clarifai-protocol
Clarifai Python Runner Protocol
Decision gist · record as of 2026-08-14
Yes, if you are building models for the Clarifai platform or using clarifai SDK. The package is actively maintained, carries no known vulnerabilities, and uses a permissive Apache 2.0 license. Install friction is moderate due to compiled wheels, but platform coverage is broad. If you are not building Clarifai runners, this is likely a transitive dependency and not a direct choice.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later.
- Optional auto-annotation extra requires av and shapely dependencies.
- Medium install friction due to compiled wheels across multiple Python versions and platforms.
License · maintenance · safety
permissive license (permissive) — Apache License 2.0 (permissive) allows free use, modification, and distribution with minimal restrictions—suitable for both open-source and commercial projects.
last release 2026-05-05 (101 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 135,647 downloads/mo, #11,425 on PyPI
Alternatives
Verify before relying
pip install clarifai-protocol
from clarifai_protocol import get_request_id, register_abort_callback
register_abort_callback(lambda req_id: print(f"Cancelled: {req_id}"))
req_id = get_request_id()- Whether the package is intended for direct use or only as a transitive dependency of clarifai SDK
- Performance characteristics and latency overhead of request cancellation callbacks
- Thread-safety guarantees under high-concurrency workloads
What it is and what it does
clarifai-protocol is the internal communication protocol layer for Clarifai's Python runner infrastructure. It handles serialization and deserialization of requests and responses between runner models and the Clarifai API, built on gRPC foundations. The package also provides request lifecycle management, including the ability to track and cancel in-flight requests when users abort operations.
The protocol supports request ID tracking and abort callbacks, allowing custom models to register handlers that fire when requests are cancelled or connections drop. This is particularly useful when models call external inference servers—they can pass the request ID to those servers and abort them cleanly when the user cancels. The package is designed to be thread-safe and runs abort callbacks in background threads to avoid blocking the main protocol flow.
Use it for
- Building custom Clarifai models that need to handle request cancellation when calling external inference servers
- Integrating with Clarifai runners to enable graceful abort of long-running inference tasks
- Tracking request IDs for debugging and monitoring model execution within the Clarifai platform
- Implementing idempotent cleanup logic when requests are cancelled or connections are lost
- Coordinating cancellation between Clarifai and downstream inference services like sglang or similar
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building models for the Clarifai platform or using clarifai SDK.
The package is actively maintained, carries no known vulnerabilities, and uses a permissive Apache 2.0 license. Install friction is moderate due to compiled wheels, but platform coverage is broad. If you are not building Clarifai runners, this is likely a transitive dependency and not a direct choice.
Install
clarifai-protocol on PyPI
Before you install
Medium install friction due to compiled wheels across multiple Python versions and platforms. Actively maintained with recent release activity. Depends on clarifai, clarifai-grpc, and psutil.
Requires Python 3.9 or later. Optional auto-annotation extra requires av and shapely dependencies.
License in practice
Apache License 2.0 (permissive) allows free use, modification, and distribution with minimal restrictions—suitable for both open-source and commercial projects.
Quickstart
pip install clarifai-protocol
from clarifai_protocol import get_request_id, register_abort_callback
register_abort_callback(lambda req_id: print(f"Cancelled: {req_id}"))
req_id = get_request_id()Verify before relying
- Whether the package is intended for direct use or only as a transitive dependency of clarifai SDK
- Performance characteristics and latency overhead of request cancellation callbacks
- Thread-safety guarantees under high-concurrency workloads
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 3 packagesclarifaiclarifai-grpcpsutil |
| Maintenance | Actively maintained 101 days since the last release |
| First released | |
| Downloads | 135,647 / month, #11,425 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.9Programming Language :: Python :: Implementation :: CPythonTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: clarifai_protocol-0.0.62-cp310-cp310-macosx_11_0_universal2.whl; clarifai_protocol-0.0.62-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl; clarifai_protocol-0.0.62-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl; clarifai_protocol-0.0.62-cp310-cp310-musllinux_1_2_aarch64.whl; clarifai_protocol-0.0.62-cp310-cp310-musllinux_1_2_x86_64.whl; clarifai_protocol-0.0.62-cp310-cp310-win_amd64.whl; clarifai_protocol-0.0.62-cp311-cp311-macosx_11_0_universal2.whl; clarifai_protocol-0.0.62-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl; clarifai_protocol-0.0.62-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl; clarifai_protocol-0.0.62-cp311-cp311-musllinux_1_2_aarch64.whl; clarifai_protocol-0.0.62-cp311-cp311-musllinux_1_2_x86_64.whl; clarifai_protocol-0.0.62-cp311-cp311-win_amd64.whl; clarifai_protocol-0.0.62-cp312-cp312-macosx_11_0_universal2.whl; clarifai_protocol-0.0.62-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl; clarifai_protocol-0.0.62-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl; clarifai_protocol-0.0.62-cp312-cp312-musllinux_1_2_aarch64.whl; clarifai_protocol-0.0.62-cp312-cp312-musllinux_1_2_x86_64.whl; clarifai_protocol-0.0.62-cp312-cp312-win_amd64.whl; clarifai_protocol-0.0.62-cp313-cp313-macosx_11_0_universal2.whl; clarifai_protocol-0.0.62-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “clarifai runner protocol”
- clarifai-protocolProvides the protocol layer for Clarifai's Python runners to…
- clarifaiOfficial Python client for Clarifai's AI platform, enabling computer…
- clarifai-grpcA gRPC client library for the Clarifai AI platform, enabling Python…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also clarifai-grpc · clarifai · azure-ai-agentserver-responses · wait-for2 · aiorun · livekit-plugins-noise-cancellation · runware · livekit-protocol · jupyter-ai-router · tb-paho-mqtt-client