{"subject":{"id":"chroma","slug":"chroma","name":"Chroma","tagline":"Prototype on Chroma; graduate to Qdrant/pgvector/Pinecone before your corpus and QPS grow up.","website":"https://www.trychroma.com","status":"active","overall":7.88,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","lastReviewed":"2026-09-14","categoryIds":["cat-vector-memory"],"regions":["global"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14: Open-source embeddable vector DB + hosted Chroma Cloud; free/local for prototypes; Cloud usage-based for managed. Excellent DX for demos; graduate before high QPS/filtered production.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://www.trychroma.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."}},"relatedJtbdSlugs":["self-host-vector","rag-memory","prototype-rag","embedded-vector"],"alternatives":[{"id":"supabase-pgvector","slug":"supabase-pgvector","name":"Supabase (pgvector)","tagline":"Depot default for most agent apps under ~25–50M vectors. Don't add Pinecone until Postgres actually hurts.","website":"https://supabase.com","status":"active","overall":8.64,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.76,"roles":["same_jtbd_pick","same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory","prototype-rag"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Postgres + pgvector + Auth + Storage; usage on compute/storage; free tier. Vectors hitchhike on Postgres.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://supabase.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/supabase-pgvector","compare":"/compare/chroma-vs-supabase-pgvector"},{"id":"qdrant","slug":"qdrant","name":"Qdrant","tagline":"Depot pick for serious vector workloads with filters. Self-host or Cloud — either way you can leave.","website":"https://qdrant.tech","status":"active","overall":8.59,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-10-19","deltaOverallVsSubject":0.71,"roles":["same_jtbd_pick","same_jtbd_runner"],"sharedJtbdSlugs":["self-host-vector","rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Rust engine; open-source + Qdrant Cloud; excellent filtered ANN; competitive cloud pricing.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://qdrant.tech","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=self-host-vector","human":"/providers/qdrant","compare":"/compare/chroma-vs-qdrant"},{"id":"lancedb","slug":"lancedb","name":"LanceDB","tagline":"Great embedded/object-store vector layer. Pair with Mem0/Zep only if you need higher-level memory APIs.","website":"https://lancedb.com","status":"active","overall":7.78,"scoreKind":"curated_estimate","confidence":"medium","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.1,"roles":["same_jtbd_pick"],"sharedJtbdSlugs":["embedded-vector"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14: Embedded + cloud vector DB on Lance format; excellent local/OSS DX and object-storage-friendly indexing. Cloud usage-based; OSS free. Popular as RAG/memory backend (e.g. with Cognee); not a hosted 'agent memory' product itself.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://lancedb.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=embedded-vector","human":"/providers/lancedb","compare":"/compare/chroma-vs-lancedb"},{"id":"turbopuffer","slug":"turbopuffer","name":"Turbopuffer","tagline":"When your vector bill scares you and much of the corpus is cold, Turbopuffer is the interesting answer.","website":"https://turbopuffer.com","status":"active","overall":8.21,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.33,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory","embedded-vector"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-10-24 (turbopuffer.com/pricing, fetched 2026-10-24): Usage-based with plan minimums: launch '$16/month minimum usage', scale '$256/month minimum usage', enterprise '>= $4,096/month' with '35% usage premium'. 'You'll pay for actual usage beyond the minimum.' 'Unused amo…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://turbopuffer.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/turbopuffer","compare":"/compare/chroma-vs-turbopuffer"},{"id":"upstash-vector","slug":"upstash-vector","name":"Upstash Vector","tagline":"Prototype/edge RAG peer when you already on Upstash. Prefer Qdrant/Pinecone for serious filtered production…","website":"https://upstash.com/vector","status":"active","overall":8.15,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.27,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory","prototype-rag"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14 (upstash.com/pricing/vector markdown): Free $0 — 200M vectors×dims, 10K queries/day, 1GB. PAYG $0.40 per 100K requests + $0.25/GB storage (≤50GB, 99.9% SLA). Fixed $60/mo (1M queries/day). Pro contact (100B scale). Bandwidth free to 200GB then $0.03/GB.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://upstash.com/vector","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/upstash-vector","compare":"/compare/chroma-vs-upstash-vector"},{"id":"pinecone","slug":"pinecone","name":"Pinecone","tagline":"Still the zero-ops vector default. If you already run Postgres, try pgvector before paying Pinecone rents.","website":"https://www.pinecone.io","status":"active","overall":7.95,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.07,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory","prototype-rag"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Serverless + dedicated/pod tiers; usage on storage/reads/writes; Dedicated Read Nodes for high QPS.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://www.pinecone.io","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/pinecone","compare":"/compare/chroma-vs-pinecone"},{"id":"upstash-redis","slug":"upstash-redis","name":"Upstash Redis","tagline":"Default serverless-edge-redis. Use classic Redis Cloud when you need always-on fat memory / Redis modules…","website":"https://upstash.com/redis","status":"active","overall":8.49,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.61,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14 (upstash.com/pricing/redis): Free 256MB / 500K commands. PAYG $0.2 per 100K commands + $0.25/GB storage; fixed plans from $10/mo. Prod Pack +$200/db. HTTP + TCP; agents can POST https://upstash.com/start-redis for temp DBs. Separate from Upstash QStash/Vector/Box…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://upstash.com/redis","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/upstash-redis","compare":"/compare/chroma-vs-upstash-redis"},{"id":"weaviate","slug":"weaviate","name":"Weaviate","tagline":"Best when hybrid search and modularity matter. Cloud for convenience; self-host when lock-in anxiety spikes.","website":"https://weaviate.io","status":"active","overall":8.2,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.32,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["self-host-vector"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Open-source + Weaviate Cloud; modular vectorizers; hybrid search; usage/cluster pricing on cloud.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://weaviate.io","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=self-host-vector","human":"/providers/weaviate","compare":"/compare/chroma-vs-weaviate"},{"id":"zilliz","slug":"zilliz","name":"Zilliz (Milvus)","tagline":"When you're truly at massive scale, Milvus/Zilliz earns its complexity. Don't start here for a chatbot MVP.","website":"https://zilliz.com","status":"active","overall":8.16,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.28,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["self-host-vector"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Managed Milvus (Zilliz Cloud); open-source Milvus for self-host; designed for large-scale ANN.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://zilliz.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=self-host-vector","human":"/providers/zilliz","compare":"/compare/chroma-vs-zilliz"},{"id":"redis","slug":"redis","name":"Redis","tagline":"Use as agent hot memory/cache, not as your only 100M-vector archive.","website":"https://redis.io","status":"active","overall":8.07,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.19,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["rag-memory"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"Redis OSS + Redis Cloud; vector search via Redis Query Engine; pay for memory-centric hosting.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://redis.io","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=rag-memory","human":"/providers/redis","compare":"/compare/chroma-vs-redis"},{"id":"duckdb","slug":"duckdb","name":"DuckDB (vector/extensions)","tagline":"Use for local analytics + light vector experiments. Production agent memory → pgvector/Qdrant/Mem0.","website":"https://duckdb.org","status":"active","overall":8,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":0.12,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["embedded-vector"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14: DuckDB is free MIT/open-source (local/embedded). Vector similarity via VSS + community extensions — not a hosted vector SaaS. MotherDuck is the hosted DuckDB warehouse (Lite $0 with 10 GB + 10 Pulse hrs; Business $250/org/mo + usage). Treat DuckDB as local OLAP …","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://duckdb.org","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=embedded-vector","human":"/providers/duckdb","compare":"/compare/chroma-vs-duckdb"}],"rankContract":{"style":"editorial_weighted","notAnElo":true,"note":"deltaOverallVsSubject is Depot overall (0–10) minus the subject. It is not Arena Elo and not an Artificial Analysis index."},"freshness":{"scoreAsOfMin":"2026-09-14","scoreAsOfMax":"2026-10-19","contractAsOf":"2026-10-03"},"honesty":["Alternatives are other catalog providers that share a JTBD as pick or runner-up. If fewer than three exist, same-category active providers fill the list and are labeled same_category.","Overall deltas are catalog scores. kind=curated_estimate is not a lab measurement.","Pricing rows are sourced or explicitly null. Do not parse pricingNotes. A single normalized USD figure is set only for a provider with exactly one token row."],"links":{"human":"/alternatives/chroma","machine":"/api/alternatives?provider=chroma","provider":"/api/providers/chroma","canonical":"/api/canonical"}}