Open source for data and AI

Projects749Relicensed101

749 projects · 101 relicensed

Companies behind open-source projects

17 projects442k starsHugging FaceTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.Transformers diffusers smolagents lerobot datasets peft candle trl transformers.js speech-to-speech tokenizers chat-ui +5 more12 projects112k starsNvidiaMegatron-LM: Ongoing research training transformer models at scale.Megatron-LM TensorRT-LLM cosmos cutlass cudf apex Isaac-GR00T FasterTransformer DALI cuml tacotron2 nccl 11 projects399k starsMicrosoftautogen: A programming framework for agentic AI.autogen VibeVoice qlib BitNet playwright-mcp graphrag semantic-kernel winget-cli OmniParser CNTK nni 9 projects430k starsOpenAIcodex: Lightweight coding agent that runs in your terminal.codex whisper gym CLIP openai-agents-python swarm gpt-oss evals tiktoken 9 projects191k starsHashiCorpTerraform enables you to safely and predictably create, change, and improve infrastructure.Terraform Vault Consul Vagrant Nomad Packer golang-lru Waypoint Boundary 8 projects336k starsDeepSeekdeepseek-harness: DeepSeek Harness: Everything is a Plugin.deepseek-harness Janus 3FS DeepSeek-LLM DeepSeek-Coder-V2 DeepSeek-VL2 DeepSeek-V2 smallpond 7 projects105k starsRedisRedis: For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.Redis RedisInsight RediSearch lettuce RedisJSON RedisBloom RedisTimeSeries 6 projects358k starsGoogleTensorFlow: An Open Source Machine Learning Framework for Everyone.TensorFlow leveldb langextract JAX adk-python magika 6 projects258k starsMetaPyTorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration.PyTorch Llama rocksdb astryx prophet relay 6 projects51.6k starsCloudflarecloudflare-os: Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.cloudflare-os moltworker computer agentic-inbox agents vibesdk 6 projects45.7k starsDeepMindsonnet: TensorFlow-based neural network library.sonnet alphafold3 pysc2 lab gemma graph_nets 5 projects78.3k starsByteDanceUI-TARS-desktop: The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra.UI-TARS-desktop trae-agent UI-TARS flowgram.ai LatentSync 5 projects52k starsAppleFoundationDB - the open source, distributed, transactional key-value store.foundationdb pkl turicreate corenet coremltools 4 projects118k starsGrafana LabsGrafana: The open and composable observability and data visualization platform.Grafana Loki Tempo Mimir 4 projects85.5k starsDatabricksApache Spark - A unified analytics engine for large-scale data processing.Apache Spark MLflow Delta Lake koalas 4 projects75.8k starsZillizMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search.Milvus claude-context deep-searcher GPTCache 4 projects71.5k starsAnthropicclaude-plugins-official: Official, Anthropic-managed directory of high quality Claude Code Plugins.claude-plugins-official Claude Code Action Claude Agent SDK for Python claude-code-security-review 4 projects65.1k starsVercelswr: React Hooks for Data Fetching.swr chatbot eve streamdown 4 projects53.1k starsSentrySentry: Developer-first error tracking and performance monitoring.Sentry MobileBuildMCP Snuba Relay 4 projects42.2k starsConfluentApache Kafka - A distributed event streaming platform.Apache Kafka confluent-kafka-go Schema Registry ksqlDB 3 projects115k starsElasticElasticsearch: Free and Open Source, Distributed, RESTful Search Engine.Elasticsearch Kibana logstash 3 projects87.2k starsGoogle Researchgoogle-research: A machine learning library from Google Research.google-research timesfm vision_transformer 3 projects86.3k starsIBMdocling: Get your documents ready for gen AI.docling Sarama beeai-framework 3 projects52k starsStability AIgenerative-models: Generative Models by Stability AI.generative-models StableLM StableStudio 3 projects46.9k starsJina AIserve: Build multimodal AI applications with cloud-native stack.serve clip-as-service reader 3 projects22.1k starsSalesforceLAVIS - A One-stop Library for Language-Vision Intelligence.LAVIS BLIP CodeGen 3 projects21.6k starsUberreact-vis: Data Visualization Components.react-vis kraken causalml 3 projects19.3k starsvLLMvllm-omni: A framework for efficient model inference with omni-modality models.vllm-omni semantic-router aibrix 3 projects767 starsCouchbaseCouchbase Sync Gateway: A database from Couchbase, written in Go.Couchbase Sync Gateway Couchbase Lite Core Couchbase Server (ns_server) 2 projects121k starsUltralyticsUltralytics YOLO27, YOLO26, YOLO11, YOLOv8, object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking.Ultralytics YOLO YOLOv5 2 projects61k starsTencentWeKnora: Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.WeKnora ncnn 2 projects54.1k starsClickHouseClickHouse is a real-time analytics database management system.ClickHouse PeerDB 2 projects45.7k starsGitHubgithub-mcp-server: An agent project from GitHub, written in Go.github-mcp-server copilot-cli 2 projects42.5k starsFish Audiofish-speech: SOTA Open Source TTS.fish-speech Bert-VITS2 2 projects26.6k starsDatadogvector: A high-performance observability data pipeline.vector datadog-agent 2 projects26.5k starsAi2olmocr: Toolkit for linearizing PDFs for LLM datasets/training.olmocr OLMo 2 projects24.6k starsWeaviateWeaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.Weaviate Verba 2 projects19.5k starsOracleMySQL Server, the world's most popular open source database, and MySQL Cluster, a real-time, open source transactional database.MySQL docker-images 2 projects19.3k starsMoonshot AIKimi-K2: Kimi K2 is the large language model series developed by Moonshot AI team.Kimi-K2 kimi-code 2 projects16.1k starsMistral AImistral-inference: Official inference library for Mistral models.mistral-inference mistral-vibe 2 projects14.2k starsGoogle Cloudkubectl-ai: AI powered Kubernetes Assistant.kubectl-ai agent-starter-pack 2 projects13.8k starsXiaomisoar: SQL Optimizer And Rewriter.soar mace 2 projects71 starsSnowplowSnowplow Collector: Collector for cloud-native web, mobile and event analytics, running on AWS and GCP.Snowplow Collector Snowplow Enrich 1 project209k starsn8nn8n: Fair-code workflow automation platform with native AI capabilities.n8n 1 project188k starsSignificant GravitasAutoGPT is the vision of accessible AI for everyone, to use and to build on.AutoGPT 1 project186k starsOllamaOllama: Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.Ollama 1 project161k starsLangGeniusDify: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace.Dify 1 project158k starsOpen WebUIOpen WebUI: User-friendly AI Interface (Supports Ollama, OpenAI API,...).Open WebUI 1 project149k starsLangChainLangChain: The agent engineering platform.LangChain 1 project115k starsSupabasesupabase: The Postgres development platform.supabase 1 project92.6k starsAll Hands AIOpenHands: AI-Driven Development.OpenHands 1 project83.7k starsLobeHubLobeChat: LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.LobeChat 1 project75.5k starsPresetApache Superset is a Data Visualization and Data Exploration Platform.Apache Superset 1 project65.4k starsNocoDBNocoDB: A Free & Self-hostable Airtable Alternative.NocoDB 1 project63.1k starsBerriAILiteLLM: The fastest, litest AI Gateway.LiteLLM 1 project61.3k starsMinIOMinIO is a high-performance, S3 compatible object store, open sourced under GNU AGPLv3 license.MinIO 1 project59.8k starsMeilisearchMeilisearch: A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.Meilisearch 1 project55.6k starsFlowiseAIFlowise: Build AI Agents, Visually.Flowise 1 project52.8k starsLlamaIndexLlamaIndex is the document processing platform for AI.LlamaIndex 1 project50.1k starsMetabaseMetabase: The easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data.Metabase 1 project47.4k starsAstronomerApache Airflow - A platform to programmatically author, schedule, and monitor workflows.Apache Airflow 1 project46.3k starsStreamlitStreamlit, A faster way to build and share data apps.streamlit 1 project45.7k starsMenlo ResearchJan is an open source alternative to ChatGPT that runs 100% offline on your computer.Jan 1 project44.2k starsAnyscaleRay is an AI compute engine.Ray 1 project43k starsDuckDB LabsDuckDB is a high-performance analytical database system.DuckDB 1 project40.7k starsPostHogPostHog is the leading platform for building self-driving products.PostHog 1 project40.3k starsPolarsPolars: Extremely fast Query Engine for DataFrames, written in Rust.Polars 1 project39.8k starsMindsDBMindsDB: The unified workspace where open-source models get things done for you.MindsDB 1 project38.1k starsKhojKhoj: Your AI second brain.Khoj 1 project35.4k starsQdrantQdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI.Qdrant 1 project33.9k starsTabbyMLTabby: Self-hosted AI coding assistant.Tabby 1 project33.3k starsSurrealDBSurrealDB: A scalable, distributed, collaborative, document-graph database, for the realtime web.SurrealDB 1 project33.2k starsOnyxOnyx (Danswer): Open Source AI Platform - AI Chat with advanced features that works with every LLM.Onyx (Danswer) 1 project32.6k starsCockroach LabsCockroachDB, the cloud native, distributed SQL database designed for high availability, effortless scale, and control over data placement.CockroachDB 1 project32.1k starsHasuraHasura GraphQL Engine: Blazing fast, instant realtime GraphQL APIs on all your data with fine grained access control, also trigger webhooks on database events.Hasura GraphQL Engine 1 project30k starsLabringFastGPT 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.FastGPT 1 project29.8k starsPlausible AnalyticsPlausible Analytics: Open source, privacy-first web analytics.Plausible Analytics 1 project29.1k starsInvokeInvokeAI: Invoke is a leading creative engine that uses image and video generation models to empower professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies.InvokeAI 1 project28.7k starsMongoDBMongoDB: The MongoDB Database.MongoDB 1 project27.7k starsxAIgrok-build: SpaceXAI's coding agent harness and TUI.grok-build 1 project26.1k starsBlack Forest Labsflux: Official inference repo for FLUX.1 models.flux 1 project25.4k starsActivepiecesActivepieces: AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents.Activepieces 1 project24.1k starsPrefectPrefect is a workflow orchestration framework for building resilient data pipelines in Python.Prefect 1 project23.8k starsTimescale (Tiger Data)TimescaleDB: A time-series database for high-performance real-time analytics packaged as a Postgres extension.TimescaleDB 1 project22.3k starsAirbyteAirbyte: Open-source data movement for ELT pipelines and AI agents, from APIs, databases & files to warehouses, lakes, and AI applications.Airbyte 1 project21.8k starsDgraph Labs (now Hypermode)Dgraph: High-performance graph database for real-time use cases.Dgraph 1 project21.2k starsCubeCube Core is open-source semantic layer for AI, BI and embedded analytics.Cube 1 project20.6k starsBitwardenserver: Bitwarden infrastructure/backend (API, database, Docker, etc).server 1 project19.9k starsUnityml-agents: The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.ml-agents 1 project17.4k starsNeo4jneo4j: Graphs for Everyone.neo4j 1 project16.9k starsEMQ TechnologiesEMQX: The most scalable and reliable MQTT broker for AI, IoT, IIoT and connected vehicles.EMQX 1 project16.4k starsDagster LabsDagster: An orchestration platform for the development, production, and observation of data assets.Dagster 1 project15.8k starsScyllaDBScyllaDB: NoSQL data store using the Seastar framework, compatible with Apache Cassandra and Amazon DynamoDB.ScyllaDB 1 project14.3k starsArangoDBArangoDB is a native multi-model database with flexible data models for documents, graphs, and key-values.ArangoDB 1 project14.1k starsdbt Labsdbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.dbt 1 project14k starsAWSOpenSearch: Open source distributed and RESTful search engine.OpenSearch 1 project13.5k starsStarburstTrino: Official repository of Trino, the distributed SQL query engine for big data, formerly known as PrestoSQL (.Trino 1 project13.3k starsAkka (Lightbend)Akka: A platform to build and run apps that are elastic, agile, and resilient.Akka 1 project13.1k starsOpenReplayOpenReplay: Session replay, cobrowsing and product analytics you can self-host.OpenReplay 1 project12.8k starsConvexconvex-backend: The open-source reactive database for app developers.convex-backend 1 project11.9k starsFivetrangreat_expectations: Always know what to expect from your data.great_expectations 1 project11.8k starsQuickwitQuickwit: Cloud-native OSS search engine for observability.Quickwit 1 project10.9k starsShopifydashing: The exceptionally handsome dashboard framework in Ruby and Coffeescript.dashing 1 project10.7k starsYugabyteYugabyteDB - the cloud native distributed SQL database for mission-critical applications.YugabyteDB 1 project10.6k starsTypebotTypebot is a powerful chatbot builder that you can self-host.Typebot 1 project10.4k starsElectricelectric: The agent platform built on sync.electric 1 project10.3k starsSourcegraphSourcegraph: Code AI platform with Code Search & Cody.Sourcegraph 1 project9,497 starsReplicatecog: Containers for machine learning.cog 1 project9,492 starsDatabendDatabend: Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox., rebuilt from scratch.Databend 1 project8,795 starsRedpanda DataRedpanda Connect (Benthos): Fancy stream processing made operationally mundane.Redpanda Connect (Benthos) 1 project8,767 starsTailscaletailcat: Like netcat, but over Tailscale's data plane, without Tailscale's control plane.tailcat 1 project8,512 starsQualcommGenieX: Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code.GenieX 1 project8,176 starsGraylogGraylog: Free and open log management.Graylog 1 project7,799 starsFirecrawlfirecrawl-mcp-server: Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.firecrawl-mcp-server 1 project7,697 starsAlteryxfeaturetools: An open source python library for automated feature engineering.featuretools 1 project7,429 starsArcee AImergekit: Tools for merging pretrained large language models.mergekit 1 project7,009 starsDgraph Labs (now Hypermode)ristretto: A high performance memory-bound Go cache.ristretto 1 project6,823 starsRobinhoodfaust: Python Stream Processing.faust 1 project6,695 starsLinkedInLiger-Kernel: Efficient Triton Kernels for LLM Training.Liger-Kernel 1 project6,636 starsHazelcastHazelcast is a unified real-time data platform combining stream processing with a fast data store, allowing customers to act instantly on data-in-motion for real-time insights.Hazelcast 1 project6,460 starsTrueFoundrytrueforge: The open-source agent harness - the runtime layer that turns an LLM into a working agent.trueforge 1 project6,408 starsE2Bfragments: Open-source Next.js template for building apps that are fully generated by AI.fragments 1 project6,373 starsOnehouseApache Hudi: Upserts, Deletes And Incremental Processing on Big Data.Apache Hudi 1 project6,311 starsPachydermPachyderm: Data-Centric Pipelines and Data Versioning.Pachyderm 1 project6,275 starsAmazonChronos: Pretrained Models for Time Series Forecasting.Chronos 1 project6,228 starsLightdashLightdash: Agentic BI.Lightdash 1 project6,051 starsdltHubdlt: Data load tool (dlt) is an open source Python library that makes data loading easy.dlt 1 project6,034 starsInngestInngest: The leading workflow orchestration platform.Inngest 1 project5,846 starsBlockPonyDebugger: Remote network and data debugging for your native iOS app using Chrome Developer Tools.PonyDebugger 1 project5,794 starsTiger Datapgai: A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL.pgai 1 project5,643 starsLiquibaseLiquibase: An infrastructure tool from Liquibase, written in Java.Liquibase 1 project5,272 starsZalandopostgres-operator: Postgres operator creates and manages PostgreSQL clusters running in Kubernetes.postgres-operator 1 project5,196 starsArgillaArgilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets.argilla 1 project5,000 starsTogether AIRedPajama-Data: The RedPajama-Data repository contains code for preparing large datasets for training large language models.RedPajama-Data 1 project4,785 starsSeldonSeldon Core: An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.Seldon Core 1 project4,649 starsDockerdocker-agent: AI Agent Builder and Runtime by Docker Engineering.docker-agent 1 project4,515 starsRudderStackRudderStack: Privacy and Security focused Segment-alternative, in Golang and React.RudderStack 1 project4,458 starsCrunchy Datapostgres-operator: A database from Crunchy Data, written in Go.postgres-operator 1 project4,160 starsJohn Snow Labsspark-nlp: State of the Art Natural Language Processing.spark-nlp 1 project3,469 starsMiniMaxMiniMax-01: The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention.MiniMax-01 1 project3,399 starsHerokureact-refetch: A simple, declarative, and composable way to fetch data for React components.react-refetch 1 project3,180 starsElevenLabselevenlabs-python: The official Python SDK for the ElevenLabs API.elevenlabs-python 1 project3,170 starsCohereCohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.Cohere Toolkit 1 project3,133 starsPalantirPlottable: A library of modular chart components built on D3.Plottable 1 project2,884 starsPerconagrafana-dashboards: WARNING: the repo moved to.grafana-dashboards 1 project2,858 starsCursorPriompt: Prompt design using JSX.Priompt 1 project2,618 starsPerplexityPerplexity MCP Server: The official MCP server implementation for the Perplexity API Platform.Perplexity MCP Server 1 project2,160 starsFelderafeldera: The Feldera Incremental Computation Engine.feldera 1 project2,051 starsStripeStripe AI: One-stop shop for building AI-powered products and businesses with Stripe.Stripe AI 1 project1,757 starsDataStaxJVector: the most advanced embedded vector search engine.jvector 1 project1,721 starsHubSpotBuckyClient: Collect performance data from the client.BuckyClient 1 project1,687 starsAdobeantialiased-cnns: Pip install antialiased-cnns to improve stability and accuracy.antialiased-cnns 1 project1,672 starsSnowflakepg_lake: Postgres with Iceberg and data lake access.pg_lake 1 project1,498 starsMariaDBMariaDB MaxScale: An intelligent database proxy.MariaDB MaxScale 1 project1,433 starsServiceNowBrowserGym, a Gym environment for web task automation.BrowserGym 1 project1,390 starsAerospikeaerospike-server: Aerospike Database Server, flash-optimized, in-memory, nosql database.aerospike-server 1 project1,288 starsModalmodal-examples: Examples of programs built using Modal.modal-examples 1 project1,209 starsNew Relicnewrelic-ruby-agent: New Relic RPM Ruby Agent.newrelic-ruby-agent 1 project1,119 starsRaindropworkshop: Give your coding agent the power to write and run agent evals.workshop 1 project1,108 starsBuildkiteagent: The Buildkite Agent is an open-source toolkit written in Go for securely running build jobs on any device or network.agent 1 project1,099 starsReplitReplitLM: Inference code and configs for the ReplitLM model family.ReplitLM 1 project1,099 starsAmplituderedux-query: A library for managing network state in Redux.redux-query 1 project1,091 starsDenoclawpatrol: Security firewall for agents.clawpatrol 1 project1,033 starsPineconecanopy: Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone.canopy 1 project1,019 starsHume AItada: Open Source Speech Language Model.tada
CompanyStars
Hugging FaceTransformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.Transformers diffusers smolagents lerobot datasets peft candle trl transformers.js speech-to-speech tokenizers chat-ui 442k
NvidiaMegatron-LM: Ongoing research training transformer models at scale.Megatron-LM TensorRT-LLM cosmos cutlass cudf apex Isaac-GR00T FasterTransformer DALI cuml tacotron2 nccl 112k
Microsoftautogen: A programming framework for agentic AI.autogen VibeVoice qlib BitNet playwright-mcp graphrag semantic-kernel winget-cli OmniParser CNTK nni 399k
OpenAIcodex: Lightweight coding agent that runs in your terminal.codex whisper gym CLIP openai-agents-python swarm gpt-oss evals tiktoken 430k
HashiCorpTerraform enables you to safely and predictably create, change, and improve infrastructure.Terraform Vault Consul Vagrant Nomad Packer golang-lru Waypoint Boundary 191k
DeepSeekdeepseek-harness: DeepSeek Harness: Everything is a Plugin.deepseek-harness Janus 3FS DeepSeek-LLM DeepSeek-Coder-V2 DeepSeek-VL2 DeepSeek-V2 smallpond 336k
RedisRedis: For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.Redis RedisInsight RediSearch lettuce RedisJSON RedisBloom RedisTimeSeries 105k
GoogleTensorFlow: An Open Source Machine Learning Framework for Everyone.TensorFlow leveldb langextract JAX adk-python magika 358k
MetaPyTorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration.PyTorch Llama rocksdb astryx prophet relay 258k
Cloudflarecloudflare-os: Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.cloudflare-os moltworker computer agentic-inbox agents vibesdk 51.6k
DeepMindsonnet: TensorFlow-based neural network library.sonnet alphafold3 pysc2 lab gemma graph_nets 45.7k
ByteDanceUI-TARS-desktop: The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra.UI-TARS-desktop trae-agent UI-TARS flowgram.ai LatentSync 78.3k
AppleFoundationDB - the open source, distributed, transactional key-value store.foundationdb pkl turicreate corenet coremltools 52k
Grafana LabsGrafana: The open and composable observability and data visualization platform.Grafana Loki Tempo Mimir 118k
DatabricksApache Spark - A unified analytics engine for large-scale data processing.Apache Spark MLflow Delta Lake koalas 85.5k
ZillizMilvus is a high-performance, cloud-native vector database built for scalable vector ANN search.Milvus claude-context deep-searcher GPTCache 75.8k
Anthropicclaude-plugins-official: Official, Anthropic-managed directory of high quality Claude Code Plugins.claude-plugins-official Claude Code Action Claude Agent SDK for Python claude-code-security-review 71.5k
Vercelswr: React Hooks for Data Fetching.swr chatbot eve streamdown 65.1k
SentrySentry: Developer-first error tracking and performance monitoring.Sentry MobileBuildMCP Snuba Relay 53.1k
ConfluentApache Kafka - A distributed event streaming platform.Apache Kafka confluent-kafka-go Schema Registry ksqlDB 42.2k
ElasticElasticsearch: Free and Open Source, Distributed, RESTful Search Engine.Elasticsearch Kibana logstash 115k
Google Researchgoogle-research: A machine learning library from Google Research.google-research timesfm vision_transformer 87.2k
IBMdocling: Get your documents ready for gen AI.docling Sarama beeai-framework 86.3k
Stability AIgenerative-models: Generative Models by Stability AI.generative-models StableLM StableStudio 52k
Jina AIserve: Build multimodal AI applications with cloud-native stack.serve clip-as-service reader 46.9k
SalesforceLAVIS - A One-stop Library for Language-Vision Intelligence.LAVIS BLIP CodeGen 22.1k
Uberreact-vis: Data Visualization Components.react-vis kraken causalml 21.6k
vLLMvllm-omni: A framework for efficient model inference with omni-modality models.vllm-omni semantic-router aibrix 19.3k
CouchbaseCouchbase Sync Gateway: A database from Couchbase, written in Go.Couchbase Sync Gateway Couchbase Lite Core Couchbase Server (ns_server) 767
UltralyticsUltralytics YOLO27, YOLO26, YOLO11, YOLOv8, object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking.Ultralytics YOLO YOLOv5 121k
TencentWeKnora: Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.WeKnora ncnn 61k
ClickHouseClickHouse is a real-time analytics database management system.ClickHouse PeerDB 54.1k
GitHubgithub-mcp-server: An agent project from GitHub, written in Go.github-mcp-server copilot-cli 45.7k
Fish Audiofish-speech: SOTA Open Source TTS.fish-speech Bert-VITS2 42.5k
Datadogvector: A high-performance observability data pipeline.vector datadog-agent 26.6k
Ai2olmocr: Toolkit for linearizing PDFs for LLM datasets/training.olmocr OLMo 26.5k
WeaviateWeaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.Weaviate Verba 24.6k
OracleMySQL Server, the world's most popular open source database, and MySQL Cluster, a real-time, open source transactional database.MySQL docker-images 19.5k
Moonshot AIKimi-K2: Kimi K2 is the large language model series developed by Moonshot AI team.Kimi-K2 kimi-code 19.3k
Mistral AImistral-inference: Official inference library for Mistral models.mistral-inference mistral-vibe 16.1k
Google Cloudkubectl-ai: AI powered Kubernetes Assistant.kubectl-ai agent-starter-pack 14.2k
Xiaomisoar: SQL Optimizer And Rewriter.soar mace 13.8k
SnowplowSnowplow Collector: Collector for cloud-native web, mobile and event analytics, running on AWS and GCP.Snowplow Collector Snowplow Enrich 71
n8nn8n: Fair-code workflow automation platform with native AI capabilities.n8n 209k
Significant GravitasAutoGPT is the vision of accessible AI for everyone, to use and to build on.AutoGPT 188k
OllamaOllama: Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.Ollama 186k
LangGeniusDify: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace.Dify 161k
Open WebUIOpen WebUI: User-friendly AI Interface (Supports Ollama, OpenAI API,...).Open WebUI 158k
LangChainLangChain: The agent engineering platform.LangChain 149k
Supabasesupabase: The Postgres development platform.supabase 115k
All Hands AIOpenHands: AI-Driven Development.OpenHands 92.6k
LobeHubLobeChat: LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.LobeChat 83.7k
PresetApache Superset is a Data Visualization and Data Exploration Platform.Apache Superset 75.5k
NocoDBNocoDB: A Free & Self-hostable Airtable Alternative.NocoDB 65.4k
BerriAILiteLLM: The fastest, litest AI Gateway.LiteLLM 63.1k
MinIOMinIO is a high-performance, S3 compatible object store, open sourced under GNU AGPLv3 license.MinIO 61.3k
MeilisearchMeilisearch: A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.Meilisearch 59.8k
FlowiseAIFlowise: Build AI Agents, Visually.Flowise 55.6k
LlamaIndexLlamaIndex is the document processing platform for AI.LlamaIndex 52.8k
MetabaseMetabase: The easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data.Metabase 50.1k
AstronomerApache Airflow - A platform to programmatically author, schedule, and monitor workflows.Apache Airflow 47.4k
StreamlitStreamlit, A faster way to build and share data apps.streamlit 46.3k
Menlo ResearchJan is an open source alternative to ChatGPT that runs 100% offline on your computer.Jan 45.7k
AnyscaleRay is an AI compute engine.Ray 44.2k
DuckDB LabsDuckDB is a high-performance analytical database system.DuckDB 43k
PostHogPostHog is the leading platform for building self-driving products.PostHog 40.7k
PolarsPolars: Extremely fast Query Engine for DataFrames, written in Rust.Polars 40.3k
MindsDBMindsDB: The unified workspace where open-source models get things done for you.MindsDB 39.8k
KhojKhoj: Your AI second brain.Khoj 38.1k
QdrantQdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI.Qdrant 35.4k
TabbyMLTabby: Self-hosted AI coding assistant.Tabby 33.9k
SurrealDBSurrealDB: A scalable, distributed, collaborative, document-graph database, for the realtime web.SurrealDB 33.3k
OnyxOnyx (Danswer): Open Source AI Platform - AI Chat with advanced features that works with every LLM.Onyx (Danswer) 33.2k
Cockroach LabsCockroachDB, the cloud native, distributed SQL database designed for high availability, effortless scale, and control over data placement.CockroachDB 32.6k
HasuraHasura GraphQL Engine: Blazing fast, instant realtime GraphQL APIs on all your data with fine grained access control, also trigger webhooks on database events.Hasura GraphQL Engine 32.1k
LabringFastGPT 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.FastGPT 30k
Plausible AnalyticsPlausible Analytics: Open source, privacy-first web analytics.Plausible Analytics 29.8k
InvokeInvokeAI: Invoke is a leading creative engine that uses image and video generation models to empower professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies.InvokeAI 29.1k
MongoDBMongoDB: The MongoDB Database.MongoDB 28.7k
xAIgrok-build: SpaceXAI's coding agent harness and TUI.grok-build 27.7k
Black Forest Labsflux: Official inference repo for FLUX.1 models.flux 26.1k
ActivepiecesActivepieces: AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents.Activepieces 25.4k
PrefectPrefect is a workflow orchestration framework for building resilient data pipelines in Python.Prefect 24.1k
Timescale (Tiger Data)TimescaleDB: A time-series database for high-performance real-time analytics packaged as a Postgres extension.TimescaleDB 23.8k
AirbyteAirbyte: Open-source data movement for ELT pipelines and AI agents, from APIs, databases & files to warehouses, lakes, and AI applications.Airbyte 22.3k
Dgraph Labs (now Hypermode)Dgraph: High-performance graph database for real-time use cases.Dgraph 21.8k
CubeCube Core is open-source semantic layer for AI, BI and embedded analytics.Cube 21.2k
Bitwardenserver: Bitwarden infrastructure/backend (API, database, Docker, etc).server 20.6k
Unityml-agents: The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.ml-agents 19.9k
Neo4jneo4j: Graphs for Everyone.neo4j 17.4k
EMQ TechnologiesEMQX: The most scalable and reliable MQTT broker for AI, IoT, IIoT and connected vehicles.EMQX 16.9k
Dagster LabsDagster: An orchestration platform for the development, production, and observation of data assets.Dagster 16.4k
ScyllaDBScyllaDB: NoSQL data store using the Seastar framework, compatible with Apache Cassandra and Amazon DynamoDB.ScyllaDB 15.8k
ArangoDBArangoDB is a native multi-model database with flexible data models for documents, graphs, and key-values.ArangoDB 14.3k
dbt Labsdbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.dbt 14.1k
AWSOpenSearch: Open source distributed and RESTful search engine.OpenSearch 14k
StarburstTrino: Official repository of Trino, the distributed SQL query engine for big data, formerly known as PrestoSQL (.Trino 13.5k
Akka (Lightbend)Akka: A platform to build and run apps that are elastic, agile, and resilient.Akka 13.3k
OpenReplayOpenReplay: Session replay, cobrowsing and product analytics you can self-host.OpenReplay 13.1k
Convexconvex-backend: The open-source reactive database for app developers.convex-backend 12.8k
Fivetrangreat_expectations: Always know what to expect from your data.great_expectations 11.9k
QuickwitQuickwit: Cloud-native OSS search engine for observability.Quickwit 11.8k
Shopifydashing: The exceptionally handsome dashboard framework in Ruby and Coffeescript.dashing 10.9k
YugabyteYugabyteDB - the cloud native distributed SQL database for mission-critical applications.YugabyteDB 10.7k
TypebotTypebot is a powerful chatbot builder that you can self-host.Typebot 10.6k
Electricelectric: The agent platform built on sync.electric 10.4k
SourcegraphSourcegraph: Code AI platform with Code Search & Cody.Sourcegraph 10.3k
Replicatecog: Containers for machine learning.cog 9,497
DatabendDatabend: Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox., rebuilt from scratch.Databend 9,492
Redpanda DataRedpanda Connect (Benthos): Fancy stream processing made operationally mundane.Redpanda Connect (Benthos) 8,795
Tailscaletailcat: Like netcat, but over Tailscale's data plane, without Tailscale's control plane.tailcat 8,767
QualcommGenieX: Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code.GenieX 8,512
GraylogGraylog: Free and open log management.Graylog 8,176
Firecrawlfirecrawl-mcp-server: Official Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.firecrawl-mcp-server 7,799
Alteryxfeaturetools: An open source python library for automated feature engineering.featuretools 7,697
Arcee AImergekit: Tools for merging pretrained large language models.mergekit 7,429
Dgraph Labs (now Hypermode)ristretto: A high performance memory-bound Go cache.ristretto 7,009
Robinhoodfaust: Python Stream Processing.faust 6,823
LinkedInLiger-Kernel: Efficient Triton Kernels for LLM Training.Liger-Kernel 6,695
HazelcastHazelcast is a unified real-time data platform combining stream processing with a fast data store, allowing customers to act instantly on data-in-motion for real-time insights.Hazelcast 6,636
TrueFoundrytrueforge: The open-source agent harness - the runtime layer that turns an LLM into a working agent.trueforge 6,460
E2Bfragments: Open-source Next.js template for building apps that are fully generated by AI.fragments 6,408
OnehouseApache Hudi: Upserts, Deletes And Incremental Processing on Big Data.Apache Hudi 6,373
PachydermPachyderm: Data-Centric Pipelines and Data Versioning.Pachyderm 6,311
AmazonChronos: Pretrained Models for Time Series Forecasting.Chronos 6,275
LightdashLightdash: Agentic BI.Lightdash 6,228
dltHubdlt: Data load tool (dlt) is an open source Python library that makes data loading easy.dlt 6,051
InngestInngest: The leading workflow orchestration platform.Inngest 6,034
BlockPonyDebugger: Remote network and data debugging for your native iOS app using Chrome Developer Tools.PonyDebugger 5,846
Tiger Datapgai: A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL.pgai 5,794
LiquibaseLiquibase: An infrastructure tool from Liquibase, written in Java.Liquibase 5,643
Zalandopostgres-operator: Postgres operator creates and manages PostgreSQL clusters running in Kubernetes.postgres-operator 5,272
ArgillaArgilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets.argilla 5,196
Together AIRedPajama-Data: The RedPajama-Data repository contains code for preparing large datasets for training large language models.RedPajama-Data 5,000
SeldonSeldon Core: An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.Seldon Core 4,785
Dockerdocker-agent: AI Agent Builder and Runtime by Docker Engineering.docker-agent 4,649
RudderStackRudderStack: Privacy and Security focused Segment-alternative, in Golang and React.RudderStack 4,515
Crunchy Datapostgres-operator: A database from Crunchy Data, written in Go.postgres-operator 4,458
John Snow Labsspark-nlp: State of the Art Natural Language Processing.spark-nlp 4,160
MiniMaxMiniMax-01: The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention.MiniMax-01 3,469
Herokureact-refetch: A simple, declarative, and composable way to fetch data for React components.react-refetch 3,399
ElevenLabselevenlabs-python: The official Python SDK for the ElevenLabs API.elevenlabs-python 3,180
CohereCohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.Cohere Toolkit 3,170
PalantirPlottable: A library of modular chart components built on D3.Plottable 3,133
Perconagrafana-dashboards: WARNING: the repo moved to.grafana-dashboards 2,884
CursorPriompt: Prompt design using JSX.Priompt 2,858
PerplexityPerplexity MCP Server: The official MCP server implementation for the Perplexity API Platform.Perplexity MCP Server 2,618
Felderafeldera: The Feldera Incremental Computation Engine.feldera 2,160
StripeStripe AI: One-stop shop for building AI-powered products and businesses with Stripe.Stripe AI 2,051
DataStaxJVector: the most advanced embedded vector search engine.jvector 1,757
HubSpotBuckyClient: Collect performance data from the client.BuckyClient 1,721
Adobeantialiased-cnns: Pip install antialiased-cnns to improve stability and accuracy.antialiased-cnns 1,687
Snowflakepg_lake: Postgres with Iceberg and data lake access.pg_lake 1,672
MariaDBMariaDB MaxScale: An intelligent database proxy.MariaDB MaxScale 1,498
ServiceNowBrowserGym, a Gym environment for web task automation.BrowserGym 1,433
Aerospikeaerospike-server: Aerospike Database Server, flash-optimized, in-memory, nosql database.aerospike-server 1,390
Modalmodal-examples: Examples of programs built using Modal.modal-examples 1,288
New Relicnewrelic-ruby-agent: New Relic RPM Ruby Agent.newrelic-ruby-agent 1,209
Raindropworkshop: Give your coding agent the power to write and run agent evals.workshop 1,119
Buildkiteagent: The Buildkite Agent is an open-source toolkit written in Go for securely running build jobs on any device or network.agent 1,108
ReplitReplitLM: Inference code and configs for the ReplitLM model family.ReplitLM 1,099
Amplituderedux-query: A library for managing network state in Redux.redux-query 1,099
Denoclawpatrol: Security firewall for agents.clawpatrol 1,091
Pineconecanopy: Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone.canopy 1,033
Hume AItada: Open Source Speech Language Model.tada 1,019