfolios — create baskets by asset class, sector, theme, valuation, liquidity, or risk profile.
• Compare relative value — use category and competitor analysis to frame pair trades or long/short ideas.
• Track thesis changes — rerun research or add follow-up analysis when governance, tokenomics, news, or market structure changes.
• Audit the reasoning — inspect analyst reports, scoring, debate, risk review, and final portfolio-manager memo.
• Deploy an agent — validate a portfolio and its guardrails, then run it in paper or live mode with explicit controls around live capital.

How It Works

OpenTrade mirrors an institutional trading desk with specialized AI agents working in sequence:

ANALYST TEAM → RESEARCHER DEBATE → TRADER → RISK ANALYSIS → INVESTMENT MEMO

Phase 1 — Analyst Team (4 default agents, each with crypto-specific tools)

• Fundamentals Analyst — Market cap vs FDV, TVL, protocol revenue, on-chain valuation (MVRV, NVT), value accrual, fee switch/buyback/burn mechanics, token dilution, and competitive positioning
• Technical Analyst — Murphy-methodology top-down analysis: Dow Theory trend structure, MA crossovers (golden/death cross), swing-based S/R, Fibonacci retracements, RSI/MACD divergence detection, volume confirmation, plus standard indicators (RSI, MACD, Bollinger Bands, ATR, ADX, Stochastic RSI)
• News Analyst — Protocol upgrades, security incidents, hack history, governance proposals (full Discourse content)
• Sentiment Analyst — Crypto Twitter discourse, community metrics, developer activity (GitHub + Electric Capital)

Phase 2 — Researcher Debate (adversarial)

• Bull Researcher — Network effects, token utility, growth catalysts
• Bear Researcher — Smart contract risk, dilution, regulatory risk, centralization
• Debate runs 1-3 rounds, then Research Manager synthesizes

Phase 3 — Trading Decision

• Trader Agent — Synthesizes all inputs into a recommendation

Phase 4 — Risk Analysis (3-way debate)

• Aggressive, Conservative, and Neutral risk analysts debate the trader's recommendation

Phase 5 — Investment Memo

• Portfolio Manager — Final structured output modeled on institutional research standards (10 sections, conviction scoring, trade plan with entry/target/stop)

Scanner Mode — Before running full memos, use YAML-defined screens in screens/ via scripts/run_screen.py or the opentrade-scanner skill to find candidates such as deep value, oversold quality, statistical mean reversion, cashflow yield, AI exposure, momentum breakouts, or unlock shorts. Scanner output includes ranked candidates and ready-to-run research commands.

Agent Deployment — Validate the portfolio, strategy, and guardrails before pushing an agent. Live deployment requires explicit approval, venue credentials added through the OpenTrade dashboard, and passing live safety checks.

Data Sources

Source	Data	Access
CoinGecko	Price, OHLCV, market cap, supply, community metrics	Managed beta connector
DefiLlama	TVL, protocol revenue, fees, DEX volume, stablecoin TVL, hacks	Managed beta connector
CoinMetrics	Network data, active addresses, transaction count, market cap, supply	Managed community connector
Tavily	Web search for news, security incidents, tokenomics, and competitive context	Managed beta connector
Token Terminal	Financial metrics, revenue, fees, users, statements	Optional self-hosted connector
Tokenomist	Unlocks, emissions, allocations, buyback/burn	Optional self-hosted connector
Nansen	Smart money signals (accumulation/distribution)	Optional self-hosted connector
Electric Capital	Ecosystem developer metrics	Open dataset
ta	Technical indicators	Computed locally
Governance Forums	Full Discourse topic content	Public APIs

Quickstart

1. Install OpenTrade

Install the CLI and OpenTrade skills:

pipx install --python 3.13 --fetch-python=missing useopentrade
opentrade setup install-skills
opentrade setup check
opentrade login

If pipx rejects --fetch-python, upgrade pipx and retry. Use opentrade auth-status to see the active control plane; change it by rerunning opentrade --base-url <api-url> login with a key for that target.

opentrade login connects the CLI and MCP server to your OpenTrade dashboard account. You can also paste the following into Claude Code, Codex, or Cursor to have your agent complete setup:

A beta setup prompt supplies its isolated API target during login; the CLI persists that target for later CLI and MCP commands.

Set up https://opentrade.money/setup.md

See SETUP.md for MCP registration, manual installation, and troubleshooting.

2. Research an asset or scan the market

Run a full research memo:

opentrade research bitcoin --depth standard --output ./bitcoin-memo.md

Or scan the supported universe before choosing what to research:

opentrade scan --max-tokens 20

For thesis-driven work, use guided mode:

opentrade guided "Find deep-value crypto assets with active development" --confirm

3. Use the hosted API and deploy an agent

The CLI calls the hosted OpenTrade API by default. When you have a reviewed portfolio_decision.json and guardrails.json, validate them and create an Agent Bundle:

opentrade portfolio validate ./portfolio_decision.json --require-stops
opentrade bundle create \
  --name my-agent \
  --portfolio ./portfolio_decision.json \
  --guardrails ./guardrails.json \
  --output ./agent_bundle

Review the generated strategy before approving and deploying it:

cat ./agent_bundle/strategy.md
opentrade bundle approve-strategy ./agent_bundle
opentrade bundle validate ./agent_bundle
opentrade agent push --bundle ./agent_bundle --mode live

Live deployment requires explicit approval, credentials stored through the dashboard, policy checks, reconciliation, audit logging, and tested emergency controls. Use --mode paper to deploy with virtual capital instead.

Local API development

You only need to run the API server when developing or self-hosting OpenTrade:

uvicorn api.main:app --reload --port 8000
OPENTRADE_API_URL=http://localhost:8000 opentrade research bitcoin

Project Structure

opentrade/
├── skills/                    # Codex, Claude Code, and compatible agent skills
├── research/
│   ├── agents/                # Analyst, debate, risk, and portfolio-manager pipeline
│   ├── dataflows/             # Market, on-chain, news, and developer data
│   ├── graph/                 # Research orchestration
│   ├── planning/              # Guided workflow planning
│   ├── bundles/               # Agent Bundle creation and validation
│   └── runtime/               # Paper and guarded-live execution
├── cli/                       # `opentrade` command-line interface
├── api/                       # FastAPI, control plane, runtime routes, and MCP server
├── app/                       # Next.js routes and product pages
├── components/                # Product and marketing UI
├── screens/                   # YAML-defined market screens
├── scripts/                   # Research and screening utilities
└── tests/

License

This project is a fork of TradingAgents, licensed under the Apache License 2.0.

---

This software is for research purposes only and does not constitute financial or investment advice.