AIAny
AI Agent2024
Icon for item

Polymarket Agents

Developer framework for building AI agents that autonomously trade on Polymarket prediction markets. Bundles the Polymarket and Gamma APIs, a Chroma RAG layer that pulls in news, and a CLI to query markets, reason with an LLM, and execute trades.

Introduction

Prediction markets turn every news event into a tradeable probability, which makes them an unusually clean playground for LLM agents: the job is to read the world faster than the crowd and price it. The hard part was never the reasoning — it's the plumbing around it. This is Polymarket's own reference scaffold for that plumbing, wiring market data, fresh news, retrieval, and on-chain execution into a single agent loop you can drive from the command line.

What Sets It Apart
  • Bundles the official Polymarket order client and the Gamma metadata API, so an agent can list live markets and place USDC trades without reverse-engineering the exchange — the integration most hobby bots get wrong.
  • Ships a RAG layer (Chroma, local or remote) that ingests news, betting-service feeds, and web search, so the model reasons over current events instead of stale training data — the actual edge in event forecasting.
  • Centers everything on a single cli.py: querying a market, pulling related news, sending a prompt to the LLM, and executing a trade are each one command away, making it a readable starting template rather than a black box.
Who It's For

Great fit if you want to prototype an autonomous Polymarket strategy and would rather extend a working data-plus-execution skeleton than build API clients from scratch. Look elsewhere if you need a maintained product or a proven money-maker: the repo is an archived reference (read-only since May 2026), it carries no trading edge of its own, and Polymarket itself restricts US persons and some jurisdictions from trading.

More Items

Hugging Face
AI Model2026

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

GitHub
AI Agent2026

A curated collection of production-ready Agent Skills that turn tasks—presentation production, image generation, local KB retrieval, article assembly, and web-design—into agent-loadable skill folders. Uses a SKILL.md contract, supports multiple agent runtimes (Claude Code, Cursor, Codex), and offers modular install paths with pinned release zips.

GitHub
AI Agent2026

Provides a ruleset and skills that make AI coding agents prefer the simplest correct implementation: reuse existing code, prefer stdlib/native features, and only write minimal new code. Cuts generated LOC, tokens, cost and time while preserving validation and safety.