LedgerProof
29 adapters live on PyPI · Apache 2.0

Developer Adapters · Open Source

One import. Article 50 receipts from any AI stack.

LedgerProof ships twenty-nine open-source adapter packages — covering every major LLM provider SDK, every major orchestration framework, every major cloud-managed AI service, and every major inference platform. Each adapter emits cryptographically signed Article 50 transparency receipts on the side-channel without modifying your response payload, without buffering streams, and without changing your latency profile. Local verification. No SaaS dependency. Foundation-stewarded protocol.

Frameworks & Orchestration

Built where your agents live.

Orchestration frameworks

4 adapters
langchain-ledgerproof

LangChain + LangGraph integration via a callback handler and a graph-node middleware. Receipts per LLM call and per graph node, including tool invocations.

pip install langchain-ledgerproof
PyPI ↗ · v1.0.1
llamaindex-ledgerproof

LlamaIndex callback handler for RAG and chat. Receipts capture the retrieval step, the LLM step, and the final response — all on the side-channel.

pip install llamaindex-ledgerproof
PyPI ↗ · v0.1.1
haystack-ledgerproof

Haystack pipeline component. Receipts emit per generator-node call in your pipeline, with retriever provenance preserved in the receipt context.

pip install haystack-ledgerproof
semantic-kernel-ledgerproof

Microsoft Semantic Kernel kernel hook (Python). Receipts emit per InvokePromptAsync call. .NET port in active development.

pip install semantic-kernel-ledgerproof

Direct LLM Provider SDKs

Built into the SDK you already call.

LLM provider SDKs

12 adapters
openai-ledgerproof

OpenAI Python SDK client wrapper, @with_receipt decorator, and manual emission helper. Streaming and non-streaming paths both covered.

pip install openai-ledgerproof
PyPI ↗ · v0.1.1
anthropic-ledgerproof

Anthropic Python SDK client wrapper, @with_receipt decorator, and tool-use support tuned for the Claude Agent SDK and multi-turn agent loops.

pip install anthropic-ledgerproof
PyPI ↗ · v0.1.1
mistral-ledgerproof

Mistral AI Python SDK client wrapper. Chat completions, function calling, and JSON-mode responses all emit receipts.

pip install mistral-ledgerproof
PyPI ↗ · v0.1.0
mistral-codestral-ledgerproof

Codestral code-completion API wrapper. Receipts capture the completion request, the model identifier, and the response hash on the side-channel.

pip install mistral-codestral-ledgerproof
cohere-ledgerproof

Cohere Python SDK client wrapper. Chat, generate, embed, and rerank endpoints all emit receipts tagged with the endpoint name.

pip install cohere-ledgerproof
ai21-ledgerproof

AI21 Jamba and Jurassic API wrapper. Streaming completions supported; tool-use receipts include the function-call payload hash.

pip install ai21-ledgerproof
aleph-alpha-ledgerproof

Aleph Alpha Pharia and Luminous SDK wrapper. Receipts tuned for sovereign-EU deployment patterns common in DACH financial services.

pip install aleph-alpha-ledgerproof
PyPI ↗ · v0.1.0
google-ai-ledgerproof

Google AI direct Gemini SDK wrapper (not Vertex). Supports the google-generativeai package; multimodal inputs are hashed deterministically.

pip install google-ai-ledgerproof
xai-ledgerproof

xAI Grok SDK wrapper. Streaming completions and tool-use receipts; image-mode inputs hashed via canonical image-byte serialization.

pip install xai-ledgerproof
deepseek-ledgerproof

DeepSeek API wrapper. Receipts emit for chat, reasoning, and code endpoints. Drop-in via the OpenAI-compatible interface.

pip install deepseek-ledgerproof
qwen-ledgerproof

Alibaba Qwen DashScope SDK wrapper. Receipts tuned for APAC-region deployments with PRC residency constraints.

pip install qwen-ledgerproof
reka-ledgerproof

Reka Core and Flash SDK wrapper. Multimodal inputs (audio, video, image) hashed via canonical serialization.

pip install reka-ledgerproof

Cloud-Managed AI Services

Hyperscaler AI, with neutral evidence.

Cloud-managed AI services

5 adapters
bedrock-ledgerproof

AWS Bedrock client wrapper covering Anthropic, Mistral, Cohere, AI21, Llama, and Amazon Titan model invocations. Streaming and tool-use both supported.

pip install bedrock-ledgerproof
vertexai-ledgerproof

Google Vertex AI client wrapper. Receipts for Gemini, PaLM, and partner-hosted models. Stateful chat sessions hash conversation history canonically.

pip install vertexai-ledgerproof
azure-openai-ledgerproof

Azure OpenAI Service wrapper. Functions identical to openai-ledgerproof but tuned for the Azure deployment-name routing pattern and content-filter responses.

pip install azure-openai-ledgerproof
watsonx-ledgerproof

IBM watsonx.ai SDK wrapper. Granite and partner models supported. Receipts include the project ID and the model-deployment identifier for audit traceability.

pip install watsonx-ledgerproof
snowflake-cortex-ledgerproof

Snowflake Cortex AI function wrapper. Receipts capture the warehouse identifier, the function name, and the row-level invocation pattern for table-bound AI calls.

pip install snowflake-cortex-ledgerproof

Inference Platforms

Wherever your tokens come from.

Inference platforms

7 adapters
together-ledgerproof

Together AI inference API wrapper. Receipts emit per chat-completion and per embedding call. OpenAI-compatible endpoint also supported.

pip install together-ledgerproof
groq-ledgerproof

Groq LPU inference SDK wrapper. Low-latency anchoring path optimized for high-volume Groq deployments; receipts batch at the operator side without adding latency.

pip install groq-ledgerproof
replicate-ledgerproof

Replicate Python SDK wrapper. Receipts for image, audio, and video generation models include canonical hashes of binary outputs for Article 50(4) deepfake-disclosure use.

pip install replicate-ledgerproof
huggingface-ledgerproof

Hugging Face Inference API and Transformers pipeline wrapper. Receipts for hosted-endpoint calls; local-model invocations supported via the pipeline hook.

pip install huggingface-ledgerproof
fireworks-ledgerproof

Fireworks AI inference SDK wrapper. OpenAI-compatible chat and completion endpoints; function calling and JSON-mode receipts both supported.

pip install fireworks-ledgerproof
cerebras-ledgerproof

Cerebras Inference SDK wrapper. Very-high-throughput deployments use the batched-anchor configuration to keep Bitcoin OP_RETURN economics rational at scale.

pip install cerebras-ledgerproof
perplexity-ledgerproof

Perplexity Sonar API wrapper. Receipts include the search-grounding citations as a deterministic hash so retrieved-source claims remain auditable.

pip install perplexity-ledgerproof

Embeddings

Receipts for the vector layer.

Embedding providers

1 adapter
voyage-ledgerproof

Voyage AI embeddings SDK wrapper. Receipts capture the embedding-model identifier and the input-batch hash, useful when the embedding step itself is the AI-touched interaction.

pip install voyage-ledgerproof
PyPI ↗ · v0.1.1

Design Constraints

Three load-bearing decisions every adapter respects.

01 Side-channel emission

Receipts never modify your response payload.

Adapters do not touch the bytes your application returns to the user. Receipts emit to a configurable sink — log, queue, webhook, or SIEM connector — on a separate path. Your existing integration tests, contract tests, and downstream consumers see nothing new in the response body.

02 Stream-aware signing

No body buffering. No latency penalty.

Streaming LLM responses are signed incrementally with a running SHA-256 over the token stream. The adapter does not buffer the response before forwarding it to your user. First-token latency is unchanged; receipt emission completes asynchronously after the stream closes.

03 Local verification

Verifiable offline against Bitcoin.

Every receipt is verifiable using only the Bitcoin chain, the published protocol public key, and the receipt itself. No call to LedgerProof servers required. The reference verifier runs in any browser. If LedgerProof Inc. disappears tomorrow, every receipt ever issued remains independently verifiable.

Start Here

LangChain is the most common entry point.

If you're not sure which adapter fits your stack, start with langchain-ledgerproof — the LangChain callback handler works with any LLM provider your LangChain code already calls, and the integration is three lines of Python. Walk through it on the quickstart page.