Free Nano
Free
One shared-capacity project per organization
- Included scope
- 500 MiB; 100K vectors; 100K graph units
Postgres retrieval for AI applications · Official-source review 2026-10-09
Polygres adds graph, vector, full-text and hybrid retrieval over PostgreSQL for AI context. Developers can host a database or synchronize selected existing data, explore retrieval in a playground and use a CLI or Python SDK.
Relevant to developers building retrieval grounded in Postgres data and relationships.
Basic from $16/project/month: isolated Postgres, 2 GiB storage, 200K vectors/graph units. Extra GiB $2, 100K vectors $3, 100K graph units $1. Graph units = nodes plus edges/10. Increasing free capacity switches all dimensions to Basic minimum; final dashboard quote includes adjustments/credits. Synchronized data still consumes selected-data/index capacity. Open pgGraph/pgContext engines are distinct from managed service; their license terms require repo checks. Advertised recall/latency benchmark is dataset-specific and not reproduced. No database connected or query run.
Use synthetic Postgres data, measure recall and latency on representative queries and inspect synchronization scope and capacity quote before connecting production.
Basic from $16/project/month: isolated Postgres, 2 GiB storage, 200K vectors/graph units. Extra GiB $2, 100K vectors $3, 100K graph units $1. Graph units = nodes plus edges/10. Increasing free capacity switches all dimensions to Basic minimum; final dashboard quote includes adjustments/credits. Synchronized data still consumes selected-data/index capacity. Open pgGraph/pgContext engines are distinct from managed service; their license terms require repo checks. Advertised recall/latency benchmark is dataset-specific and not reproduced. No database connected or query run.
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | Polygres adds graph, vector, full-text and hybrid retrieval over PostgreSQL for AI context. Developers can host a database or synchronize selected existing data, explore retrieval in a playground and use a CLI or Python SDK. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Basic from $16/project/month: isolated Postgres, 2 GiB storage, 200K vectors/graph units. Extra GiB $2, 100K vectors $3, 100K graph units $1. Graph units = nodes plus edges/10. Increasing free capacity switches all dimensions to Basic minimum; final dashboard quote includes adjustments/credits. Synchronized data still consumes selected-data/index capacity. Open pgGraph/pgContext engines are distinct from managed service; their license terms require repo checks. Advertised recall/latency benchmark is dataset-specific and not reproduced. No database connected or query run. | Facts sourced | 2026-10-09 |
Understand the total cost
Free Nano
Free
One shared-capacity project per organization
Basic
$16.00 /mo
Per project/month plus selected capacity
Enterprise
Not listed
Custom capacity/deployment agreement
chat-recall stores coding conversations for full-text and knowledge-graph retrieval. It offers MCP access, analytics and code-related findings, with hosted and self-hosted deployment options.
Explore toolBrandfetch provides searchable brand logos, colors, fonts and company context through web search and APIs. Brands can claim their profiles, while developers use separate logo, search and full-brand data endpoints to enrich applications and agent workflows.
Explore toolActx0 stores agent sessions and extracts compact memories for semantic retrieval before the next model reply. Managed workspaces include knowledge search, memory consolidation, keys, audit events and usage tracking.
Explore toolThe practical questions
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
Polygres adds graph, vector, full-text and hybrid retrieval over PostgreSQL for AI context. Developers can host a database or synchronize selected existing data, explore retrieval in a playground and use a CLI or Python SDK.
One Free Nano project per organization across hosted/synchronized projects: 500 MiB storage, 100K vectors and 100K graph units on shared capacity.. This record lists ongoing free access; check the plan limits before starting.
The listed monthly price is $16.00 USD at monthly billing. See the plan cards for entitlements, billing commitments and seat minimums.
Unified retrieval API and typed Python SDK are advertised; CLI manages projects, imports and configuration.. API access and subscription access may have different terms; consult the linked sources.
Basic from $16/project/month: isolated Postgres, 2 GiB storage, 200K vectors/graph units. Extra GiB $2, 100K vectors $3, 100K graph units $1. Graph units = nodes plus edges/10. Increasing free capacity switches all dimensions to Basic minimum; final dashboard quote includes adjustments/credits. Synchronized data still consumes selected-data/index capacity. Open pgGraph/pgContext engines are distinct from managed service; their license terms require repo checks. Advertised recall/latency benchmark is dataset-specific and not reproduced. No database connected or query run.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Current official product source read individually; product artwork inspected visually.
Read original source ↗Official pricing and billing restrictions read individually.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.