# Lay of the Land

> An evidence-linked field guide to the sources and systems used by search agents. Coverage and placement are not rankings or endorsements.

Canonical: https://www.searchforagents.com/market-map
Reviewed: 2026-09-24

Point-in-time backtesting is marked only where a provider documents access to information available as of a specified date. A date filter alone does not qualify. Exa's snapshot applies to current search candidates and does not reconstruct historical ranking.

## Across source domains

Products with documented coverage spanning multiple source types.

- [Valyu](https://docs.valyu.ai/api-reference/endpoint/search) - Web + selectable specialist sources (sources: web, finance, science); [point-in-time access documented](https://docs.valyu.ai/api-reference/endpoint/search)
- [AlphaSense](https://developer.alpha-sense.com/) - Market and company research (sources: web, finance)
- [Perplexity](https://www.perplexity.ai/hub/blog/introducing-finance-search-in-the-agent-api) - Web, finance & academic-source search (sources: web, finance, science)

## Web discovery

Indexes and APIs for finding live public web content.

- [Brave Search](https://brave.com/search/api/) - Independent web index (sources: web)
- [You.com](https://you.com/docs/api-reference/search/v1-search) - Web and news search API (sources: web)
- [Exa](https://docs.exa.ai/reference/the-exa-index) - Web index + select private sources (sources: web, finance, science); [point-in-time access documented](https://exa.ai/docs/search/snapshot)
- [Tavily](https://docs.tavily.com/documentation/api-reference/endpoint/search) - Agent search API (sources: web)
- [Parallel](https://parallel.ai/products/search) - Search API for agents (sources: web)
- [Linkup](https://www.linkup.so/) - Web search API (sources: web)
- [Kagi](https://help.kagi.com/kagi/api/search.html) - Search results API (sources: web)
- [SerpApi](https://serpapi.com/search-api) - Search results API (sources: web)
- [Serper](https://serper.dev/) - Google search results API (sources: web)
- [SearchApi](https://www.searchapi.io/docs/google) - Search engine results API (sources: web)
- [Mojeek](https://www.mojeek.com/services/search/web-search-api/) - Independent web search API (sources: web)
- [Keenable](https://docs.keenable.ai/) - Web search and page content API (sources: web); [point-in-time access documented](https://docs.keenable.ai/mcp-server)
- [Seltz](https://docs.seltz.ai/api-reference/search) - Ranked web search API for agent workflows (sources: web)
- [Olostep](https://www.olostep.com/endpoints) - Web search and content extraction APIs (sources: web)
- [Nimble](https://docs.nimbleway.com/nimble-sdk/web-tools/search) - Live web search with structured results (sources: web)
- [TinyFish](https://docs.tinyfish.ai/search-api) - Web and research-paper search API (sources: web, science)

## Financial intelligence

Market, company, filing, transcript, and economic data.

- [Bloomberg](https://www.bloomberg.com/professional/) - Professional market data (sources: finance)
- [FactSet](https://www.factset.com/) - Company and market data (sources: finance)
- [LSEG](https://www.lseg.com/en/data-analytics) - Markets and news data (sources: finance)
- [S&P Capital IQ](https://www.spglobal.com/marketintelligence/) - Company intelligence (sources: finance)
- [Massive](https://www.massive.com/) - Market data APIs (sources: finance)
- [Alpha Vantage](https://www.alphavantage.co/) - Financial data APIs (sources: finance)
- [SEC EDGAR](https://www.sec.gov/search-filings/edgar-application-programming-interfaces) - Public filings API (sources: finance)
- [FRED](https://fred.stlouisfed.org/docs/api/fred/) - Economic data API (sources: finance)
- [Intrinio](https://docs.intrinio.com/documentation/api_v2/getting_started) - Fundamentals and market data (sources: finance)
- [Financial Modeling Prep](https://site.financialmodelingprep.com/developer/docs/quickstart) - Company financials API (sources: finance)
- [Quartr](https://quartr.com/products/quartr-api) - Earnings and filings API (sources: finance)

## Scientific literature

Papers, citations, preprints, patents, and biomedical records.

- [Semantic Scholar](https://www.semanticscholar.org/product/api) - Research graph API (sources: science)
- [OpenAlex](https://docs.openalex.org/) - Scholarly graph (sources: science)
- [Crossref](https://www.crossref.org/documentation/retrieve-metadata/rest-api/) - DOI metadata (sources: science)
- [arXiv](https://info.arxiv.org/help/api/) - Research preprints (sources: science)
- [PubMed](https://pubmed.ncbi.nlm.nih.gov/) - Biomedical index (sources: science)
- [Europe PMC](https://europepmc.org/RestfulWebService) - Life science literature (sources: science)
- [CORE](https://core.ac.uk/services/api) - Open access papers (sources: science)
- [Lens](https://docs.api.lens.org/) - Scholarly and patent data (sources: science)
- [Dimensions](https://docs.dimensions.ai/dsl/data-sources.html) - Research data platform (sources: science)
- [OpenAIRE Graph](https://graph.openaire.eu/docs/apis/graph-api/) - Scholarly knowledge graph API (sources: science)
- [OpenCitations](https://api.opencitations.net/index/v2) - Open citation and reference API (sources: science)
- [DataCite](https://support.datacite.org/docs/rest-api) - Research DOI metadata API (sources: science)
- [bioRxiv](https://www.biorxiv.org/about-biorxiv) - Life sciences preprint archive (sources: science)
- [medRxiv](https://www.medrxiv.org/content/about-medrxiv) - Medical and health sciences preprints (sources: science)
- [ChemRxiv](https://chemrxiv.org/) - Chemistry preprint repository (sources: science)

## Retrieval systems

Search engines and vector stores for private corpora.

- [Elasticsearch](https://www.elastic.co/elasticsearch) - Search and vector engine
- [OpenSearch](https://opensearch.org/) - Search and vector engine
- [Pinecone](https://www.pinecone.io/) - Vector database
- [Weaviate](https://weaviate.io/) - Vector database
- [Qdrant](https://qdrant.tech/) - Vector database
- [Milvus](https://milvus.io/) - Vector database
- [Vespa](https://docs.vespa.ai/en/learn/tutorials/hybrid-search) - Hybrid search engine
- [Typesense](https://typesense.org/docs/28.0/api/vector-search.html) - Search and vector engine
- [Chroma](https://docs.trychroma.com/reference/search) - Search database
- [Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) - Full-text, vector and hybrid search
- [LanceDB](https://docs.lancedb.com/) - Multimodal and hybrid retrieval
- [turbopuffer](https://turbopuffer.com/docs) - Vector and full-text search engine
- [Redis Search](https://redis.io/docs/latest/develop/ai/search-and-query/) - Indexed text and vector search
- [ZeroEntropy](https://docs.zeroentropy.dev/zsearch) - Managed search with parsing, embeddings, and reranking

## Data platforms

Databases and warehouses used as agent systems of record.

- [PostgreSQL](https://www.postgresql.org/) - Relational database
- [MongoDB Atlas](https://www.mongodb.com/atlas) - Document and vector data
- [Snowflake](https://www.snowflake.com/) - Data cloud
- [BigQuery](https://cloud.google.com/bigquery) - Data warehouse
- [ClickHouse](https://clickhouse.com/) - Analytics database
- [Supabase](https://supabase.com/) - Postgres platform
- [Databricks](https://docs.databricks.com/aws/en/introduction/) - Governed data lakehouse
- [Amazon Redshift](https://docs.aws.amazon.com/redshift/latest/dg/welcome.html) - Managed SQL data warehouse
- [SingleStore](https://docs.singlestore.com/cloud/getting-started-with-singlestore-helios/) - SQL database for applications and analytics
- [Neon](https://neon.com/docs/introduction) - Serverless Postgres platform

## Acquisition & extraction

Crawlers, browser runtimes, and document extraction tools.

- [Firecrawl](https://www.firecrawl.dev/) - Web extraction (sources: web)
- [Apify](https://apify.com/) - Web automation
- [Browserbase](https://www.browserbase.com/) - Browser runtime
- [Jina Reader](https://jina.ai/reader/) - Reader API
- [Diffbot](https://www.diffbot.com/) - Knowledge graph extraction
- [ScrapingBee](https://www.scrapingbee.com/) - Extraction API
- [Bright Data](https://docs.brightdata.com/products/scrapers/overview) - Web scraping and structured data API (sources: web)
- [Zyte API](https://docs.zyte.com/zyte-api/get-started.html) - Web scraping and automatic extraction (sources: web)
- [Unstructured](https://docs.unstructured.io/overview-sdk-api) - Document parsing and data pipelines
- [LlamaParse](https://developers.llamaindex.ai/llamaparse/parse/) - Layout-aware document parsing
- [Docling](https://docling-project.github.io/docling/) - Open-source document conversion

## Embedding models

Models that turn queries and documents into vectors for semantic retrieval.

- [Cohere Embed](https://docs.cohere.com/reference/embed) - Text and image embedding API
- [Voyage AI Embeddings](https://docs.voyageai.com/docs/embeddings) - Text and multimodal embedding models
- [Jina Embeddings](https://jina.ai/embeddings/) - Text and multimodal embedding API
- [OpenAI Embeddings](https://platform.openai.com/docs/guides/embeddings) - Text embedding API
- [Vertex AI Embeddings](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api) - Google Cloud text embedding models

## Reranking

Models that reorder a candidate set after initial search.

- [Cohere Rerank](https://docs.cohere.com/docs/rerank-overview) - Query-document relevance reranking API
- [Voyage AI Rerank](https://docs.voyageai.com/docs/reranker) - Cross-encoder reranking models
- [Jina Reranker](https://jina.ai/reranker/) - Multilingual and multimodal reranking API
- [Pinecone Inference](https://docs.pinecone.io/guides/inference/rerank) - Hosted reranking API for search results
- [BGE Reranker](https://huggingface.co/BAAI/bge-reranker-large) - Open-weight cross-encoder reranking models

## Evaluation & observability

Tools for measuring retrieval relevance, answer quality, and traces.

- [Ragas](https://docs.ragas.io/en/stable/concepts/metrics/overview/) - Retrieval and answer evaluation metrics
- [Arize Phoenix](https://docs.arize.com/phoenix/evaluation/how-to-evals/running-pre-tested-evals/retrieval-rag-relevance) - Retrieval traces and relevance evaluation
- [LangSmith](https://docs.langchain.com/langsmith/evaluation) - Datasets, traces, and application evaluation
- [DeepEval](https://deepeval.com/docs/getting-started-rag) - RAG evaluation tests and metrics