--- title: GitHub radar url: https://www.ml-quant.com/radar/ site: ML-Quant (https://www.ml-quant.com) updated: 2026-09-26 license: Summaries CC BY 4.0; links go to the original sources index: https://www.ml-quant.com/llms.txt --- # 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/OpenStock](https://github.com/Open-Dev-Society/OpenStock) (8 quants, 19210 stars): Open-source platform for tracking real-time stock prices and company insights. - [jarrodwatts/jev-trader](https://github.com/jarrodwatts/jev-trader) (4 quants, 2395 stars): AI trading bot making one Jev trade decision per Monad block. - [brycewang-stanford/Auto-Empirical-Research-Skills](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills) (4 quants, 4374 stars): Collection of 23,000+ agent skills for empirical research in social sciences. - [anthropics/financial-services](https://github.com/anthropics/financial-services) (4 quants, 37481 stars): Anthropic's financial services implementation. - [Yijia-Xiao/FinanceHarness](https://github.com/Yijia-Xiao/FinanceHarness) (2 quants, 176 stars): Autonomous financial deep research framework with agentic capabilities. - [caiovicentino/eikos](https://github.com/caiovicentino/eikos) (2 quants, 18 stars): Calibrated typed-decision models for finance and trading applications. - [securo-finance/securo](https://github.com/securo-finance/securo) (2 quants, 3783 stars): Open-source self-hosted privacy-first personal finance manager. - [ccxt/ccxt](https://github.com/ccxt/ccxt) (2 quants, 44146 stars): Unified API for 100+ crypto exchanges and prediction markets. ## What quants are playing with - [NandhaKishorM/laya](https://github.com/NandhaKishorM/laya) (28 quants, 23992 stars): Non-autoregressive decision engine for typed choices over text in 100+ languages. - [browser-use/jev-ultrafast](https://github.com/browser-use/jev-ultrafast) (19 quants, 20053 stars): Fastest and cheapest web agent for automation tasks. - [google/ax](https://github.com/google/ax) (19 quants, 11097 stars): Google's open agentic orchestration runtime for agent systems. - [jaredpalmer/kev](https://github.com/jaredpalmer/kev) (13 quants, 6886 stars): Decision models built on Qwen3.5/3.8 you can train locally. - [Contrastive-LM/CLM](https://github.com/Contrastive-LM/CLM) (8 quants, 1065 stars): Contrastive language model implementation. - [nokia-applied-research/AnyJev](https://github.com/nokia-applied-research/AnyJev) (7 quants, 590 stars): Turn any LLM into a Jev-style decision model with typed decisions. ## Repos the letter featured - [Turso: SQLite SQL Database](https://github.com/tursodatabase/turso) (2026-05-20): SQLite SQL Database: Turso is a SQL database that works well with SQLite. - [Optimizing LLM Inference](https://github.com/algorithmicsuperintelligence/optillm) (2026-05-20): The article focuses on improving inference proxies for large language models. - [Fullstack China AShare Toolkit](https://github.com/simonlin1212/a-stock-data) (2026-05-20): A new toolkit helps AI coding assistants analyze China's A-share market. - [Ashare Multi-Agent Framework](https://github.com/simonlin1212/TradingAgents-astock) (2026-05-20): A research framework uses AI agents to discuss investment strategies for the A-share market. - [LLMDriven Alpha Factory](https://github.com/Miasyster/QuantGPT) (2026-05-20): An agent-based alpha factory enables LLMs to independently conduct backtests and analyze factors. - [AffaanmECC: AI Performance Optimization](https://github.com/affaan-m/ECC) (2026-05-20): AI Performance Optimization: Claude Code Codex improves AI agents' abilities by using different skills and development techniques. - [RiskLabAI: Advanced Risk Management](https://github.com/RiskLabAI/RiskLabAI.py) (2026-05-20): Advanced Risk Management: The article discusses how Python can be applied in financial AI applications. - [ViktorAxelsenMemSkill: Evolving AI Memory Skills](https://github.com/ViktorAxelsen/MemSkill) (2026-05-20): Evolving AI Memory Skills: MemSkill enhances AI agents' memory skills through continuous learning. - [Struktoaimirage: Unified AI Filesystem](https://github.com/strukto-ai/mirage) (2026-05-20): Unified AI Filesystem: The article introduces a unified virtual filesystem that boosts efficiency for AI agents. - [MVanHornCliprintingPress: AI CLI with SQLite Sync](https://github.com/mvanhorn/cli-printing-press) (2026-05-20): AI CLI with SQLite Sync: This tool picks out key features from rival APIs to build a better command-line interface for AI agents. - [Alpha Stock Factors via RL](https://github.com/ICT-FinD-Lab/alphagen) (2026-04-16): The article explores how reinforcement learning can be applied to develop stock prediction factors. - [Financial Features](https://github.com/YuxinSUN89/quant-ohlcv-feature) (2026-04-16): It compiles 300 features and factors drawn from both research and industry perspectives. - [Feature Engineering for Quant](https://github.com/lucasinglese/oryon) (2026-04-16): The paper outlines effective methods for feature and target engineering, utilizing a Rust core with a Python interface. - [Science Agent Skills](https://github.com/K-Dense-AI/scientific-agent-skills) (2026-04-16): It presents practical skills for agents to improve tasks in research, engineering, finance, and writing. - [Open Source AI Trading Agent](https://github.com/alsk1992/CloddsBot) (2026-04-16): The article introduces an autonomous open-source AI trading agent capable of trading in various markets and managing risk. - [MaalSalan Tool](https://github.com/maaslalani/sheets) (2026-04-16): A terminal tool enables users to manage spreadsheets directly from the command line. - [JackWener OpenCLI](https://github.com/jackwener/OpenCLI) (2026-04-16): A platform transforms websites or apps into command-line interfaces for easy AI tool integration. - [MemPalace AI System](https://github.com/MemPalace/mempalace) (2026-04-16): A free, highly effective AI memory system has been tested successfully. - [Caveman Token Tech](https://github.com/JuliusBrussee/caveman) (2026-04-16): Claude Code is a new skill that minimizes token usage by using simpler language. - [Small Fish 9M LLM](https://github.com/arman-bd/guppylm) (2026-04-16): A lightweight language model, with 9 million parameters, imitates the speech of a small fish. - [NVIDIA AI Portfolio Optimization](https://github.com/NVIDIA-AI-Blueprints/quantitative-portfolio-optimization) (2026-04-03): The article provides a developer example for enhancing investment portfolios with NVIDIA's tools. - [Modular RL Trading Framework](https://github.com/TorchTrade/torchtrade) (2026-04-03): It introduces a flexible system that uses reinforcement learning to enhance algorithmic trading strategies. - [Rust Optopsy Engine Rewrite](https://github.com/goldspanlabs/optopsy-mcp) (2026-04-03): This article covers a Rust-based update of Optopsy, a backtesting engine for options trading, featuring a new protocol. - [LLM Trading System for ETFs](https://github.com/45ck/llm-quant) (2026-04-03): It highlights a paper trading system using LLM and Claude for macro ETF strategies, equipped with a secure trade ledger. - [Apache Fluss: Real-Time Analytics](https://github.com/apache/fluss) (2026-04-03): Real-Time Analytics: Apache Fluss is presented as a real-time data analytics solution for streaming storage. - [Repo Ownership Transfer](https://github.com/ultraworkers/claw-code) (2026-04-03): The repository is locked for ownership transfer; users are redirected to a faster alternative to reach 100K stars. - [Rust Rebuild of Claude](https://github.com/instructkr/claw-code) (2026-04-03): Better Harness Tools aims to archive leaked Claude Code and is being rewritten in Rust for better functionality. - [Enhance Codex](https://github.com/Yeachan-Heo/oh-my-codex) (2026-04-03): OmX Oh My codeX upgrades your codex with new features including hooks, agent teams, and HUDs. - [Terse CLAUDE.md Workflows](https://github.com/drona23/claude-token-efficient) (2026-04-03): The CLAUDE.md file simplifies responses by keeping them brief without requiring code changes. - [Cognitive Architecture for Claude](https://github.com/marciopuga/cog) (2026-04-03): The article describes a cognitive architecture for Claude Code that includes persistent memory, self-reflection, and foresight. - [VectorBT Trading Skills](https://github.com/marketcalls/vectorbt-backtesting-skills) (2026-03-04): VectorBT provides tools for testing trading strategies with realistic costs and templates. - [HTML & Slide Agent](https://github.com/nicobailon/visual-explainer) (2026-03-04): An agent skill that generates HTML pages or presentations for project documentation. - [AI Options Research Library](https://github.com/goldspanlabs/optopsy) (2026-03-04): An AI-powered Python library designed for options research and backtesting. - [Code Review Database](https://github.com/roborev-dev/roborev) (2026-03-04): A system that continuously reviews code to improve agent productivity and responsibility. - [AlphaEvolve Implementation](https://github.com/algorithmicsuperintelligence/openevolve) (2026-03-04): An open-source version of AlphaEvolve is now accessible for users. - [Anthropics Plugins](https://github.com/anthropics/financial-services-plugins) (2026-03-04): The Allinone AI framework toolkit provides an extensive solution for different AI projects. - [Mindfold Toolkit](https://github.com/mindfold-ai/Trellis) (2026-03-04): A new stealthy rootkit targets and compromises modern Linux kernels. - [MatheuZ Rootkit](https://github.com/MatheuZSecurity/Singularity) (2026-03-04): OpenClaw introduces an easy-to-use web dashboard to better manage agents and improve shipping speed. - [OpenClaw Dashboard](https://github.com/grp06/openclaw-studio) (2026-03-04): GitHub Copilot CLI enables users to use Copilot's coding features directly in the terminal. - [Prediction Market Framework](https://github.com/Jon-Becker/prediction-market-analysis) (2026-02-12): A new framework gathers and analyzes data from prediction markets, featuring extensive datasets from Polymarket and Kalshi.