catalog / Finance / FinRobot — AI Agent Platform for Finance
AgentFinanceFree

FinRobot — AI Agent Platform for Finance

AI4Finance Foundation's multi-agent platform for financial tasks — market forecasting, report generation, portfolio management, and earnings analysis.

Installations34k
⟳ upstream desktop-v0.1.0 · updated 2mo ago
Dépôt source
! Grade B · 75/100 · ReviewSecurity assessment
No compromise signals20capabilities surfaced1known CVE5of 20 OWASP controls clear
External endpoints declaredSuspicious code patternsSuspicious network referencesBroad capability surface
scanned 2mo agoosv · gitleaks · opengrep · picklescan + heuristicsfull breakdown in the Security tab ↓

FinRobot — AI Agent Platform for Finance

FinRobot is an open-source AI agent framework purpose-built for financial applications. It provides a multi-layer architecture: a Smart Scheduler orchestrates specialised financial agents (market forecasters, report generators, earnings analysts, risk managers) that share a common toolset — data connectors, LLM adapters, and quantitative utilities.

Key Features

  • Pre-built financial agents: CIOAgent, PortfolioManagerAgent, ForecasterAgent, ReportWriterAgent
  • Integrates with AutoGen, LangChain, and custom agent loops
  • Data connectors: Yahoo Finance, SEC EDGAR, FRED, Bloomberg (via SDK)
  • LLM backends: OpenAI, Anthropic, local models via Ollama
  • Automated 10-K / 10-Q narrative analysis and financial report generation

Quick Start

from finrobot.agents import ForecasterAgent
from finrobot.data_source import YFinanceData

data = YFinanceData().fetch("NVDA", start="2023-01-01", end="2024-12-31")
agent = ForecasterAgent(llm="gpt-4o", horizon_days=30)
forecast = agent.run(data)
print(forecast.summary)
npx ai-supply add finrobot-ai-finance-agent

Curated mirror of the open-source FinRobot (Apache-2.0). Get it from the source.

More from @ai-supply

View profile →
Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
1.0M
Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
892k
Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
811k
Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
784k