ai-agent

HFTFramework: Boost Market Making

Name: HFTFramework: Boost Market Making
Author: javifalces

Improve market making performance with HFTFramework, a research-backed tool for founders in high-frequency trading.

From the repo · “HFTFramework utilized for research on " A reinforcement learning approach to improve the performance of the Avellaneda-Stoikov market-making algorithm " ”

advanced⏱ 1-2 hours💵 Free (self-hosted)

308 stars+1★ this week64 forksJupyter NotebookGuide quality 8/10 · reviewed Jul 1Updated 10/18/2026100% free · open source

What it is

Use HFTFramework to create algorithms that make markets more efficiently.

Real use case example

"A founder wants to improve the performance of their high-frequency trading system. They use HFTFramework to implement a reinforcement learning approach to the Avellaneda-Stoikov market-making algorithm. Within a few hours, they've optimized their system to execute trades more efficiently."

Best insideClaude DesktopClaude Code

When to use it

•When you need to optimize market making strategies for high-frequency trading
•When researching reinforcement learning applications in finance
•When looking to improve the performance of the Avellaneda-Stoikov algorithm

Ready-to-paste prompt

Run the `python train.py --env=stock_exchange --agent=rl_agent` command to start training the reinforcement learning model for a stock exchange environment

Heads up: Make sure you have the required Python libraries installed, including `numpy`, `pandas`, and `gym`, and that your Jupyter Notebook is configured to run the necessary dependencies

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/hftframework && curl -fsSL https://workflowstacks.com/api/skills/hftframework/claude-skill -o ~/.claude/skills/hftframework/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

415.4M

source size

Apache-2.0

license

Key files

AGENTS.md

README.md

File tree

.github/

data/

docs/

fig/

java/

monitoring/

python/

.gitignore

AGENTS.md

CITATION.cff

LICENSE

README.md

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/hftframework && curl -fsSL https://workflowstacks.com/api/skills/hftframework/claude-skill -o ~/.claude/skills/hftframework/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

javifalces

Language

Jupyter Notebook