Search and filter curated AI tools. Find the right tool for your task.
Milvus is an open-source vector database for large-scale similarity search. Billion-vector scale. Multiple index types: IVF, HNSW, DiskANN. Cloud-hosted or self-hosted. Supports multiple languages. CNCF incubating project.
Neptune is a metadata store for ML experiments. Track metrics, params, code, environment. Real-time collaboration. Charts and alerts. Series-A startup. Used by 1000+ teams.
Open-source AI gateway for routing, caching, and monitoring LLM API calls.
Qdrant is an open-source vector database optimized for semantic search and recommendation systems. HNSW indexing with pruning. Payload storage with filtering. Snapshots and recovery. Rust implementation. Growing in adoption.
An open-source distributed computing framework for scaling Python AI and ML workloads from a single machine to a large cluster without rewriting code. Ray's core model lets any Python function run as a distributed task and any Python class run as a distributed stateful actor, making parallel and distributed execution almost as easy as regular Python. Ray Tune provides distributed hyperparameter optimization across hundreds of parallel training jobs. Ray Train scales model training in PyTorch and TensorFlow across multiple GPUs and machines. Ray Serve deploys ML models as production online services with batching, autoscaling, and model composition support. Ray Data handles large-scale data preprocessing in parallel pipelines. Used by every major AI company and research lab for scaling LLM training, reinforcement learning environments, and inference workloads. Open source under Apache 2.0 on GitHub; managed cloud version is Anyscale. Used by companies including OpenAI, Anthropic, and Uber.
Microsoft's open-source AI orchestration SDK for building AI agents and copilot experiences in C#, Python, and Java. Semantic Kernel provides abstractions for connecting LLMs from OpenAI and Azure OpenAI with native code functions, memory stores, and planners that let AI models invoke application logic. The Planner component lets an AI model decompose a goal into a sequence of function calls, enabling multi-step agentic workflows where the model can search a database, call an API, write a file, and summarize results in a single user request. Memory integration supports vector database-backed semantic memory retrieval. A Process Framework enables designing multi-agent systems with defined coordination patterns. Used heavily within Microsoft's own products and deeply integrated with Azure AI services. Open source on GitHub under MIT license. Popular with .NET development teams and enterprises building copilots on the Azure platform.
Supabase hosts open-source Postgres with pgvector. IVF and HNSW indexing. Realtime subscriptions. Row-level security. Built on pg_trgm for text search.
An enterprise RAG platform providing a fully managed, API-first service for building semantic search and AI-powered question answering systems over private data. Vectara handles the complete RAG pipeline as a service: document ingestion and chunking, embedding generation, vector storage, hybrid search, reranking, and answer generation, without the user needing to manage any infrastructure. The Grounded Generation feature produces answers that cite specific sections of ingested documents, reducing hallucinations and making outputs verifiable. A Hallucination Evaluation Model is a free open-source score for measuring how factually grounded any AI response is. Enterprise features include access control, multi-tenant data isolation, and SOC 2 compliance. Free plan covers 50MB of data and 200 queries per month; paid plans scale by data volume and query count. Used by enterprises building internal knowledge bases, customer support assistants, and document search systems.
Weaviate is an open-source vector database with HNSW indexing. GraphQL API for queries. Multi-model: combine vectors and structured data. Semantic search and RAG out of box. Cloud-hosted option. Growing adoption.
A document AI platform enabling natural language conversation with uploaded PDFs, Word documents, text files, and PowerPoint files, as well as documents loaded from URLs or Google Drive links. AskYourPDF stores documents in a personal knowledge library and lets users query across multiple documents simultaneously, asking a question and getting a synthesized answer from several sources. A team workspace lets shared documents be queried by all members. An API allows developers to embed document Q&A into their own applications. The platform also supports web-based research where users submit a URL and ask questions about the page content. Free plan covers basic document chat with limited messages; Pro is $9.99/month. Popular with legal professionals, consultants, researchers, and business analysts who work with large volumes of document-based information.
An interactive learning platform for building skills in math, science, data analysis, and computer science through guided problem solving rather than video lectures. Brilliant's approach is hands-on: each concept is learned by solving progressively harder problems with built-in hints, visual interactive simulations, and AI explanations of why an answer is wrong in context. Subjects covered include algebra, geometry, calculus, probability, statistics, logic, quantum computing, neural networks, Python programming, and data science. The AI adapts the difficulty of problems dynamically based on performance and identifies knowledge gaps to address. Unlike Coursera or Khan Academy, Brilliant does not offer certifications but focuses purely on deep conceptual understanding. Free trial includes some content; Brilliant Premium is $24.99/month or $149.99/year for full access. Used by students, working professionals developing technical skills, and lifelong learners.
A web tool that lets users upload any PDF document and have a natural language conversation with its contents using AI. Users ask questions about the document and ChatPDF retrieves and synthesizes relevant passages to generate a direct answer with page references. It works for research papers, legal contracts, financial reports, textbooks, manuals, and any other document-based content. The tool handles documents up to several hundred pages and retains context across multiple questions in the same session, making it possible to explore a complex document through conversation rather than linear reading. A summary is auto-generated when a document is first uploaded. Free plan covers 2 PDFs per day up to 120 pages each; Pro is $5/month for more PDFs, larger files, and higher message limits. Popular with students reading academic papers, lawyers reviewing contracts, and analysts processing reports.
A visual research tool that generates a graph showing relationships between academic papers based on citation networks and semantic similarity. Researchers enter a seed paper they consider relevant to their topic, and Connected Papers builds a visual map of related work, clustering similar papers together and showing how closely each paper is connected to the seed through edge thickness and node proximity. This helps researchers quickly identify the most influential papers in a field, find seminal works they might have missed, and see which papers are highly cited together. Papers can be clicked to open in their source database. The graph view is more intuitive for exploring a field than a list of search results, making it especially useful at the start of a literature review. Free plan allows 5 graph builds per month; Pro is $3/month for unlimited graphs. Popular with academics, graduate students, and research analysts.
Duolingo has integrated AI throughout its language learning app, with the most significant additions in Duolingo Max, the premium AI tier. Explain My Answer is an AI tutor that explains why a user's response was correct or incorrect in natural language rather than showing a generic error message. Roleplay lets users practice real-world conversational scenarios with an AI character in the target language, covering situations like ordering food, asking for directions, or making plans. The existing spaced repetition algorithm uses AI to schedule vocabulary review at the optimal time for each individual learner. Duolingo's AI also powers audio comprehension practice, adaptive hint systems, and sentence-level translation exercises. Free tier covers core lessons; Duolingo Max with full AI features is $29.99/month. Duolingo has over 500 million registered users globally, making it the world's most used language learning platform.
An AI English pronunciation and speaking coach app that uses speech recognition to detect and correct pronunciation errors at the level of individual phonemes. Unlike apps that only transcribe speech, Elsa analyzes precisely which sounds are mispronounced, why they are incorrect, and provides targeted exercises to correct the specific mouth position and airflow needed for each sound. The app builds a personal pronunciation profile for each learner based on their native language and detected weaknesses, then creates a customized learning path. Elsa covers over 22,000 English words and includes practice with sentences, conversations, and business scenarios. Users practice being understood in meetings, on video calls, at the doctor, and in other real-life situations. Free plan includes limited daily lessons; Elsa Pro is $11.99/month or $59.99/year. Used by over 7 million people in 101 countries learning to speak English more clearly.
AI tool that explains complex sections of research papers simply.
AI tool for asking questions about your uploaded documents.
The AI tutor from Khan Academy, built on GPT-4 and designed around Socratic teaching methods rather than just giving answers. Instead of solving problems directly for students, Khanmigo asks guiding questions that help them reason through solutions themselves, supporting deeper learning rather than answer copying. Khanmigo works across Khan Academy's full curriculum including math, science, history, computing, and economics, and also tutors for SAT and AP exam preparation. A teacher mode lets educators use Khanmigo to generate lesson plans, quiz questions, writing rubrics, and ideas for explaining difficult concepts in new ways. A writing coach guides students through essay structure without doing the writing for them. Available to Khan Academy learners for $4/month as an individual add-on, with free access available through school and district partnerships. Used by millions of K-12 students and families globally.
A literature mapping and paper discovery tool that helps researchers visualize and navigate scientific literature networks. Litmaps generates a timeline graph showing how papers in a field relate to each other and how research has evolved over time. A Seed Map feature starts from one or more known relevant papers and grows outward to discover connected works through citation relationships. The Discover feature continuously monitors for new papers matching the researcher's topic profile and sends email alerts when relevant new research is published. Notes and highlighting tools allow researchers to annotate papers within the platform. Litmaps integrates with Zotero, Mendeley, and Excel for managing reference lists. Free plan allows 2 active maps; paid plans start at $10/month. Popular with PhD students, research scientists, and systematic review teams building comprehensive literature maps.
AI math solver that explains step-by-step solutions from camera input.
