Aggregated from data/gh/*.json (GitHub REST GET /repos/{owner}/{repo}). Snapshot date 2026-08-07; re-verify at integration time.
| Repository | Stars | License | Language | Last push | Archived | Description |
|---|---|---|---|---|---|---|
| n8n-io/n8n | 199,663 | NOASSERTION | TypeScript | 2026-08-07 | Fair-code workflow automation platform with native AI capabilities. Combine visu | |
| langchain-ai/langchain | 143,614 | MIT | Python | 2026-08-07 | The agent engineering platform. | |
| supabase/supabase | 107,653 | Apache-2.0 | TypeScript | 2026-08-07 | The Postgres development platform. Supabase gives you a dedicated Postgres datab | |
| puppeteer/puppeteer | 95,415 | Apache-2.0 | TypeScript | 2026-08-07 | JavaScript API for Chrome and Firefox | |
| microsoft/playwright | 94,145 | Apache-2.0 | TypeScript | 2026-08-07 | Playwright is a framework for Web Testing and Automation. It allows testing Chro | |
| modelcontextprotocol/servers | 89,312 | NOASSERTION | TypeScript | 2026-08-05 | Model Context Protocol Servers | |
| elastic/elasticsearch | 77,800 | NOASSERTION | Java | 2026-08-07 | Free and Open Source, Distributed, RESTful Search Engine | |
| nestjs/nest | 76,362 | MIT | TypeScript | 2026-08-07 | A progressive Node.js framework for building efficient, scalable, and enterprise | |
| scrapy/scrapy | 63,682 | BSD-3-Clause | Python | 2026-08-06 | Scrapy, a fast high-level web crawling & scraping framework for Python. | |
| microsoft/autogen | 60,291 | CC-BY-4.0 | Python | 2026-04-15 | A programming framework for agentic AI | |
| meilisearch/meilisearch | 58,895 | NOASSERTION | Rust | 2026-08-06 | A lightning-fast search engine API bringing AI-powered hybrid search to your sit | |
| crewAIInc/crewAI | 56,729 | MIT | Python | 2026-08-07 | Framework for orchestrating role-playing, autonomous AI agents. By fostering col | |
| FlowiseAI/Flowise | 55,235 | NOASSERTION | TypeScript | 2026-08-07 | Build AI Agents, Visually | |
| twentyhq/twenty | 54,447 | NOASSERTION | TypeScript | 2026-08-07 | The open alternative to Salesforce, designed for AI. | |
| odoo/odoo | 53,553 | NOASSERTION | Python | 2026-08-07 | Odoo. Open Source Apps To Grow Your Business. | |
| run-llama/llama_index | 51,442 | MIT | Python | 2026-08-06 | LlamaIndex is the leading document agent and OCR platform | |
| huginn/huginn | 49,754 | MIT | Ruby | 2026-08-07 | Create agents that monitor and act on your behalf. Your agents are standing by! | |
| apache/airflow | 46,407 | Apache-2.0 | Python | 2026-08-07 | Apache Airflow - A platform to programmatically author, schedule, and monitor wo | |
| milvus-io/milvus | 45,552 | Apache-2.0 | Go | 2026-08-07 | Milvus is a high-performance, cloud-native vector database built for scalable ve | |
| streamlit/streamlit | 45,511 | Apache-2.0 | Python | 2026-08-07 | Streamlit — A faster way to build and share data apps. | |
| paperless-ngx/paperless-ngx | 44,051 | GPL-3.0 | Python | 2026-08-07 | A community-supported supercharged document management system: scan, index and a | |
| gradio-app/gradio | 43,310 | Apache-2.0 | Python | 2026-08-07 | Build and share delightful machine learning apps, all in Python. 🌟 Star to suppo | |
| appsmithorg/appsmith | 40,599 | Apache-2.0 | TypeScript | 2026-08-07 | Platform to build admin panels, internal tools, and dashboards. Integrates with | |
| novuhq/novu | 39,458 | NOASSERTION | TypeScript | 2026-08-07 | The open-source communication infrastructure for agents and products | |
| langchain-ai/langgraph | 39,106 | MIT | Python | 2026-08-06 | Build resilient agents. | |
| ToolJet/ToolJet | 38,303 | AGPL-3.0 | JavaScript | 2026-08-07 | ToolJet is the open-source foundation of ToolJet AI - the enterprise app generat | |
| portainer/portainer | 38,175 | Zlib | TypeScript | 2026-08-06 | Making Docker and Kubernetes management easy. | |
| frappe/erpnext | 37,714 | GPL-3.0 | Python | 2026-08-07 | Free and Open Source Enterprise Resource Planning (ERP) | |
| directus/directus | 37,220 | NOASSERTION | TypeScript | 2026-08-06 | The flexible backend for all your projects 🐰 Turn your DB into a headless CMS, a | |
| keycloak/keycloak | 36,053 | Apache-2.0 | Java | 2026-08-07 | Open Source Identity and Access Management For Modern Applications and Services | |
| qdrant/qdrant | 33,824 | Apache-2.0 | Rust | 2026-08-07 | Qdrant - High-performance, massive-scale Vector Database and Vector Search Engin | |
| langfuse/langfuse | 32,687 | NOASSERTION | TypeScript | 2026-08-07 | 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt | |
| encode/django-rest-framework | 30,125 | NOASSERTION | Python | 2026-08-07 | Web APIs for Django. 🎸 | |
| getzep/graphiti | 29,648 | Apache-2.0 | Python | 2026-08-05 | Build Real-Time Knowledge Graphs for AI Agents | |
| chroma-core/chroma | 28,971 | Apache-2.0 | Rust | 2026-08-06 | Search infrastructure for AI | |
| assafelovic/gpt-researcher | 28,873 | Apache-2.0 | Python | 2026-07-18 | An autonomous agent that conducts deep research on any data using any LLM provid | |
| supermemoryai/supermemory | 28,803 | MIT | TypeScript | 2026-08-07 | Memory and context engine + app that is extremely fast, scalable, and can be run | |
| mongodb/mongo | 28,475 | NOASSERTION | C++ | 2026-08-07 | The MongoDB Database | |
| openai/openai-agents-python | 28,467 | MIT | Python | 2026-08-07 | A lightweight, powerful framework for multi-agent workflows | |
| typesense/typesense | 26,406 | GPL-3.0 | C++ | 2026-08-05 | Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative t | |
| apify/crawlee | 25,219 | Apache-2.0 | TypeScript | 2026-08-07 | Crawlee—A web scraping and browser automation library for Node.js to build relia | |
| vanna-ai/vanna | 23,822 | MIT | Python | 2026-02-02 | yes | 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using |
| sinaptik-ai/pandas-ai | 23,726 | NOASSERTION | Python | 2025-10-28 | Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes dat | |
| activepieces/activepieces | 23,615 | NOASSERTION | TypeScript | 2026-08-07 | AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • A | |
| PrefectHQ/prefect | 23,567 | Apache-2.0 | Python | 2026-08-07 | Prefect is a workflow orchestration framework for building resilient data pipeli | |
| pgvector/pgvector | 22,525 | NOASSERTION | C | 2026-08-04 | Open-source vector similarity search for Postgres | |
| temporalio/temporal | 22,160 | MIT | Go | 2026-08-07 | Temporal service | |
| airbytehq/airbyte | 21,829 | NOASSERTION | Python | 2026-08-07 | Open-source data movement for ELT pipelines and AI agents — from APIs, databases | |
| postgres/postgres | 21,717 | NOASSERTION | C | 2026-08-07 | Mirror of the official PostgreSQL GIT repository. Note that this is just a *mirr | |
| smicallef/spiderfoot | 20,100 | MIT | Python | 2026-04-13 | SpiderFoot automates OSINT for threat intelligence and mapping your attack surfa | |
| elizaOS/eliza | 18,917 | MIT | TypeScript | 2026-08-07 | Open source agentic operating system | |
| langchain-ai/langchainjs | 18,019 | MIT | TypeScript | 2026-08-05 | The agent engineering platform | |
| windmill-labs/windmill | 17,468 | NOASSERTION | Rust | 2026-08-07 | Open-source developer platform to power your entire infra and turn scripts into | |
| projectdiscovery/katana | 17,283 | MIT | Go | 2026-08-05 | A next-generation crawling and spidering framework. | |
| Unstructured-IO/unstructured | 15,274 | Apache-2.0 | HTML | 2026-08-04 | Convert documents to structured data effortlessly. Unstructured is open-source E | |
| browserless/browserless | 13,559 | NOASSERTION | TypeScript | 2026-08-07 | Deploy headless browsers in Docker. Run on our cloud or bring your own. Free for | |
| apify/crawlee-python | 9,410 | Apache-2.0 | Python | 2026-08-06 | Crawlee—A web scraping and browser automation library for Python to build reliab | |
| modelcontextprotocol/modelcontextprotocol | 8,879 | NOASSERTION | TypeScript | 2026-08-06 | Specification and documentation for the Model Context Protocol | |
| litestar-org/litestar | 8,376 | MIT | Python | 2026-08-07 | Light, flexible and extensible ASGI framework | |
| cloudquery/cloudquery | 6,479 | MPL-2.0 | Go | 2026-08-07 | Data pipelines for cloud config and security data. Build cloud asset inventory, | |
| apache/nifi | 6,187 | Apache-2.0 | Java | 2026-08-06 | Apache NiFi | |
| dlt-hub/dlt | 5,714 | Apache-2.0 | Python | 2026-08-07 | data load tool (dlt) is an open source Python library that makes data loading ea | |
| SuiteCRM/SuiteCRM | 5,637 | AGPL-3.0 | PHP | 2026-07-31 | SuiteCRM - Open source CRM for the world | |
| camunda/camunda | 4,237 | Java | 2026-08-07 | Process Orchestration Framework | ||
| apache/tika | 3,952 | Apache-2.0 | Java | 2026-08-06 | The Apache Tika toolkit detects and extracts metadata and text from over a thous | |
| espocrm/espocrm | 3,198 | AGPL-3.0 | PHP | 2026-08-06 | EspoCRM – Open Source CRM Application | |
| meltano/meltano | 2,583 | MIT | Python | 2026-08-07 | Meltano: the declarative code-first data integration engine that powers your wil | |
| microsoft/Agents | 1,024 | MIT | TypeSpec | 2026-08-04 | The Microsoft 365 Agent SDK simplifies building full stack, multichannel, truste | |
ai16z_eliza |
— | — | — | — | — | Moved Permanently |
apify_apify |
— | — | — | — | — | Not Found |
boxyhq_jackson |
— | — | — | — | — | Moved Permanently |
gventuri_pandas-ai |
— | — | — | — | — | Moved Permanently |
modelcontextprotocol_mcp |
— | — | — | — | — | Not Found |
openai_openai-agents-node |
— | — | — | — | — | Not Found |
vectara_ragfinder |
— | — | — | — | — | Not Found |