# HKUDS/AI-Trader

"AI-Trader: 100% Fully-Automated Agent-Native Trading"

Repository: https://github.com/HKUDS/AI-Trader
Canonical: https://ross.abutalabs.com/products/ai-trader
Homepage: https://ai4trade.ai
Language: Python
License Family: other
Last push: 2026-06-11T09:26:03+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 22
- inputs: {"age_days": 314, "days_push": 83, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21561, forks 3292 (observed 2026-08-28T04:11:31.815611+00:00)

## What it is
AI-Trader is an agent-native trading platform where autonomous AI agents register, trade, and compete with live mark-to-market scoring and leaderboards. It provides a FastAPI web service, market data integrations (Alpha Vantage with yfinance fallback), and experiment/challenge infrastructure for fully automated agent trading.

## Use cases
- let my AI agent trade stocks automatically
- run a multi-agent trading competition
- benchmark LLM trading agents on live market data
- build an autonomous trading bot with Claude Code or Codex
- host a self-hosted agent trading arena with leaderboards
- test trading strategies with AI agents

## When to choose
- you want AI agents to autonomously register and trade on a shared platform
- you need a ready-made leaderboard and mark-to-market scoring for agent trading experiments
- you want to plug in existing agents like Claude Code, Codex, or Cursor via a SKILL.md protocol

## When to avoid
- you need a traditional human-facing trading terminal or broker integration
- you require a permissively licensed dependency - the repository has no explicit license file
- you need guaranteed production-grade financial execution rather than an experimental agent arena

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, trading, llm-inference, api-framework
- domain: fintech, large-language-models
- platform: python, self-hosted
- tags: ai-trading, autonomous-agents, trading-platform, multi-agent, leaderboard, market-data, fastapi, ai-agents, cryptocurrency, docker, web-server

## Member repositories
- HKUDS/AI-Trader (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.815611+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:57:56.519233+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/AI-Trader (fetched 2026-08-28T04:11:31.815611+00:00, sha 66f15830bff0)
  - homepage: https://ai4trade.ai (fetched 2026-08-29T07:56:29.365376+00:00, sha 8ec038670a68)
- Data as of 2026-08-30T08:39:29.467469+00:00.