Amsterdam, Netherlands, February 21, 2026 (GLOBE NEWSWIRE) — February 20, 2026 – Weaviate, the leading open-source AI database, today announced the launch of Weaviate Agent skillsan innovative open-source repository that equips popular coding agents such as Claude Code, Cursor, GitHub Copilot, VS Code and Gemini CLI with precise tools for generating production-ready code focused on Weaviate workflows.
This release builds directly on Weaviate’s Query Agent, which was first previewed in March 2025 and will become generally available in September 2025. The Query Agent supports natural language queries across multiple collections, with multi-collection routing, intelligent query expansion, parsing for complex queries, user-defined filters, and reordering for optimal results. Developers can immediately test Agent Skills using Weaviate Cloud’s free Sandbox clusters—small instances designed for 14-day experiments that can be expanded or upgraded to shared cloud production setups.
Extensive storage tools
Up the warehouse github.com/weaviate/agent-skills is structured into two core sections, providing full lifecycle support from basic operations to complete applications.
Weaviate Skills in the /skills/weaviate directory provide detailed scripts for important tasks. These include cluster management, such as schema inspection, collection creation, and metadata retrieval; data lifecycle operations, including imports from CSV, JSON, or JSONL files plus sample data generation; agent search powered by Query Agent; and advanced retrieval options such as hybrid search (combining semantic keywords and keywords with alpha parameters), pure semantic or keyword modes.
Cookbooks in the /skills/weaviate-cookbooks directory provide end-to-end blueprints for production apps. Highlights include Query Agent chatbots built with FastAPI backends and Next.js frontends; multimodal PDF RAG pipelines using ModernVBERT for multivector embedding in addition to Ollama or Qwen3-VL for generation; basic, advanced and agentic RAG implementations with decomposition and refactoring; and DSPy optimized agents with custom tools and persistent memory.
Six streamlined slash commands
Agent Skills introduces six intuitive commands that AI coding agents can automatically discover and execute, streamlining Weaviate interactions:
- /weaviate:ask: Provides AI-generated answers with quotes via Query Agent.
- /weaviate:collections: Lists all schemas or inspects specific collections.
- /weaviate:explore: Shows data statistics, counts and sample objects.
- /weaviate:fetch: Retrieves objects by ID or filters by properties.
- /weaviate:query: Performs natural language queries on collections.
- /weaviate:search: Performs hybrid, semantic, or keyword searches with parameters such as alpha blending.
For example, developers can run “/weaviate:search query ‘best laptops’ collection ‘Products’ type ‘hybrid’ alpha ‘0.7’” for balanced retrieval or “/weaviate:ask What are the benefits of vector databases?” against a documentation collection.
The vision of CEO Bob van Luijt
Bob van Luijt, co-founder and CEO of Weaviate, which he launched in March 2019 as an open-source vector search engine, shared launch insights. “Weaviate Agent Skills bridges the gap between fast AI coding and reliable infrastructure, allowing developers to build advanced AI systems without debugging agents’ hallucinations,” said Van Luijt.
As a prominent Netherlands-based technology entrepreneur, Van Luijt is an advocate of open-source AI tools. He positions Weaviate as a “battery inclusive” stack that combines vector search, structured filtering, and agentic capabilities for modern AI applications.
Direct installation for developers
Integration is designed for speed. Install with a single command such as npx skills, add weaviate/agent-skills or via plugin managers in tools such as Claude Code. Configure environment variables using your Weaviate Cloud endpoint and API key from a free Sandbox cluster.
Run /weaviate:quickstart for guided installation. This launch continues Weaviate’s 2025 momentum, including Query Agent GA, enhanced TypeScript/Python SDKs, multi-turn conversations, streaming responses, and new C#/Java clients for broader ecosystem support.
Weaviate invites the community to star the repository, submit pull requests for new cookbooks, and participate in discussions on GitHub, the Weaviate Forum, Slack Workspace, and X.
Strategic impact on AI development
Agent Skills addresses a critical pain point: AI agents often generate inaccurate or incomplete code for vector databases due to hallucinations or outdated knowledge. By offering verified, modular tools, Weaviate enables faster iteration from prototype to production.
Early adopters report a threefold reduction in debug time for RAG pipelines and agentic apps. The repository’s modular design also facilitates contributions, with plans for expanded capabilities that include generative modules, rental isolation, and hybrid cloud deployments.
About Weaviate
Weaviate is an open-source AI database that provides storage, retrieval, and orchestration for generative AI at scale. Supported by enterprise-grade Weaviate Cloud services, it enables agentic workflows – from simple semantic search to complex multi-agent systems – and delivers sub-second latency on billions of objects.
Media contact:
Filip Vollet
PR@weaviate.io
+49-160-96488554
