AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Data Processing/
QuantDinger
QuantDinger logo

QuantDinger

Active·★ 13.2k·Apache-2.0·Updated 2026-10-27
★ Most Popular★ Trending

QuantDinger calls itself an open-source AI Trading OS for independent traders, Python strategy authors and small teams. The flow runs from AI research to strategy code, backtest, paper or live execution and monitoring, all in one self-hosted stack that keeps market data, strategy code, broker credentials and deployment under the operator's control. It is a product of Open Byte Inc., and the README says it is not a black-box signal service.

It combines multi-provider AI market research, Python indicators and a Strategy API V2, server-side backtesting, paper and live execution across crypto exchanges and traditional brokers, and access through web, mobile H5, a human API, an Agent Gateway and MCP. Version 5 separates the HTTP API from trading, scheduler, Celery and migration processes, uses separate Redis instances for cache and durable jobs, and offers JSON logs, request IDs, Prometheus metrics and alert rules. Run it from prebuilt Docker images or from a source checkout. The README warns that it can submit real orders when live trading is enabled, recommends starting with paper trading and restricted API keys, and states it provides no investment advice.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-24.

License
Apache-2.0
Latest release
v5.7.3 · 2026-10-24
Last commit
2026-10-24
Contributors
33
Forks
2,662
Open issues and PRs
29
First published
2025-12-28

Source: GitHub, npm and PyPI public APIs.

#AI Trading#Algorithmic Trading#Backtesting#Python#Docker#Financial Automation#Multi-Agent Systems#Observability
$ Install
$ curl -fsSL https://raw.githubusercontent.com/OpenByteInc/QuantDinger/main/install.sh | bash
↗ Visit site★ GitHub
01

Features

01Multi-provider AI market research and analysis
02Python indicator and Strategy API V2 development
03Server-side backtesting and experiment workflows
04Paper and live execution across crypto exchanges and traditional brokers
05Web, mobile H5, human API, Agent Gateway, and MCP access
02

Why choose it

+Covers the whole loop from AI research and strategy code to backtests, paper trading, live execution and monitoring.
+Self-hosted and local-first, so strategy code, data and broker credentials stay with you.
+Offers several access paths: web, mobile H5, human API, Agent Gateway and MCP.
+v5 separates API, trading and scheduler processes, with audit logs, Prometheus metrics and alert rules.
03

Trade-offs

!It can submit real orders once live trading is enabled, so losses are possible; the README advises paper trading and restricted API keys first.
!The project provides no investment advice, and compliance requirements depend on your jurisdiction.
!The v5 architecture (separate workers, PostgreSQL, two Redis instances, optional observability) is more than a small script to run and maintain.
05

Maintenance check

ActiveChecked: 2026-10-24
Last commit
2026-10-24
Commits, last 90 days
100+
Releases, last 90 days
30
Latest release
v5.7.3 (2026-10-24)
Open issues
29
Recent issues with at least one comment
2/7
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 4, 1, 7, 8, 26, 32, 53, 22, 21, 4, 21, 45

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #179 Proposal: benchmark-relative Information Ratio for fixed-income fund analytics6 comments · 2026-07-19
  • #266 Use Laya as an alternative to Jev4 comments · 2026-09-28
  • #257 [Roadmap] Portfolio research and execution roadmap2 comments · 2026-09-18
  • #258 [RFC] Define point-in-time universe contract and snapshot model1 comments · 2026-09-18
  • #245 之前版本生产的策略不会指定标的，更新后总是固定标的MSFT，怎么回事1 comments · 2026-09-15

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

04

Who it fits

Pick it if
  • You write Python strategies and want research, backtests, paper trading, live execution and monitoring in one self-hosted stack.
  • Broker credentials, strategy code and market data must stay under your control.
  • You want several access paths: web, mobile H5, API, an Agent Gateway and MCP.
Look elsewhere if
  • You want a small script: v5 runs separate workers, PostgreSQL and two Redis instances.
  • You only want an assistant to look up quotes: a single MCP server is far lighter.
  • You would enable live trading before testing on paper with restricted API keys.
06

How it differs

alpaca-mcp-server logovs alpaca-mcp-server★ 1.0k

Alpaca's server lets an assistant trade through one broker directly. QuantDinger adds strategy code, backtests and monitoring around execution.

Full comparison →
tradememory-protocol logovs tradememory-protocol★ 1.4k

TradeMemory records what trades happened and why, as memory for an agent. QuantDinger is the platform that runs strategies.

Full comparison →
07

Compatibility

Python
Runtime
Verified via docs
Docker
Containerization
Verified via docs
PostgreSQL
Database
Verified via docs
Redis
Cache/Job Queue
Verified via docs
Linux
Operating System
Verified via docs
macOS
Operating System
Verified via docs
08

Quick start

1
$ curl -fsSL https://raw.githubusercontent.com/OpenByteInc/QuantDinger/main/install.sh | bash
09

Use cases

↳Automating trading strategy development and deployment
↳Conducting server-side backtests and experiments for Python trading strategies
↳Executing paper and live trades across various crypto and traditional brokers
↳Utilizing AI for market research and integrating multi-agent trading systems
↳Self-hosting a complete trading stack for enhanced control over data and credentials
10

Alternatives

⚡Top VS:
VSalpaca-mcp-server★1.0k→VStradememory-protocol★1.4k→VSpolymarket-mcp-server★728→VSoracle3-prediction-market-agent★527→
alpaca-mcp-server logo
alpaca-mcp-server★ 1.0k
Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs
VSCompare→
tradememory-protocol logo
tradememory-protocol★ 1.4k
Memory layer for AI trading agents. Outcome-weighted recall, autonomous strategy evolution, 15 MCP tools.
VSCompare→
polymarket-mcp-server logo
polymarket-mcp-server★ 728
🤖 AI-Powered MCP Server for Polymarket - Enable Claude to trade prediction markets with 45 tools, real-time monitoring, and enterprise-grade safety features
VSCompare→
oracle3-prediction-market-agent logo
oracle3-prediction-market-agent★ 527
Oracle3: paper-trading engine and MCP server for prediction markets (Kalshi, Polymarket). Checks no-arbitrage constraints across related event contracts net of each venue's fees, under pre-trade risk limits. 13 MCP tools, JSON CLI, agent skills, 600+ tests.
VSCompare→
datagouv-mcp logo
datagouv-mcp★ 1.6k
Official data.gouv.fr Model Context Protocol (MCP) server that allows AI chatbots to search, explore, and analyze datasets from the French national Open Data platform, directly through conversation.
VSCompare→
excel-mcp-server logo
excel-mcp-server★ 4.3k
A Model Context Protocol server for Excel file manipulation
VSCompare→
FinnewsHunter logo
FinnewsHunter★ 1.5k
FinnewsHunter: Multi-agent financial intelligence platform powered by AgenticX. Real-time news analysis, sentiment fusion, and alpha factor mining.
VSCompare→
wisp-science logo
wisp-science★ 1.1k
Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.
VSCompare→
See all alternatives →

Featured in these lists

  • Open-Source AI Trading and Finance Tools

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06How it differs07Compatibility08Quick start09Use cases10Alternatives
OpenByteInc /
QuantDinger
↗

Self-hosted AI trading OS: strategies, backtests, paper and live execution

13.2k2.7kApache-2.0
Last commit1d ago
StatusActive
CategoryData Processing
Contributors33
Latest releasev5.7.3
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.