91 AI AgentsFree scan on submit

Data Science & ML AI Agents

Compare the best open-source AI agents for data science & ML. Models, RAG pipelines, embeddings and datasets. Ranked by GitHub stars, with install commands, what each one can touch and scan reports where available.

AllCoding AgentsDeveloper ToolsData Science & MLProductivity & WorkflowResearch & AnalysisBrowser AutomationWeb Scraping & DataDatabase ManagementSecurity & TestingDeployment & DevOpsCloud InfrastructureDesign & MediaContent & WritingMarketing AutomationFinance & TradingCommunicationSEO & AI SearchSocial MediaJob Search & CareersSales & CRME-commerceCrypto & Web3Gaming & Game DevSmart Home & IoTLearning ResourcesOther

Ragflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Data Science & ML Scanned 93k

Cherry Studio

Your AI workspace for models, agents, and productivity.

Data Science & ML Scanned 53k

PageIndex

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Data Science & ML Scanned 40k

Graphiti

Build Real-Time Knowledge Graphs for AI Agents

Data Science & ML Scanned 32k

Cua

Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.

Data Science & ML Scanned 31k

Mlflow

The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

Data Science & ML Scanned 29k

NemoClaw

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

Data Science & ML Scanned 23k

Kubeflow

The Cloud Native AI Platform

Data Science & ML Scanned 16k

MiMo Code

MiMo Code: Where Models and Agents Co-Evolve

Data Science & ML Scanned 14k

Txtai

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Data Science & ML Scanned 13k

Aichat

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

Data Science & ML Scanned 11k

Metaflow

Build, Manage and Deploy AI/ML Systems

Data Science & ML Scanned 10k

Oh My Opencode Slim

Lean, fine tuned Opencode multi agent suite · Mix any models · Auto delegate tasks

Data Science & ML Scanned 10k

Oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

Data Science & ML Scanned 9.4k

Big AGI

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

Data Science & ML Scanned 7.2k

Rakazo

Open-source Grok Bot alternative. Choose your own model and sandbox.

Data Science & ML Scanned 6.5k

Zenml

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

Data Science & ML Scanned 5.6k

AI Data Science Team

An AI-powered data science team of agents to help you perform common data science tasks 10X faster.

Data Science & ML Scanned 5.5k

OpenKB

OpenKB: Open LLM Knowledge Base

Data Science & ML Scanned 4.8k

Thunderbolt

AI You Control: Choose your models. Own your data. Eliminate vendor lock-in.

Data Science & ML Scanned 4.8k

DeepAnalyze

DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师,自动分析大量数据,一键生成专业分析报告!

Data Science & ML Scanned 4.8k

Optillm

Optimizing inference proxy for LLMs

Data Science & ML Scanned 4.3k

Agentic Rag For Dummies

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Data Science & ML Scanned 4.3k

LazyLLM

Easiest and laziest way for building multi-agent LLMs applications.

Data Science & ML Scanned 3.9k

List refreshed November 15, 2026. Data comes from public GitHub repositories.