Open-Source V1.0 Launch

Forecast AIMulti-Agent Intelligence Infrastructurefor Prediction Markets.

Deploy specialized agents to crawl news, extract sentiment, and analyze prediction markets (Kalshi & Polymarket). Aggregate output using our Bayesian Consensus Engine and hand off trades via Robinhood's Agentic Trading MCP.

$FORAI
Contract Address (CA)0xcc9c1ec224c3824ae5ea699ec72ef5fad4165e49

Built for Robinhood Predict

Native design for Robinhood's prediction market product.

Powered by AI Agents

Collaborative consensus over single model bias.

Open Source Infrastructure

Fully audit-ready, secure, and self-hosted.

Multi-Venue Data Coverage

Real-time market feeds from Kalshi & Polymarket.

Robinhood MCP Hand-off

Execution hand-off via Robinhood Agentic Trading MCP.

Core Capabilities

An intelligence layer engineered for extreme prediction accuracy.

Forecast AI orchestrates isolated agent pipelines to extract evidence and continuously calibrate confidence scoring.

Multi-Agent Intelligence

Deploys specialized agents (News, Social, Macro, Market) in parallel to evaluate forecasting questions.

Consensus Engine

Aggregates independent agent probabilities based on their dynamic, historical accuracy scores.

Evidence Ranking

Evaluates information source credibility, relevance, and recency to filter noise.

Historical Memory

Utilizes vector stores to maintain contextual persistence across long-term prediction markets.

Robinhood Agentic MCP

Formats consensus forecasts into structured trade recommendations for Robinhood's official MCP endpoint.

Explainable Predictions

Generates clear, structured rationales detailing each specialized agent's confidence and findings.

Modular Providers

Flexible backend compatible with OpenAI, Anthropic, DeepSeek, or local Ollama instances.

Developer Friendly CLI

Configure models, fetch midpoints, and execute live forecasts directly from the terminal.

Professional API Server

Exposes lightweight FastAPI routes for microservice orchestration and status metrics.

100% Open Source

Free, extensible, and fully self-hostable codebase under the Apache 2.0 License.

System Architecture

End-to-End Consensus Pipeline

Watch how raw signals flow from public feeds (Kalshi, Polymarket), compile in our Multi-Agent mesh, and output structured trade recommendations via Robinhood's Agentic Trading MCP.

Consensus Engine

Pipeline Phase

Technical Modules & Feeds

  • Bayesian model averaging
  • Reputation-based confidence weight
  • Self-calibrating feedback loop

Click other components in the visualizer to explore how Forecast AI builds consensus dynamically across diverse agents.

Why Forecast AI

One LLM is not enough.

Single-prompt LLMs suffer from recency bias, lack local context, and fail to weigh contradictory evidence properly.

Forecast AI separates concern: dedicated agents collect, debate, and consensus-pool, achieving +24% Brier Score accuracy gains over vanilla GPT-4.

Phase 1: Multi-Vector Signal Harvesting

Rather than asking a model to recall facts, sources stream real-time feeds (News, Social sentiment, Kalshi & Polymarket orderbooks). Each stream is indexed by the Source Manager to guarantee zero-shot ground truths.

Phase 2: Decentralized Specialized Debate

Isolated agents receive customized system prompts representing different personas (Macro Economist, Market Analyst, Social Sentiment Expert). They generate localized predictions and present evidence.

Phase 3: Dynamic Bayesian Consensus

The Consensus Engine weighs agent inputs using historical Brier score accuracy ratings. The engine filters anomalies, scales results via Platt calibration, and yields a single probability matrix.

Phase 4: Robinhood Agentic Recommendation Hand-off

The consensus probability outputs to structured trade recommendations handed off to your own Robinhood Agentic Trading MCP session for user-controlled execution.

Multi-Venue Data

Kalshi & Polymarket Feeds.

Forecast AI continuously monitors public market feeds from Kalshi (serving as a proxy for Robinhood Predict pricing) and Polymarket as read-only market data feeds.

Kalshi public API provides real-time market data matching Robinhood Predict probabilities.

Polymarket Gamma & read-only CLOB orderbooks supply secondary liquidity and probability signals.

api.kalshi.com & polymarket
MARKETMIDPOINT
Kalshi (Fed Rate)$0.68
Polymarket (BTC 2026)$0.74
Kalshi (US CPI)$0.42
📊
Prediction Market Data Feeds
Robinhood Agentic MCP
EXECUTION FLOW
Non-CustodialUser Executed
Formats consensus forecasts into structured MCP trade recommendations. You retain full control inside your own Robinhood account session.

Agentic Trading MCP

Robinhood Agentic Execution.

Forecast AI formats probability forecasts into structured trade recommendations and hands them off for you to execute via Robinhood's official Agentic Trading MCP endpoint (https://agent.robinhood.com/mcp/trading) in your own AI client (Claude Code, ChatGPT, Cursor). Forecast AI never holds credentials or executes trades directly.

Build your own AI Forecasting System.

Get started today by cloning our repository, installing our CLI, and deploying prediction agents. Forecast AI is fully open-source.