# Alternatives to Claude Agent SDK

> Source: https://theagentsindex.com/claude-agent-sdk/alternatives (current datasheets, evidence-ranked)

Candidates share the baseline category or are previously researched peers. Requirements, preserved strengths, explicit trade-offs and research coverage decide the order; paid tier does not.

## Shortlist

### 1. Agno

Python SDK, self-hosted AgentOS runtime and hosted control plane for building and operating agent platforms.

**Research coverage:** 35/35 criteria

**Where it improves on Claude Agent SDK:**
- [GPT: yes — OpenAI is a registered provider key with both Chat Completions and Responses adapters, plus a separate Azure OpenAI deployment adapter.](https://docs.agno.com/models/providers/model-index)
- [Open models: yes — Open-weight models run through documented local runtime adapters for Ollama, vLLM, llama.cpp and LM Studio, so inference can stay on your own hardware.](https://docs.agno.com/models/providers/model-index)
- [Model choice: yes — You choose the provider and the model, passed as a string or a class, and fallback models plus custom model classes are supported; the vendor supplies no model of its own.](https://www.agno.com/)

**Trade-offs against Claude Agent SDK:**
- [Writes tests: partial — The documented Verify stage runs the repository's existing gates; test authoring appears only in the example prompt, not as a capability claim.](https://docs.agno.com/use-cases/coding-agents)
- [In your pipeline: no — The enumerated serving surfaces are REST, MCP in Claude/ChatGPT and chat apps; no pull-request or CI surface appears.](https://www.agno.com/)
- [Pooled budget: partial — There is no metered balance to pool; seats share access to the same connected runtimes and usage inside a connection is unlimited.](https://www.agno.com/pricing)

[View Agno](https://theagentsindex.com/agno)

### 2. LangChain

Open source agent frameworks plus LangSmith, a hosted platform to trace, evaluate, deploy and govern agents.

**Research coverage:** 34/35 criteria

**Where it improves on Claude Agent SDK:**
- [Ships it: yes — LangSmith Deployment runs agents in production with one-click deploy from Studio and a control-plane API; the free Developer plan shows Deployment as N/A, so shipping starts at Plus.](https://docs.langchain.com/langsmith/studio)
- [GPT: yes — A first-party langchain-openai package covers GPT models and Azure OpenAI deployments, and the gateway accepts OpenAI Chat Completions and Responses requests for them.](https://docs.langchain.com/oss/python/integrations/chat/openai)
- [Open models: yes — Open-weight models run through local Ollama, vLLM, Hugging Face and Together integrations, and the gateway can front a self-hosted OpenAI-compatible endpoint you operate yourself.](https://docs.langchain.com/oss/python/integrations/chat/ollama)

**Trade-offs against Claude Agent SDK:**
- [Debugs and fixes: partial — LangSmith Engine diagnoses failures from production traces and opens a GitHub pull request with the fix, but a human still merges it, and Engine is absent from the free Developer plan.](https://docs.langchain.com/langsmith/engine)
- [Writes tests: partial — Engine generates ground-truth dataset examples and assertions so a fix can be evaluated offline; those are agent evals, not unit tests, and the vendor's CI guide leaves unit tests to you.](https://docs.langchain.com/langsmith/engine)
- [Self-hosted: partial — The open source frameworks run anywhere, but self-hosting or hybrid-hosting the LangSmith platform on Kubernetes is an Enterprise-plan option; Developer and Plus are cloud-only.](https://www.langchain.com/pricing)

[View LangChain](https://theagentsindex.com/langchain)

### 3. Letta

Stateful agent harness, cloud and SDK for agents with persistent, git-versioned memory.

**Research coverage:** 35/35 criteria

**Where it improves on Claude Agent SDK:**
- [GPT: yes — OpenAI API keys and ChatGPT Plus/Pro Codex subscriptions both connect; toolsets switch per model family.](https://docs.letta.com/configuration/models/index.md)
- [Open models: yes — Ollama, LM Studio and llama.cpp endpoints are local-only integrations; DeepSeek, Mistral and Together are also listed.](https://docs.letta.com/configuration/models/index.md)
- [Model choice: yes — You pick the model and can switch mid-conversation; memory travels with the agent across providers.](https://docs.letta.com/configuration/models/index.md)

**Trade-offs against Claude Agent SDK:**
- [Writes tests: partial — Vendor claims agents run test suites; it never claims they author tests.](https://docs.letta.com/handbook/index.md)
- [MCP server: no — MCP runs inbound only: Letta sessions consume stdio, HTTP and SSE MCP servers; no Letta MCP server is published.](https://docs.letta.com/agent-sdk/mcp/index.md)
- [Pooled budget: no — Quota attaches to each purchased Pro seat; unpaid seats get no Letta-hosted inference at all.](https://docs.letta.com/teams/quickstart/index.md)

[View Letta](https://theagentsindex.com/letta)

### 4. LangGraph

Open-source orchestration framework and runtime for stateful, long-running LLM agents, from LangChain.

**Research coverage:** 35/35 criteria

**Where it improves on Claude Agent SDK:**
- [GPT: yes — First-party ChatOpenAI integration, plus AzureChatOpenAI for GPT models hosted on Azure; both are listed in the featured chat-model table.](https://docs.langchain.com/oss/python/integrations/chat/openai)
- [Open models: yes — Open-weight models run locally through the ChatOllama integration, and self-hosted vLLM and Hugging Face endpoints are documented as chat-model integrations.](https://docs.langchain.com/oss/python/integrations/chat/ollama)
- [Model choice: yes — You choose the model. LangGraph does no model abstraction of its own and the vendor markets provider-independence; the featured integration table spans OpenAI, Anthropic, Google, Bedrock, Ollama and more.](https://www.langchain.com/langgraph)

**Trade-offs against Claude Agent SDK:**
- [Debugs and fixes: partial — LangGraph itself does not diagnose code; the separate LangSmith Engine product analyses LangGraph agent traces, proposes fixes and can open a pull request with one.](https://docs.langchain.com/oss/python/langgraph/overview)
- [Agent permissions: partial — There are no preset permission tiers: you decide where the agent must stop by placing interrupt() calls, which pause the graph and wait for approval before continuing.](https://www.langchain.com/langgraph)
- [Admin controls: partial — Workspace RBAC and tag-based ABAC are Enterprise-only; other plans default every user to Admin. Gateway cost controls, rate limiting and PII redaction are checked on all three plans.](https://docs.langchain.com/langsmith/rbac)

[View LangGraph](https://theagentsindex.com/langgraph)

### 5. Mastra

Open-source TypeScript framework for building AI agents, with a hosted platform for running and observing them.

**Research coverage:** 35/35 criteria

**Where it improves on Claude Agent SDK:**
- [GPT: yes — OpenAI is a named first-class provider in the model router, with provider-specific options such as reasoningEffort.](https://mastra.ai/models)
- [Open models: yes — Open-weight models run against any OpenAI-compatible endpoint on your own hardware; the vendor names gpt-oss, Qwen3 and DeepSeek.](https://mastra.ai/models)
- [Model choice: yes — You choose the model per agent, per request or as a fallback chain; the router is explicitly positioned as provider-agnostic.](https://mastra.ai/ai-agent-framework)

**Trade-offs against Claude Agent SDK:**
- [Writes code: partial — Code mode has the model author a TypeScript function that orchestrates your tools, executed in a sandbox; it is a beta tool-use optimisation, not a code-authoring product.](https://mastra.ai/docs/agents/code-mode)
- [In your pipeline: partial — Scorers and eval suites run in CI through Vitest/Jest via runEvals; the vendor claims no agent that acts on a pull request.](https://mastra.ai/docs/evals/running-in-ci)
- [Admin controls: partial — RBAC restricts read/write/execute/delete per resource in Studio and on the API, but SSO and RBAC in production are Enterprise Edition features requiring a licence.](https://mastra.ai/docs/studio/auth)

[View Mastra](https://theagentsindex.com/mastra)

### 6. AgentsKit

Composable TypeScript packages for agent runtime, tools, memory, RAG and headless chat UI.

**Research coverage:** 34/35 criteria

**Where it improves on Claude Agent SDK:**
- [GPT: yes — A native OpenAI adapter supports the GPT and o-series models with streaming, parallel tool calls and multimodal input, and an Azure OpenAI adapter covers enterprise tenants.](https://www.agentskit.io/llms.txt)
- [Open models: yes — Local and open-weight inference is a documented path, with adapters for Ollama, LM Studio, vLLM and llama.cpp alongside hosted open-model services such as Together and Fireworks.](https://www.agentskit.io/llms.txt)
- [Model choice: yes — You pick the provider, and swapping it is an import change rather than a rewrite, since every adapter implements the same contract behind the runtime.](https://www.agentskit.io/llms.txt)

**Trade-offs against Claude Agent SDK:**
- [Debugs and fixes: partial — Self-debug lets an agent read its own traces and retry after a failure, which covers the agent run rather than a documented workflow for diagnosing and landing a fix in someone's repository.](https://www.agentskit.io/llms.txt)
- [Writes tests: partial — The coder persona is described as test-driven in style, and a separate eval package produces agent test suites, but no page states that the agent writes unit tests for your application code.](https://www.agentskit.io/llms.txt)
- [Agent permissions: partial — Gating is opt-in per tool: marking a tool as requiring confirmation pauses the run for approval or denial, so anything you do not gate executes unattended by default.](https://www.agentskit.io/docs/agents/hitl)

[View AgentsKit](https://theagentsindex.com/agentskit)

## Method

Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.