Credentials. Your LLM and data keys are stored in the app, so protect the machine it runs on.
Who it is forAn analyst who wants AI agents to draft research inside the same app that holds the data.
The problemCopying data between a terminal and a chatbot loses context and wastes time.
The outcomeAgent research inside the terminal, billed to your own LLM account or run locally.
What you need first
- Windows x64, Linux x64 or macOS on Apple Silicon
- Your own LLM API key (OpenAI, Anthropic, Gemini, Groq, DeepSeek, OpenRouter) or Ollama for the AI agents
- Optional API keys for paid data connectors
Steps
- Install the terminal as above
- Add your LLM key (OpenAI, Anthropic, Gemini, Groq, DeepSeek or OpenRouter) or point it at Ollama
- Pick one of the trader, investor, economic or geopolitics agents and give it a research question
- Watch your provider's usage page while you test
Prompt for your agent
In Fincept-Corporation/FinceptTerminal, configure <provider or Ollama> and run an investor agent on <question about a company>. Summarise its answer and estimate the token cost of the run.
Caveat. The README warns the open build's real cost is your own data and LLM bills, charged per token with no ceiling. Not financial advice: paper trade first, and remember you can lose money.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Fincept-Corporation/FinceptTerminal and "Research markets with 37 AI agents on your own key"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer