Open-source AI tools

Black Forest Labs' open-weights image model — rivals Midjourney quality.

Stateful, graph-based agent orchestration from LangChain.

Data framework for connecting LLMs to your data.

Python framework for multi-agent orchestration.

Open-source image generation — run anywhere, fine-tune anything.

Open-source agentic coding assistant that plans, edits, and runs code inside your IDE

Hybrid vector + keyword search in the enterprise-grade Elasticsearch engine

Anthropic's official SDK for building autonomous Claude agents.

OpenAI's open-source speech-to-text — the de-facto baseline.

Terminal-based AI pair programmer that writes commits.

Low-code Python AutoML library that wraps scikit-learn, XGBoost, LightGBM and friends behind a few-line API.

Open-source RAG framework for building custom AI assistants over your own documents in a few lines of Python.

LLM-driven web scraping API that turns natural-language prompts into structured JSON.

Microsoft's open-source SDK for wiring LLMs, plugins, and agents into enterprise .NET, Python, and Java apps.

Open-source vector DB with hybrid search and modules.

Foundation models from 01.AI — open-weight Yi family plus frontier Yi-Lightning and Yi-Large

A high-performance, multiplayer code editor built in Rust with native AI agent workflows.

End-to-end MLOps and GenAI platform with open-source experiment tracking and enterprise GPU orchestration.

Open-source Python-native orchestration platform for AI, ML, and data workflows at production scale.

Enterprise AI platform combining AutoML, generative AI, and vertical agents for regulated industries.

Open-source LLM observability — one-line proxy install.

The broad LLM application framework — chains, agents, retrievers.

Meta's open-weight LLM family covering 1B mobile models up to 405B frontier and natively multimodal 10M-context Llama 4 variants.

Meta's open-weights LLM family that put serious frontier-adjacent models in everyone's hands.

Desktop app for discovering, downloading, and running open-weight LLMs locally with an OpenAI-compatible server.

Source-available workflow automation with first-class AI-agent and RAG building blocks.

Alibaba's open-weight foundation model family covering chat, vision, image generation, translation, and safety classification.

AI browser agent that automates web workflows from natural-language instructions, with CAPTCHA and 2FA handling built in.

Open-source text-to-SQL agent that learns your schema and writes queries against your real warehouse.

Open-source high-throughput inference engine for serving LLMs with PagedAttention and continuous batching.

Observability and debugging platform purpose-built for AI agents, with time-travel replay and cost tracking across 400+ LLMs.

Meta's open-source research toolkit for generating music and sound effects from text via a single autoregressive language model.

Open-source framework and managed platform for serving and scaling AI models in production.

Open-source browser automation harness and cloud platform for LLM agents that drive real websites.

Open-source feature store that serves consistent features to ML training and online inference, with RAG vector search built in.

Continuous AI red teaming platform that stress-tests LLM agents for vulnerabilities before they hit production.

Open-source data quality framework for validating the datasets that feed your ML and analytics pipelines.

Open-source multi-channel AI agent with persistent memory, scheduling, and subagent delegation from Nous Research.

Open-source video composition framework that lets AI agents build videos by writing HTML, CSS, and JS.

Open-source desktop ChatGPT alternative that runs local LLMs and routes to cloud providers from one app.

Open-source multimodal lakehouse and vector database built for AI training and retrieval at petabyte scale.

Open-source, self-hostable ChatGPT-style frontend that brings every major LLM provider under one roof.

Contamination-free LLM benchmark that refreshes its questions monthly to keep frontier models honest.

Declarative, YAML-driven deep learning framework for fine-tuning LLMs and multi-modal models without writing training loops.

Open-source high-throughput inference engine for LLMs and multimodal models with OpenAI-compatible serving.

Open-source visual workspace for building, deploying, and monitoring AI agents.

Open-source LLM fine-tuning toolkit with custom kernels that train 2-30x faster and use up to 90% less VRAM.

Yahoo's open-source search engine with vector + sparse retrieval.