ML-Quant
GitHub radar
What about 10,600 quant developers starred on GitHub this week. The panel is everyone who starred the FirmAI finance repos; we read a sample of their public star lists and publish only counts.
- Quant panel
- 10.6k
- Sampled
- 860
- Starred something
- 244
- Stars this week
- 1,470
GitHub radar
What the quant community starred on GitHub this week, from a panel of 10,589 developers who follow financial machine learning (244 of the 860 we checked starred something). Counts only: we never publish who starred what.
Quant repos rising
- Open-Dev-Society/OpenStock8 quants
Open-source platform for tracking real-time stock prices and company insights.
★ 19.2k+3,593 this weekTypeScript
- jarrodwatts/jev-trader4 quants
AI trading bot making one Jev trade decision per Monad block.
★ 2,395+1,462 this weekTypeScriptNew repo
Collection of 23,000+ agent skills for empirical research in social sciences.
★ 4,374+500 this weekStata
- anthropics/financial-services4 quants
Anthropic's financial services implementation.
★ 37.5k+2,589 this weekPython
- Yijia-Xiao/FinanceHarness2 quants
Autonomous financial deep research framework with agentic capabilities.
★ 176+33 this weekPythonNew repo
- caiovicentino/eikos2 quants
Calibrated typed-decision models for finance and trading applications.
★ 18+18 this weekPythonNew repo
- securo-finance/securo2 quants
Open-source self-hosted privacy-first personal finance manager.
★ 3,783+181 this weekPython
- ccxt/ccxt2 quants
Unified API for 100+ crypto exchanges and prediction markets.
★ 44.1k+123 this weekPython
What quants are playing with
- NandhaKishorM/laya28 quants
Non-autoregressive decision engine for typed choices over text in 100+ languages.
★ 24.0k+23.7k this weekPythonNew repo
- browser-use/jev-ultrafast19 quants
Fastest and cheapest web agent for automation tasks.
★ 20.1k+14.0k this weekPythonNew repo
- google/ax19 quants
Google's open agentic orchestration runtime for agent systems.
★ 11.1k+9,108 this weekGo
- jaredpalmer/kev13 quants
Decision models built on Qwen3.5/3.8 you can train locally.
★ 6,886+6,653 this weekPythonNew repo
- Contrastive-LM/CLM8 quants
Contrastive language model implementation.
★ 1,065+1,065 this weekPythonNew repo
- nokia-applied-research/AnyJev7 quants
Turn any LLM into a Jev-style decision model with typed decisions.
★ 590+590 this weekPythonNew repo
Repos the letter featured
From the letter's GitHub section, newest first.
- 20 May 202618,767shares
Turso: SQLite SQL Database
SQLite SQL Database: Turso is a SQL database that works well with SQLite.
GitHubFinanceIn No. 131
- 20 May 20263,843shares
Optimizing LLM Inference
The article focuses on improving inference proxies for large language models.
GitHubFinanceIn No. 131
- 20 May 20261,403shares
Fullstack China AShare Toolkit
A new toolkit helps AI coding assistants analyze China's A-share market.
GitHubFinanceIn No. 131
- 20 May 2026394shares
Ashare Multi-Agent Framework
A research framework uses AI agents to discuss investment strategies for the A-share market.
GitHubFinanceIn No. 131
- 20 May 2026215shares
LLMDriven Alpha Factory
An agent-based alpha factory enables LLMs to independently conduct backtests and analyze factors.
GitHubFinanceIn No. 131
- 20 May 2026187,081shares
AffaanmECC: AI Performance Optimization
AI Performance Optimization: Claude Code Codex improves AI agents' abilities by using different skills and development techniques.
GitHubTrendingIn No. 131
- 20 May 2026110shares
RiskLabAI: Advanced Risk Management
Advanced Risk Management: The article discusses how Python can be applied in financial AI applications.
GitHubTrendingIn No. 131
- 20 May 2026479shares
ViktorAxelsenMemSkill: Evolving AI Memory Skills
Evolving AI Memory Skills: MemSkill enhances AI agents' memory skills through continuous learning.
GitHubTrendingIn No. 131
- 20 May 20262,135shares
Struktoaimirage: Unified AI Filesystem
Unified AI Filesystem: The article introduces a unified virtual filesystem that boosts efficiency for AI agents.
GitHubTrendingIn No. 131
- 20 May 20262,069shares
MVanHornCliprintingPress: AI CLI with SQLite Sync
AI CLI with SQLite Sync: This tool picks out key features from rival APIs to build a better command-line interface for AI agents.
GitHubTrendingIn No. 131
- 16 Apr 20261,069shares
Alpha Stock Factors via RL
The article explores how reinforcement learning can be applied to develop stock prediction factors.
GitHubFinanceIn No. 130
- 16 Apr 202672shares
Financial Features
It compiles 300 features and factors drawn from both research and industry perspectives.
GitHubFinanceIn No. 130
- 16 Apr 202614shares
Feature Engineering for Quant
The paper outlines effective methods for feature and target engineering, utilizing a Rust core with a Python interface.
GitHubFinanceIn No. 130
- 16 Apr 202618,128shares
Science Agent Skills
It presents practical skills for agents to improve tasks in research, engineering, finance, and writing.
GitHubFinanceIn No. 130
- 16 Apr 2026159shares
Open Source AI Trading Agent
The article introduces an autonomous open-source AI trading agent capable of trading in various markets and managing risk.
GitHubFinanceIn No. 130
- 16 Apr 20261,796shares
MaalSalan Tool
A terminal tool enables users to manage spreadsheets directly from the command line.
GitHubTrendingIn No. 130
- 16 Apr 202614,939shares
JackWener OpenCLI
A platform transforms websites or apps into command-line interfaces for easy AI tool integration.
GitHubTrendingIn No. 130
- 16 Apr 202642,961shares
MemPalace AI System
A free, highly effective AI memory system has been tested successfully.
GitHubTrendingIn No. 130
- 16 Apr 202610,369shares
Caveman Token Tech
Claude Code is a new skill that minimizes token usage by using simpler language.
GitHubTrendingIn No. 130
- 16 Apr 20262,145shares
Small Fish 9M LLM
A lightweight language model, with 9 million parameters, imitates the speech of a small fish.
GitHubTrendingIn No. 130
- 3 Apr 2026239shares
NVIDIA AI Portfolio Optimization
The article provides a developer example for enhancing investment portfolios with NVIDIA's tools.
GitHubFinanceIn No. 129
- 3 Apr 2026268shares
Modular RL Trading Framework
It introduces a flexible system that uses reinforcement learning to enhance algorithmic trading strategies.
GitHubFinanceIn No. 129
- 3 Apr 20267shares
Rust Optopsy Engine Rewrite
This article covers a Rust-based update of Optopsy, a backtesting engine for options trading, featuring a new protocol.
GitHubFinanceIn No. 129
- 3 Apr 202619shares
LLM Trading System for ETFs
It highlights a paper trading system using LLM and Claude for macro ETF strategies, equipped with a secure trade ledger.
GitHubFinanceIn No. 129
- 3 Apr 20261,834shares
Apache Fluss: Real-Time Analytics
Real-Time Analytics: Apache Fluss is presented as a real-time data analytics solution for streaming storage.
GitHubFinanceIn No. 129
- 3 Apr 2026145,323shares
Repo Ownership Transfer
The repository is locked for ownership transfer; users are redirected to a faster alternative to reach 100K stars.
GitHubTrendingIn No. 129
- 3 Apr 202641,232shares
Rust Rebuild of Claude
Better Harness Tools aims to archive leaked Claude Code and is being rewritten in Rust for better functionality.
GitHubTrendingIn No. 129
- 3 Apr 20267,868shares
Enhance Codex
OmX Oh My codeX upgrades your codex with new features including hooks, agent teams, and HUDs.
GitHubTrendingIn No. 129
- 3 Apr 20262,527shares
Terse CLAUDE.md Workflows
The CLAUDE.md file simplifies responses by keeping them brief without requiring code changes.
GitHubTrendingIn No. 129
- 3 Apr 2026314shares
Cognitive Architecture for Claude
The article describes a cognitive architecture for Claude Code that includes persistent memory, self-reflection, and foresight.
GitHubTrendingIn No. 129
- 4 Mar 202678shares
VectorBT Trading Skills
VectorBT provides tools for testing trading strategies with realistic costs and templates.
GitHubFinanceIn No. 128
- 4 Mar 20263,926shares
HTML & Slide Agent
An agent skill that generates HTML pages or presentations for project documentation.
GitHubFinanceIn No. 128
- 4 Mar 20261,266shares
AI Options Research Library
An AI-powered Python library designed for options research and backtesting.
GitHubFinanceIn No. 128
- 4 Mar 2026622shares
Code Review Database
A system that continuously reviews code to improve agent productivity and responsibility.
GitHubFinanceIn No. 128
- 4 Mar 20265,505shares
AlphaEvolve Implementation
An open-source version of AlphaEvolve is now accessible for users.
GitHubFinanceIn No. 128
- 4 Mar 20263,824shares
Anthropics Plugins
The Allinone AI framework toolkit provides an extensive solution for different AI projects.
GitHubTrendingIn No. 128
- 4 Mar 20263,037shares
Mindfold Toolkit
A new stealthy rootkit targets and compromises modern Linux kernels.
GitHubTrendingIn No. 128
- 4 Mar 20261,463shares
MatheuZ Rootkit
OpenClaw introduces an easy-to-use web dashboard to better manage agents and improve shipping speed.
GitHubTrendingIn No. 128
- 4 Mar 20261,294shares
OpenClaw Dashboard
GitHub Copilot CLI enables users to use Copilot's coding features directly in the terminal.
GitHubTrendingIn No. 128
- 12 Feb 2026693shares
Prediction Market Framework
A new framework gathers and analyzes data from prediction markets, featuring extensive datasets from Polymarket and Kalshi.
GitHubFinanceIn No. 127
Papers with code
Papers whose code the letter pointed to.
- 20 May 2026219shares
SkillsVote: Governance for Agent Skills
Governance for Agent Skills: SkillsVote is a system that helps long-term AI agents manage and improve their skills over time.
Papers with codeTrendingIn No. 131
- 20 May 2026101shares
MMSkills: Multimodal Skills for Agents
Multimodal Skills for Agents: Multimodal procedural knowledge frameworks enhance visual agents by merging text and visuals for improved decision-making.
Papers with codeTrendingIn No. 131
- 20 May 202659shares
SelfDistilled RL: Enhancing Training with Self-Distillation
Enhancing Training with Self-Distillation: SDAR optimizes training for multiturn agents in reinforcement learning by boosting positive feedback and minimizing negative feedback.
Papers with codeTrendingIn No. 131
- 20 May 202648shares
AI Research Trust
AI excels in structured tasks but needs human oversight in scientific research to handle new ideas and judgment effectively.
Papers with codeRisingIn No. 131
- 20 May 202642shares
Olympiad Reasoning Scaling
A new systematic approach boosts reasoning models, making them top contenders in math and physics competitions through advanced learning methods.
Papers with codeRisingIn No. 131
- 20 May 202633shares
Dynamic NPC Steering
ReactiveGWM improves game play by separating player controls from NPC actions, enhancing strategic options in various games.
Papers with codeRisingIn No. 131
- 20 May 202631shares
DexJoCo for Manipulation
DexJoCo provides a benchmark and toolkit for evaluating dexterous manipulation skills, along with a budget-friendly data collection system.
Papers with codeRisingIn No. 131
- 16 Apr 2026376shares
SkillClaw: Skill Evolution
Skill Evolution: SkillClaw enhances multiuser AI systems by leveraging group interactions to strengthen shared abilities.
Papers with codeTrendingIn No. 130
- 16 Apr 2026367shares
ClawGUI: Unified GUI
Unified GUI: ClawGUI is an open-source tool that streamlines the development of GUI agents using unified reinforcement learning across different platforms.
Papers with codeTrendingIn No. 130
- 16 Apr 2026200shares
DDTree: Speculative Decoding
Speculative Decoding: DDTree improves speculative decoding by generating draft trees from data distributions and validating multiple paths at once.
Papers with codeTrendingIn No. 130
- 16 Apr 202655shares
Strips as Tokens
SATO introduces a new way to order tokens in transformers that improves mesh generation by preserving edge flow using triangle strip sequences.
Papers with codeTrendingIn No. 130
- 16 Apr 202653shares
Introspective Consistency
Introspective Diffusion Language Models enhance autoregressive models by refining their output consistency through advanced decoding and optimized methods.
Papers with codeTrendingIn No. 130
- 16 Apr 202646shares
HabitatGS Navigation
HabitatGS enhances HabitatSim with 3D Gaussian Splatting for realistic visuals and dynamic avatars, improving AI agent navigation and generalization.
Papers with codeTrendingIn No. 130
- 16 Apr 202646shares
KnowUBench: Mobile Agent Evaluation
Mobile Agent Evaluation: KnowUBench assesses how well personalized mobile agents can understand user preferences and provide helpful assistance in real-world graphical user interfaces.
Papers with codeRisingIn No. 130
- 16 Apr 202641shares
KnowRL: LLM Reasoning Enhancement
LLM Reasoning Enhancement: KnowRL improves the reasoning abilities of language models through a framework that uses reinforcement learning to provide better, guided interactions.
Papers with codeRisingIn No. 130
- 16 Apr 202635shares
OnPolicy Distillation in Language Models
Effective distillation in large language models depends on matching thought processes between teacher and student models, with teachers needing to impart new skills.
Papers with codeRisingIn No. 130
- 16 Apr 202634shares
Parallel Decoding for Diffusion Models
DMax introduces a new technique for diffusion language models that reduces mistakes in parallel decoding.
Papers with codeRisingIn No. 130
- 16 Apr 202633shares
Autonomous ML with AiScientist
AiScientist develops a system that boosts long-term machine learning research by improving coordination and project management.
Papers with codeRisingIn No. 130
- 16 Apr 202622shares
Benchmarking LLMs for Human Behavior Simulation
The OmniBehavior benchmark reveals that large language models have difficulty mimicking complex human behaviors due to biases and limited diversity.
Papers with codeRisingIn No. 130
- 3 Apr 2026475shares
Latent Space as Foundation
Latent space improves language models by creating a continuous representation that minimizes redundancy and boosts efficiency.
Papers with codeTrendingIn No. 129
How the radar works
GitHub only shows a repository's stargazers to its owner, so the panel is built from the FirmAI repositories' own stargazers: about 10,600 people who starred financial machine learning, asset management or time-series projects. Each week we read a sample of their public star lists, count how many starred each repository in the last seven days, and ask a small model to sort finance projects from general ones. We never publish who starred what, and never a count below two.