Comparisons / DSPy vs Mastra

DSPy vs Mastra: Which Agent Framework to Use?

DSPy vs Mastra, head to head

DSPy and Mastra both let you build an agent, but they sit in different parts of the stack and they assume different things about who's writing the code.

DSPy replaces hand-written prompts with compiled modules.

Mastra is a TypeScript-first framework for building AI agents, from the team behind Gatsby.

Underneath, both wrap the same thing: a model call, a tool dispatch, a loop. The decision is about which abstraction your team wants to think in day to day, and which ecosystem you're willing to inherit along with it. There's an honest, framework-free version of the same pattern in about 60 lines of Python in the lesson at the bottom of this page — useful as a baseline regardless of which framework wins.

Pick DSPy if

Pick DSPy if dSPy's real innovation is automated prompt optimization — replacing manual prompt engineering with algorithmic tuning. This is genuinely novel and valuable for production systems where prompt quality matters at scale. For simple agents or learning, hand-written prompts are easier to understand and modify. The tradeoffs in its intro should match how your team already thinks about agents; Mastra will feel like translation if they don't.

Full DSPycomparison →

Pick Mastra if

Pick Mastra if mastra is the best option for TypeScript teams that want a batteries-included agent framework without leaving the Node.js ecosystem. The workflow engine and Studio are genuinely productive. For simple agents or Python teams, the plain approach avoids an unnecessary dependency. The tradeoffs in its intro should match how your team already thinks about agents; DSPy will feel like translation if they don't.

Full Mastracomparison →

What both add

Whichever you pick, you're inheriting a dependency tree and a vocabulary your team has to learn before they ship anything. DSPy has its own class hierarchy and tool registration conventions; Mastra has its. Either way, when something misbehaves you'll be reading framework source before you reach the actual HTTP call.

If the real workload is one model and a handful of tools, both can feel like a workbench for driving a nail. The lesson below builds the same pattern in plain Python — useful as a comparison point even if you ultimately keep the framework.

By the numbers

By the numbers

DSPy

GitHub Stars

33.4k

Forks

2.8k

Language

Python

License

MIT

Created

2023-01-09

Created by

Stanford NLP (Omar Khattab)

github.com/stanfordnlp/dspy

Mastra

GitHub Stars

22.7k

Forks

1.8k

Language

TypeScript

License

Apache-2.0

Created

2024-08-06

Created by

Mastra AI

Backed by

Spark Capital, Y Combinator

Funding

Series A ($22M, Apr 2026 — $35M total)

Weekly downloads

244.0k

github.com/mastra-ai/mastra

GitHub stats as of April 2026. Stars indicate community interest, not necessarily quality or fit for your use case.

ConceptDSPyMastra
Agent`dspy.ReAct` module with signature and tools`new Agent({ model, instructions, tools })` with automatic tool dispatch
Prompts`dspy.Signature` defines input/output fields, compiled to optimized prompts
Optimization`dspy.BootstrapFewShot`, `MIPROv2` auto-tune prompts against a metric
ToolsTools passed to `ReAct` module as callable list`createTool({ name, schema, execute })` with Zod validation
Chaining`dspy.ChainOfThought`, `dspy.Module` with `forward()` composition
Evaluation`dspy.Evaluate` with metric functions and dev sets
Workflows`Workflow` class with `.step()`, `.then()`, `.branch()` for orchestration
RAGBuilt-in document syncing, chunking, embedding, and vector search
MemoryShort-term thread memory + long-term vector memory across sessions
StudioMastra Studio: local GUI for testing agents, viewing traces, debugging

Or build your own in 60 lines

Both DSPy and Mastra implement the same 8 patterns. An agent is a function. Tools are a dict. The loop is a while loop. The whole thing composes in ~60 lines of Python.

No framework. No dependencies. No opinions. Just the code.

Build it from scratch →