Serverless search database
Search your data
Version every change
Vector, full-text, and hybrid search with built-in data versioning. Scale on demand, with $0 compute when idle.
Set up with your AI agent
Copy this prompt into your coding agent.
Set up LambdaDB for this project. Read https://docs.lambdadb.ai/guides/get-started/with-an-agent.md and follow the setup instructions.
Solution
Agent memory
Build agent memory without graphs or LLM bookkeeping. Search original conversations for the context each answer needs.
See memory in action- Mean answer input tokens
- 95% fewer
- 105,183 → 4,886 per answer
- Answer accuracy
- 96.0%
- vs. 95.2% with full history
- Compute cost
- $0
- when idle
Agent memory benchmark: Token and accuracy figures: 500 English LongMemEval-S questions. Results vary by model, data, and retrieval configuration. Methodology
Estimate your savings
For answers that use conversation history. Assumes 95% fewer input tokens; actual savings vary.
$2 / 1M input tokens
M = million · B = billion · T = trillion
Estimated input-cost savings
Assumptions & rates
Illustrative gross input-cost savings, not a total bill or net savings estimate. Applies the benchmark’s rounded 95% input-token reduction to your selected model; this reduction was not measured for every model listed.
Uses standard paid, uncached text-input rates in USD for base/short-context requests. Excludes output tokens, caching and batch discounts, long-context and regional premiums, and LambdaDB storage, search, embedding, and reranking costs.
Rates checked 2026-11-13; applied for 2026-11-14 (UTC). Gemini 4 Carbon and Argon are $2 / 1M input tokens through November 30, 2026, then $4 from December 1, 2026. Provider rates may change.
OpenAI pricingAnthropic pricingGoogle pricingBenchmark methodology
Version control
Manage your data like code
Keep a history of your data, make changes on branches, and choose which version your application reads.
Versioning primitives
Tags
Pin an immutable version for reproducible reads.
Aliases
Switch application reads between branches or tags, including a prior tagged version.
Branches
Keep ongoing updates on separate version histories within a collection.
Scaling
Scales with your workload $0 compute when idle
Hybrid search fans out one request into parallel queries; agents stack writes on top of every read. The burst lands on your biggest day.
Provisioned capacity can leave you paying for idle resources, while request quotas can constrain a burst. LambdaDB manages capacity for you.
Features
Production-grade search, included in every plan
No platform fees or minimum monthly charges. Hybrid search, filters, consistent reads, and language-specific text analyzers are available on every plan, including free.
From text and images to relevant results
Generate embeddings from text and images, combine full-text and vector search with filters, and rerank results with native integrations. Bring your own vectors if you prefer.
Native embeddings Native rerankingts
// Hybrid search with a native embedding fieldconst results = await client.collection("kb").query({ size: 10, query: { rrf: [ { queryString: { query: 'title:(refund OR policy)^2.5 OR content:lambdadb~2' } }, { knn: { filter: { queryString: { query: "metadata.type:guide" } }, field: "content_embedding", queryText: "refund policy update", k: 10 } }, ], },});// Hybrid search with native embeddingsconst kb = client.collection("kb");const results = await kb.query({ size: 10, query: { rrf: [ { queryString: { query: 'title:policy^2 OR refund~1' } }, { knn: { filter: { queryString: { query: "metadata.type:guide" } }, field: "content_embedding", queryText: "refund policy", k: 10 } }, ], },});Works with your AI stack: MCP server for Claude, Cursor, and any MCP client · Python, TypeScript, and Go SDKs · REST · LangChain · MCP setup guide →
Guides for migrating from Elasticsearch, Pinecone, and Qdrant →
Safety
Isolated, encrypted, recoverable
What happens to your data, in plain terms.
Isolation
API keys are scoped to one project. A key can't read another project's data.
Data residency
Data lives in the AWS region you choose, and stays there.
Durability
Object storage underneath, replicated across availability zones.
Recovery
Roll back to any tagged version, and search past versions to see what changed.
Encrypted at rest and in transit · SOC 2 Type II in progress.
Stay on the Frontier
FAQFrequently asked questions
LambdaDB is a serverless search database combining vector, full-text, and hybrid search with built-in data versioning.
Store original conversation text in LambdaDB and search for relevant passages when a new question arrives. Your application combines those passages with recent messages to build the answer prompt. SillyMemory shows this approach in a working example.
Explore SillyMemory →You pay for storage, reads, and writes — compute is $0 between requests. Your documents, vectors, and indexes live in object storage, a durable layer with no compute attached. Query and indexing workers spin up per request and disappear when the burst passes, so there are no always-on index servers to bill.
Create a branch to isolate changes, use a tag to pin a version, and point an alias at the branch or tag your application should read. You can search a selected version and switch the alias when you're ready.
Explore data versioning →It is, if you hit cold storage on every query. LambdaDB keeps frequently-read data in a cache layer the system manages for you, so most reads never touch the object store. Measured on 22M Cohere-V3 vectors (1024-dim): P99 280 ms at 128 QPS.
Limits and pricing in the docs →In durable object storage, in the region you choose, isolated per project. A write is durable once acknowledged and becomes searchable within seconds. When a query needs to see its own writes immediately, enable consistent reads — conditions and limits are in the search guide.
Search guide →Either way works. Bring your own vectors, or use native embeddings to generate vectors from text and images and embed queries with the configured model.
Didn't find your question? Ask in the community Slack or talk to us.
Search at any scale
Stay in control of every version
Hybrid search with no clusters to size. Update data on branches, pin versions, and manage reads with aliases.