AI TrustMark

AI SDKs companies, products & suppliers

Client libraries and SDKs for calling models and AI services from application code. Jobs: official model sdks; typed clients; streaming helpers.

What are AI SDKs?

Client libraries and SDKs for calling models and AI services from application code. Jobs: official model sdks; typed clients; streaming helpers.

What problems does it solve?

Each model host has a different request shape, so application code forks.

Typical business use cases

  • Official model SDKs
  • Typed clients
  • Streaming helpers

Important capabilities

  • Language support
  • Auth helpers
  • Retry and streaming

What buyers should evaluate

  • Licence
  • Telemetry defaults
  • Compatibility with pinned models

Risks and governance considerations

An SDK that phones home with prompts by default.

Procurement checklist

  • Telemetry opt-out
  • Pinned versions
  • Licence

Relevant AI Trustmark assurance

AI Trustmark independent findings appear only when an assessment or certificate exists. Category membership does not imply verification.

Methodology · How verification works

Products and providers

Open a product profile for its catalogue details, or use the provider link for the company profile. Claimed listings appear first, then by name. Payment never changes the order.

  • Anthropic SDK

    By Anthropic

    The Claude SDK for Python is Anthropic's official open-source library for calling the Claude API from Python applications. Installed with pip as the anthropic package and MIT-licen

  • Cohere Python SDK

    By Cohere

    Cohere is a Toronto-headquartered model company selling text, embed and RAG-oriented APIs for enterprises. Public pages emphasise private deployment options alongside hosted APIs.

  • Google Gen AI SDK

    By Google

    The Google Gen AI SDK is Google's open-source client library for building with its generative models. The Python version, published on GitHub as googleapis/python-genai, gives deve

  • Transformers

    By Hugging Face

    Hugging Face operates a model hub, inference tooling and collaboration products for machine-learning teams. Public pages cover hosting, inference endpoints and open-model distribut

  • LangChain

    By LangChain

    LangChain enables every company to own their intelligence. Control, govern, and compound intelligence with an open agent engineering platform. Trusted by 7k+ organizations. LangCha

  • LlamaIndex

    By LlamaIndex

    LlamaIndex is LlamaIndex's platform, from LlamaIndex, Inc. Published at llamaindex.ai. Directory filing: AI SDKs. Vendor legal name on this product record: LlamaIndex, Inc. LlamaIn

  • Semantic Kernel

    By Microsoft

    Semantic Kernel is Microsoft's open-source, model-agnostic SDK for building, orchestrating and deploying AI agents and multi-agent systems, released under the MIT licence for Pytho

  • Mistral Python SDK

    By Mistral AI

    Mistral AI is a Paris-headquartered model company selling open-weight and hosted language models. Public pages cover APIs, model licences and enterprise deployments. Mistral Python

  • OpenAI SDK

    By OpenAI

    OpenAI is a US AI research company that sells hosted assistants, APIs and developer tools, including ChatGPT and the OpenAI API. OpenAI SDK is OpenAI's platform, from OpenAI OpCo,

  • AI SDK

    By Vercel

    AI SDK is Vercel's platform, from Vercel Inc. Published at ai-sdk.dev. Directory filing: AI SDKs. Deployment options: Self-hosted / open-source. Recorded capabilities: Generation a

Products

Claimed products appear first. Ranking packs and payment do not change this list.

Related categories

Relevant procurement and assurance guides

Frequently asked questions

What is AI SDKs?

Client libraries and SDKs for calling models and AI services from application code. Jobs: official model sdks; typed clients; streaming helpers.

What should not be listed as AI SDKs?

Products whose buyer job is finished assistants, model APIs as products, or agent frameworks. Those belong on their own category page so search queries are not split.

Has AI Trustmark independently assessed every AI SDKs supplier?

No. A category listing is descriptive. Independent assessment is shown only on company or product pages that carry Trustmark evidence.

What are AI SDKs?

Client libraries and SDKs for calling models and AI services from application code. Jobs: official model sdks; typed clients; streaming helpers.

Should coding assistants be allowed to send private source code to third-party models?

That is a buyer policy decision. Procurement should require the default data-use terms, retention, whether snippets leave the organisation, and whether secrets are redacted. A listing under coding assistants does not mean code stays on-premises.

How should prompt injection and tool-output attacks be controlled?

Agents that read untrusted content or tool output can be instructed to exfiltrate data or take writes. Buyers should ask what is treated as untrusted, whether tool output can change the plan, and what tests were run. Scanner marketing is not the same as independent testing.

How can buyers tell whether customer data is used to train models?

Ask whether prompts, files, logs or outputs are used to train, fine-tune or evaluate models, including by subprocessors. Require the contractual default, any opt-out, and whether the setting can be changed silently. Treat marketing 'we do not train' claims as unverified until evidenced.

What model or provider changes should a buyer insist on being told about?

Material change usually includes a new model family, new region, new subprocessor, new write-capable tool, or a change that affects logging, privacy or human oversight. Those changes should trigger evidence refresh rather than a silent release.