The strongest open-source alternatives to DSPy for building AI agents — agent frameworks ranked by GitHub traction, each with a head-to-head.
Short answer: the closest alternative to DSPy is AutoGen (★ 60k), the most-starred agent frameworks; CrewAI and LlamaIndex are also strong.
✓ Live data verified
DSPy (★ 37k) is Programming — not prompting — language models: compile declarative pipelines into optimized prompts/weights. If it is not the right fit, these 11 agent frameworks cover the same ground — AutoGen is the most-starred option below. Or browse the best agent frameworks and DSPy's own page.
Microsoft's framework for multi-agent conversation, with a programming model for agents that talk to each other and tools. Best for conversational multi-agent.
Role-playing autonomous agents that collaborate as a 'crew' with defined roles, goals, and task delegation. Best for role-based multi-agent teams.
Data framework for connecting LLMs to private data — indexing, retrieval, and agentic RAG over your documents. Best for RAG.
Batteries-included agent runtime — built-in memory, knowledge/RAG, and AgentOS, a control plane you run in your own cloud. Formerly Phidata. Best for full-stack agents.
Graph-based orchestration for stateful, multi-actor agent workflows with explicit control flow and checkpointing. Best for stateful multi-agent workflows.
OpenAI's lightweight agent framework — a small set of primitives (Agents, Handoffs, Guardrails, Sessions); provider-agnostic via LiteLLM. Evolved from Swarm. Best for minimal orchestration.
Google's Agent Development Kit — a code-first, model-agnostic toolkit for building, evaluating, and deploying multi-agent systems. Optimized for Gemini. Best for multi-agent systems.
Type-safe agent framework from the Pydantic team — structured outputs, dependency injection, and model-agnostic agents. Best for type-safe agents.
Anthropic's SDK for building agents on Claude — the harness behind Claude Code, with in-process tools, hooks, and an interactive client. Formerly the Claude Code SDK. Best for Claude-native agents.
AWS's model-driven agent SDK — give it a prompt and tools and let the model plan, call tools, and reflect in a loop. First-class Bedrock, MCP-native, OpenTelemetry tracing. Best for AWS/Bedrock agents.
TypeScript-first SDK for stateful agents where each agent is a Durable Object — embedded SQLite, WebSockets, cron scheduling, and hibernation, running globally on Cloudflare's edge. Best for edge AI agents.
AutoGen (★ 60k) is the most-starred agent frameworks alternative to DSPy. Microsoft's framework for multi-agent conversation, with a programming model for agents that talk to each other and tools.
The strongest agent frameworks alternatives to DSPy are AutoGen, CrewAI, LlamaIndex, Agno and more — each with a head-to-head comparison.
Yes — the alternatives listed are open source and free to self-host; you bring your own model keys.
We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.