AI Tools Scout
Open-source ToolsLLM ProjectsMCP ServersMethodology
AI Tools Scout

An open-source AI tools directory with clear use cases, visible source freshness, and maintenance evidence for anyone deciding what to try.

Explore
Open source AI projectsOpen source LLM projectsMCP servers list
More
SkillsContentAbout
Rankings use public ecosystem signals. Treat them as a starting point, then confirm license, setup, safety, and fit with the upstream project.
  1. Home
  2. /Open-source Tools

Open-source AI tools directory

Open Source AI Tools & Projects Directory

Discover 31 open source AI tools across 1 categories. Start with what each tool does, then use current activity, maintenance signals, and source freshness when you need a deeper comparison.

Project data last synced 2d ago.
Most adopted
All-time GitHub footprint
Trending
Fastest weekly growth
Healthiest
Strongest maintenance signals
Recently updated
Latest repository activity
All
🤖 Agent
🧱 Framework
⚡ Inference
💬 Interface
☁️ Platform (selected)
🎨 Image
🎵 Audio
✓ Verified evidence

Showing 1-31 of 31 projects

Clear filters
#ProjectCategoryStars▼Weekly▽TrendHealth▽LanguageUpdated▽
1
Made With ML
Learn how to develop, deploy and iterate on production-grade ML applications.
Basic listing
☁️ Platform48.8K+1.3KWatch54/100Jupyter Notebook4mo ago
2
Airflow
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
Basic listing
☁️ Platform46.2K+845Strong91/100Python1d ago
3
Deepspeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Basic listing
☁️ Platform42.8K+463Healthy78/100Python2d ago
4
Ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Basic listing
☁️ Platform42.5K+72Healthy76/100Python2mo ago
5
Colossalai
Making large AI models cheaper, faster and more accessible
Basic listing
☁️ Platform41.4K+39Watch56/100Python10d ago
6
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Basic listing
☁️ Platform34.0K+580Healthy60/100Jupyter Notebook4mo ago
7
Qdrant
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Basic listing
☁️ Platform33.5K+2.3KStrong86/100Rust1d ago
8
Fastgpt
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.
Basic listing
☁️ Platform29.1K+1.1KStrong92/100TypeScript1d ago
9
Kestra
Event Driven Orchestration & Scheduling Platform for Mission Critical Applications
Basic listing
☁️ Platform27.4K0Healthy69/100Java1d ago
10
Label Studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Basic listing
☁️ Platform27.3K+70Healthy76/100TypeScript2mo ago
11
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.
Basic listing
☁️ Platform25.9K+129Strong83/100Python2mo ago
12
Marimo
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
Basic listing
☁️ Platform21.9K+1.0KStrong90/100Python1d ago
13
Awesome Production Machine Learning
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
Basic listing
☁️ Platform20.5K0Watch40/100-2mo ago
14
Tfjs
A WebGL accelerated JavaScript library for training and deploying ML models.
Basic listing
☁️ Platform19.1K0Watch48/100TypeScript2mo ago
15
Megatron LM
Ongoing research training transformer models at scale
Basic listing
☁️ Platform16.3K0Healthy61/100Python2mo ago
16
DVC
🦉 Data Versioning and ML Experiments
Basic listing
☁️ Platform15.6K+14Watch48/100Python2mo ago
17
Trigger.dev
Trigger.dev – build and deploy fully‑managed AI agents and workflows
Basic listing
☁️ Platform14.9K0Healthy63/100TypeScript2mo ago
18
Weights & Biases
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
Basic listing
☁️ Platform11.1K+17Healthy64/100Python2mo ago
19
Metaflow
Build, Manage and Deploy AI/ML Systems
Basic listing
☁️ Platform10.1K0Watch54/100Python2mo ago
20
BentoML
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
Basic listing
☁️ Platform8.6K+13Watch53/100Python2mo ago
21
Evidently
Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
Basic listing
☁️ Platform7.5K0Caution37/100Jupyter Notebook2mo ago
22
Unstract
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Basic listing
☁️ Platform6.7K0Watch58/100Python1d ago
23
Academic Research Skills
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Basic listing
☁️ Platform6.1K0Healthy62/100Python2mo ago
24
Chinese CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Basic listing
☁️ Platform5.9K0Caution32/100Jupyter Notebook3mo ago
25
LLM Engineers Handbook
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
Basic listing
☁️ Platform5.0K0Caution34/100Python3mo ago
26
Cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
Basic listing
☁️ Platform4.4K0Watch41/100Python4mo ago
27
Fengshenbang LM
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。
Basic listing
☁️ Platform4.1K0Caution37/100Python1mo ago
28
Swanlab
⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / verl / LLaMA Factory / ms-swift / Ultralytics / MMEngine / Keras etc.
Basic listing
☁️ Platform3.9K0Watch50/100Python2mo ago
29
Instill Core
🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications
Basic listing
☁️ Platform2.3K0Caution34/100Python2mo ago
30
Rocketride Server
High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.
Basic listing
☁️ Platform2.2K0Healthy73/100C++2mo ago
31
Nullhub
Management console for the Null ecosystem — install, configure, and monitor AI agents, orchestration workflows, task pipelines, and system health
Basic listing
☁️ Platform1.6K0Watch59/100Zig5d ago

How to use the ranking

Turn a leaderboard into an adoption shortlist

1. Match the use case

Start with category and search filters. An agent framework, inference runtime, interface, and image model solve different problems even when all are called “AI tools.”

2. Check present-tense health

Use weekly growth, last update, commit frequency, and health score to distinguish active projects from repositories living on historical popularity.

3. Validate in your environment

Open the detail page, inspect the upstream repository and license, then run a small proof of concept. Rankings narrow the field; they do not replace technical due diligence.

Quick answers

Open source AI project rankings

What makes an open source AI project worth adopting?+

Start with the use case, then look beyond stars. Recent activity, releases, issue handling, contributor depth, documentation, license, and setup fit all matter. This directory exposes those signals so you can create a shortlist before trying a tool.

Is the most-starred AI project always the best choice?+

No. Stars show awareness and broad adoption, but they do not guarantee active maintenance or suitability for your use case. Use the Trending, Healthiest, and Recently Updated views alongside the all-time ranking.

How should I compare two AI projects?+

Compare maturity, current momentum, maintenance health, language, license, deployment model, integrations, and operating cost. Project detail pages also link to side-by-side comparison pages when a relevant peer is available.

Weekly AI open-source movers

Get the fastest-growing projects, useful MCP servers, and technical reads in one weekly email.