Softwr

Databases · head to head

Dgraph vs Letta

Dgraph logo

Dgraph

Databases

Apache 2.0 distributed graph database written in Go, maintained by Hypermode, queried through GraphQL or its own DQL language.

From
Free
Free plan
Yes
Letta logo

Letta

Automation Integration

Machines that learn

From
Free
Free plan
Yes

The short version

  • Free plans on both; paid from $39/mo and $20/mo.
  • Where Letta falls short: free tier limited to 3 stateful agents.
  • Prices and features on this page were last checked on 13 November 2026.

How do Dgraph and Letta differ?

Dgraph and Letta differ on platforms and category. Only the attributes on which Dgraph and Letta actually diverge.

Attributes where Dgraph and Letta differ
AttributeDgraphLetta
PlatformsLinux, macOS, Self-hosted, WebWeb
CategoryDatabasesAutomation Integration

Identical on both: starting price (Free), pricing model (Freemium), free tier (Yes).

Not yet recorded: founded for Letta.

Which features does each one have?

They share no listed features; 10 appear only for Dgraph. Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.

Only in Dgraph

  • Apache 2.0 licence
  • Generated GraphQL API
  • DQL query language
  • Predicate sharding
  • Raft replication
  • Distributed ACID transactions
  • Written in Go
  • Full-text and geo indexing

Only in Letta

Nothing recorded that Dgraph does not also cover.

What is each one used for?

Letta is most often brought in for building agents with memory for continuous learning. The jobs each tool is most often brought in to do.

Dgraph

  • An application whose core data is a graph, such as permissions, social connections or product relationships, where the frontend already consumes GraphQLnot Letta
  • A knowledge graph that outgrew a single machine and needs storage distributed across nodes without a per-core licence negotiationnot Letta
  • Recommendation or fraud-detection features that traverse several hops at request time, where a relational join chain has become the bottlenecknot Letta
  • Teams that want a graph database they can read, fork and self-host under a permissive licence rather than a source-available onenot Letta

Letta

  • Building agents with memory for continuous learningnot Dgraph
  • Enabling reflection during idle periods via sleep-computenot Dgraph
  • Managing agent context and extracting learningsnot Dgraph

Where do Dgraph and Letta fall short?

Letta's most cited limit: free tier limited to 3 stateful agents. Documented limitations, not opinions. Every one is a constraint you would hit in normal use.

Dgraph

  • Sharding is by predicate, so a single very hot predicate lives entirely in one Raft group and cannot be split further; adding nodes does not relieve it and the fix is a data model change
  • Stewardship passed from Dgraph Labs to Hypermode after the original company stopped operating independently, so anyone building on it is betting on a second custodian rather than on the original team's roadmap
  • The GraphQL layer is generated and opinionated, so anything it does not express drops you into DQL, which is a second language your team must learn and which no other database speaks
  • The community is a fraction of Neo4j's, so operational answers, tuning experience, hiring and third-party tooling are all thinner, and unusual failure modes in a Zero and Alpha cluster leave you reading source rather than a forum
  • There is no portable graph standard to migrate to; Cypher, Gremlin and SPARQL are all different query models, so the schema and every query is a rewrite if you later leave, and that cost grows with the application

Letta

  • Free tier limited to 3 stateful agents
  • Pro tier capped at 20 stateful agents
  • API Plan usage charges apply beyond base tier

How much do Dgraph and Letta cost?

Dgraph has a free plan, with paid plans from $39/mo; Letta has a free plan, with paid plans from $20/mo. Plan by plan below, from each vendor's own pricing page.

Dgraph

Free
  • CommunityFree
    • Native GraphQL
    • Graph queries
    • Full-text search
  • Cloud$39/mo
    • Managed service
    • Auto-scaling
    • Enterprise support

Letta

Free
  • FreeFree
    • Limited agents
    • Limited Letta Auto usage
    • Bring your own API keys
  • Pro$20/mo
    • Weekly and monthly Letta Auto quota
    • Pay-as-you-go overage
    • Up to 20 stateful agents
  • API Plan$20/mo
    • Unlimited agents
    • $0.10/active agent/month
    • $0.00015/second for tool execution
  • Teams Pro$20/mo
    • Per seat pricing
    • Add teammates
    • Letta Auto quota

Which should you pick?

Choose Dgraph if

  • You need apache 2.0 licence.
  • You want to start without paying.
  • You work on Linux, macOS, Self-hosted, Web.
  • You also want generated graphql api.

Choose Letta if

  • You want to start without paying.

Questions people ask

Is Dgraph or Letta better?
Neither clearly leads. Dgraph starts at Free and Letta at Free, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
Which is cheaper, Dgraph or Letta?
Dgraph starts at Free and Letta at Free.
Does Dgraph or Letta run on more platforms?
Dgraph runs on Linux, macOS, Self-hosted, Web. Letta runs on Web.
Can I use Dgraph for free?
Both have a free tier, so you can try either at no cost before committing.
What is Dgraph best used for?
Dgraph is most often used for an application whose core data is a graph, such as permissions, social connections or product relationships, where the frontend already consumes graphql, a knowledge graph that outgrew a single machine and needs storage distributed across nodes without a per-core licence negotiation, recommendation or fraud-detection features that traverse several hops at request time, where a relational join chain has become the bottleneck, teams that want a graph database they can read, fork and self-host under a permissive licence rather than a source-available one. Of those, an application whose core data is a graph, such as permissions, social connections or product relationships, where the frontend already consumes graphql and a knowledge graph that outgrew a single machine and needs storage distributed across nodes without a per-core licence negotiation are not what Letta is typically brought in for.
What can Dgraph do that Letta cannot?
Dgraph covers Apache 2.0 licence, Generated GraphQL API, DQL query language, Predicate sharding.

Answered from the vendors’ own pages

Dgraph: Is Dgraph open source?

Yes. The current repository is Apache 2.0, which is a permissive OSI licence, and the project is at v25 under Hypermode's maintenance.

Letta: How much does Letta cost?

Letta offers a free tier, then Pro plan at $20/month with up to 20 stateful agents, API Plan at $20/month base plus usage charges ($0.10/active agent/month, $0.00015/second for tool execution), and Teams Pro at $20/seat/month.

Source
Dgraph: Is it really GraphQL?

It serves a generated GraphQL API, which is real GraphQL for clients. Its native language, DQL, resembles GraphQL syntactically but is Dgraph's own language and is not the GraphQL specification.

Letta: How many agents can I create on the free plan?

The free tier is limited to 3 stateful agents. Pro plan allows up to 20 stateful agents, while API Plan offers unlimited agents.

Source
Dgraph: How does it compare to Neo4j?

Neo4j has the larger ecosystem, Cypher, and far more operational precedent. Dgraph distributes storage across nodes by default and gives you a GraphQL endpoint without writing resolvers. The choice usually turns on whether you need horizontal scale and a GraphQL surface more than you need ecosystem depth.

Letta: Does Letta charge for tool execution?

On the API Plan, Letta charges $0.00015 per second for tool execution. The Pro and Teams Pro plans include execution in their monthly fee.

Source
Dgraph: What does a production cluster look like?

At minimum a set of Zero nodes for coordination and a replicated set of Alpha nodes for data, typically three of each for fault tolerance, which is a meaningfully larger operational footprint than a single graph server.

Dgraph: Who maintains it now?

Hypermode. Dgraph Labs, the original company, no longer operates it, and that change of custodian is the main non-technical risk to weigh.

Share

Related pages

Other head to heads