ai agent storage

Cloud JSON storage for AI agents.

AI agents generate structured data constantly: tool outputs, conversation logs, scraped content, task results. Sprigr gives your agent a simple REST API to store any JSON and search it instantly. No database setup, no schema design, no backend code.

Start free See how it works
sprigr · new workflow listening
Example run · 41 actions hover the gate to approve it yourself
the ai agent storage back office

Cloud-hosted: data persists across runs and machines. Schema-free JSON: store anything, change shape anytime. Built-in full-text search with no extra infrastructure. REST API works from any language, any framework. Ready in 60 seconds, no provisioning, no migrations.

You focus on the work. Sprigr runs the paperwork.

what it handles
  • Schema-free JSON
  • Full-text & semantic
  • REST API + MCP
  • Flat pricing
what it runs

Built for how agents actually work

Every feature designed around the reality of AI agent data patterns.

  • Schema-free JSON

    No tables to create, no columns to define. Push a flat key-value object today, a different shape tomorrow. Set searchable_attributes once per index (the MCP create_index tool defaults to all fields) and every record is indexed on write.

  • Full-text & semantic search

    Find records by content, not just IDs. Typo-tolerant keyword search plus optional hybrid semantic search that finds results by meaning, even when the exact words don't match.

  • Faceted filtering

    Combine text search with exact-match filters on any JSON field. Query status:complete, agent_id:agent-7, or source:web-scrape alongside free-text terms.

  • Multi-index support

    Create separate indexes for different agents, users, or data types. Indexes are isolated per tenant. Spin up a new index with a single API call.

  • REST API + MCP

    Standard REST endpoints work with curl, fetch, requests, or any HTTP client. For agents built on the Model Context Protocol, Sprigr also ships an MCP server for native tool integration.

  • Flat pricing

    Pay per records stored, not per query. No surprise bills when your agent runs a thousand searches in a loop. Free tier included for prototyping and small projects.

how it starts

How it works

Three steps from raw agent output to searchable cloud storage.

  1. 01

    Sign up and get an API key

    Create a free account and generate an API key. Keys are scoped to your account and can optionally be restricted to specific indexes, so each agent gets its own namespace.

  2. 02

    Push any JSON

    Send records to the Sprigr REST API with a single POST request. No schema to define, no migrations to run. If it's valid JSON, Sprigr stores it and indexes it for search.

  3. 03

    Retrieve and search

    Fetch records by ID for exact lookups, or use full-text search to find records by content. Add facet filters to narrow results by any field in your JSON.

Push JSON: POST /1/indexes/agent-data/batch with your records. Search it: POST /1/indexes/agent-data/query with query and filters. Retrieve by ID: GET /1/indexes/agent-data/objects/task-result-001. The same calls work from Python, JavaScript, Go, or any language with an HTTP library.

Read the API docs →
questions

Questions

What kind of data can AI agents store in Sprigr?

Any valid JSON. Conversation history, tool outputs, scraped web pages, task results, extracted facts, embeddings, user preferences. The API is schema-free, so records can have completely different shapes within the same index. If your agent produces structured data, Sprigr can store and search it.

Do I need to define a schema before storing data?

No. Sprigr is schema-free. Push a record with any JSON structure and it gets indexed automatically. You can change the shape of your records over time without migrations. Fields that appear in some records and not others just show up empty in search results.

How do I query stored data from my AI agent?

Three ways: fetch records by their objectID for exact lookups, run full-text search queries with typo tolerance, or combine free-text search with facet filters on any JSON field. All three work through the same REST API and return results in milliseconds.

Can multiple agents share the same index?

Yes. Multiple agents can read and write to the same index using the same API key, or you can give each agent its own API key. Use facet filters (for example, agent_id:agent-7) to keep each agent's records separate while still allowing cross-agent queries when needed. To enforce the separation, mint a scoped key per agent with a locked filter: the engine applies it to every query and the agent cannot remove it.

Is there an SDK, or do I have to use HTTP directly?

The REST API works with any HTTP client: curl, fetch, requests, axios, whatever you already use. For Model Context Protocol agents, we provide an MCP server (@sprigr/mcp-server) that exposes Sprigr as native tools in Claude Desktop, Claude Code, and other MCP clients.

ai agent storage

Give your agent cloud storage that just works.

Paid plans from $49 a month.

Start free Explore the platform