agno-agi

agno-agi / investment-team

Public

Multi-agent investment team powered by Agno and Gemini — 7 AI analysts collaborate across 5 architectures to deploy a $10M equity portfolio

101
23
100% credibility
Found Feb 20, 2026 at 60 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

An AI-powered simulation of a collaborative investment team with specialized analysts that evaluate stocks, assess risks, and recommend portfolio allocations through various team coordination patterns.

How It Works

1
📰 Discover the AI Investment Team

You find this cool project online that lets a group of smart AI helpers act like a team of stock experts to analyze investments.

2
📥 Bring it to your computer

Download the project files to your own computer so you can set it up at home.

3
🔗 Connect the smart thinkers

Link up AI services so your team of analysts can think, search news, and pull stock data.

4
▶️ Wake up the team

Start everything with a quick launch, and it prepares a memory spot for research.

5
📚 Add research wisdom

Load company profiles and industry reports into the team's shared knowledge so they have background info.

6
🌐 Open the friendly dashboard

Visit a simple web control panel online, add your local team, and connect it up easily.

7
💬 Chat with your analysts

Ask questions like 'Should we buy NVIDIA?' or 'Build a $10M portfolio' and watch the team collaborate.

📈 Get investment wisdom

Your AI team delivers full reviews, risk checks, memos, and clear buy/sell decisions with dollar amounts ready to use.

Sign up to see the full architecture

6 more

Sign Up Free

Star Growth

See how this repo grew from 60 to 101 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is investment-team?

This Python project deploys a multi-agent investment team powered by Agno and Gemini models, where seven AI analysts—covering market trends, fundamentals, technicals, risk, knowledge retrieval, memo writing, and final decisions—collaborate to build and manage a simulated $10M equity portfolio. It automates stock evaluation, portfolio allocation, and investment memos through five user-selectable team modes (dynamic orchestration, routing, broadcasting, task decomposition) plus a fixed pipeline workflow. Developers get a Dockerized API with Postgres-backed RAG knowledge base, YFinance data pulls, and Exa web search, all connectable to a web UI for instant queries like "Deploy $10M across top AI stocks."

Why is it gaining traction?

Unlike basic langgraph multi agent github repos or single-model scripts, it showcases a full multi agent investment platform with real-world finance tools and multiple orchestration patterns—like parallel analyst broadcasts or autonomous task teams—making multi agent github code tangible for finance apps. The quick-start Docker setup and preloaded research library let users skip boilerplate, while seed memos and conviction-scored outputs hook experimenters building investment team assistants or prototyping multi agent orchestration github copilot flows.

Who should use this?

AI engineers prototyping multi-agent systems for finance, quant devs testing investment team structures without hiring a real team, or indie builders creating investment team intern tools for stock screening and private equity analysis. Ideal for those exploring multi agent ppo github or multi-agent-pathfinding github ideas in a domain-specific context like portfolio risk management.

Verdict

With 38 stars and a 1.0% credibility score, it's early-stage but shines through solid docs, one-command setup, and deployable demos—fork it for multi agent investment experiments rather than production. Maturity lags in tests and scale, but the structured output makes it a practical learning tool. (198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.