Tigris vs Weaviate
Side-by-side trajectory, velocity, and editorial themes.
Tigris turns its object store into agent infrastructure with Agent Kit, agent-shell, and durable global streams.
Tigris's release stream is a sustained product-marketing push around AI-agent storage primitives. Agent Kit landed as a TypeScript SDK exposing bucket forks, workspaces, checkpoints, and event coordination. agent-shell put a virtual bash environment with persistent storage in front of those primitives. Durable global streams via S2 Lite extended the object store into a streaming substrate suitable for per-agent reasoning traces. Around the launches, case studies and tutorials (Basic Memory, the $10 self-updating knowledge base) make the pitch concrete.
Tigris is staking a position that the right substrate for AI agents is not a database, vector store, or queue — it is a globally-distributed, fork-able object store. Each blog and SDK in this batch reinforces that thesis from a different angle: storage as message queue, fork-per-agent sandboxing, storage-protected agent containment, streams for reasoning traces. The competitive map being drawn includes R2, S3 Express, Backblaze, and the agent-runtime vendors (Modal, E2B), not other databases.
Expect a managed Vector or Lance-index surface on top of buckets to compete more directly with Turbopuffer and Pinecone, and a Python counterpart to the @tigrisdata/agent-shell TypeScript runtime to widen the agent-developer surface area.
Weaviate is rebuilding around agent memory and MCP, not just vector storage.
Weaviate's recent feed is anchored by two strategic releases: the 1.37 release with a built-in MCP Server, Diversity Search, and Query Profiling, and Engram — a managed memory service for agents. Surrounding work makes the AI-native database real on more clouds (Shared Cloud GA on AWS US-East and Europe) and surfaces (C# managed client, hybrid-search tokenization improvements). Engineering blogs lean into RAG quality and multimodal embeddings.
The product is rotating from 'vector database' positioning toward 'memory and retrieval substrate for AI agents.' The combination of MCP server in core, Engram as a managed offering, and dogfooding inside Claude Code suggests agent memory is the next category Weaviate intends to own — distinct from raw vector storage, where Pinecone and Pgvector continue to crowd the market.
Expect Engram to expand integrations beyond Claude Code (Cursor, Cline, custom agent frameworks) and a clearer pricing surface for memory-as-a-service. The MCP server in 1.37 should evolve from preview to GA with curated tool catalogs.
See more alternatives to Tigris →
See more alternatives to Weaviate →