#7474th of 80 in Agent platformsFor finance and business, trading, stocks and crypto, finance and accounting
ai-market-maker
LangGraph multi-agent crypto trading stack with a Risk Guard veto
- Stars
- 2.1k
- License
- AGPL-3.0
- Last commit
- Aug 2026
- Language
- Python
565 on 21 Apr 20262,110 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Runs specialist LLM trading desks (technical, macro, news, pattern, statistical) through a LangGraph workflow, fuses their signals with weighted math, and sends proposals through a Risk Guard veto before execution on Binance Testnet. It includes a bar-by-bar perp backtester with buy-and-hold benchmarks, pinned historical data with a sha256 manifest, and a Next.js dashboard backed by Postgres.
Who it is for: Quant-minded developers researching LLM-driven crypto trading strategies
Strengths
- Risk Guard has final veto before any trade executes
- Pinned data/ with sha256 manifest allows offline --csv-only backtests
- Every backtest reports Sharpe, Sortino, profit factor and buy-and-hold excess return
- Strategy lives in deploy JSON; .env holds secrets only
Weaknesses
- Agentic mode and backtests require an OpenAI or Atlas Cloud API key
- LLM path dependence means backtest re-runs are not bit-identical
- Execution limited to Binance Testnet; Hyperliquid adapter is dry-run only
- TA-Lib C library must be installed separately for CLI use
What it needs
- no GPU
- Docker + Compose
- Needs Docker Compose, PostgreSQL, TA-Lib, Binance Testnet API keys, OpenAI or Atlas Cloud API key
- Models: OpenAI-compatible API, Atlas Cloud
- port 3000
Quick answers
Is ai-market-maker open source?
Yes. Its code is on GitHub under the AGPL-3.0 license.
Can you run ai-market-maker with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does ai-market-maker need a GPU?
No, it runs without one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |