valyu
Deepsearch API for AI.
Decision gist · record as of 2026-08-14
Yes. Valyu is actively maintained, has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. It is worth installing if you need to integrate external search, content extraction, or AI-powered research capabilities into an application. The main prerequisite is obtaining and configuring a Valyu API key; review pricing and quota terms on their platform before committing to production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a Valyu API key set via VALYU_API_KEY environment variable or passed to Valyu(api_key=...).
- Low install friction with a pure Python wheel and three common runtime dependencies (requests, httpx, pydantic).
- Active maintenance with a recent release.
License · maintenance · safety
permissive license (permissive) — MIT license permits unrestricted use, modification, and distribution with minimal obligations.
last release 2026-08-12 (2 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 106,312 downloads/mo, #12,658 on PyPI
Alternatives
Verify before relying
pip install valyu
from valyu import Valyu
valyu = Valyu() # uses VALYU_API_KEY env var
response = valyu.search("latest advances in transformers", max_num_results=5)
for result in response.results:
print(result.title, result.url)- Whether the SDK supports async/await patterns beyond the documented async contents mode.
- Rate limits, quota behavior, and cost structure for different search types and data sources.
- Streaming support details and latency characteristics for real-time research workflows.
What it is and what it does
Valyu is a Python SDK that wraps a suite of research and search APIs designed to integrate external data into AI applications. It provides four main capabilities: web and proprietary data search with filtering and date range support, content extraction and summarization from URLs, AI-generated answers grounded in search results, and DeepResearch—a multi-step research agent that produces comprehensive reports with citations. The SDK also supports batch processing of research tasks, templated workflows with variable substitution, and programmatic access to available data sources. All request and response models use Pydantic v2 for type safety.
The package depends on requests, httpx, and pydantic for HTTP communication and data validation. It is designed for developers building AI agents, research automation tools, and applications that need to augment their own knowledge with current web data or proprietary sources. Authentication is API-key based, and the SDK includes error handling with transaction IDs for debugging.
Use it for
- Build an AI agent that searches for recent scientific papers and extracts structured data from them for literature review automation.
- Create a research report generator that runs multi-step DeepResearch tasks to compile comprehensive competitor analysis or market trend reports.
- Integrate web search results into a chatbot or LLM application to ground AI-generated answers with current, cited sources.
- Automate batch processing of research queries across multiple topics, tracking progress and collecting results in parallel.
- Set up templated research workflows with variable placeholders to standardize recurring research tasks across your organization.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Valyu is actively maintained, has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. It is worth installing if you need to integrate external search, content extraction, or AI-powered research capabilities into an application. The main prerequisite is obtaining and configuring a Valyu API key; review pricing and quota terms on their platform before committing to production use.
Install
valyu on PyPI
Before you install
Low install friction with a pure Python wheel and three common runtime dependencies (requests, httpx, pydantic). Active maintenance with a recent release.
Requires a Valyu API key set via VALYU_API_KEY environment variable or passed to Valyu(api_key=...).
License in practice
MIT license permits unrestricted use, modification, and distribution with minimal obligations.
Quickstart
pip install valyu
from valyu import Valyu
valyu = Valyu() # uses VALYU_API_KEY env var
response = valyu.search("latest advances in transformers", max_num_results=5)
for result in response.results:
print(result.title, result.url)Verify before relying
- Whether the SDK supports async/await patterns beyond the documented async contents mode.
- Rate limits, quota behavior, and cost structure for different search types and data sources.
- Streaming support details and latency characteristics for real-time research workflows.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.6 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagesrequestshttpxpydantic |
| Maintenance | Actively maintained 2 days since the last release |
| First released | |
| Downloads | 106,312 / month, #12,658 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | License :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: valyu-2.12.1-py3-none-any.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 › “search api sdk for ai agents”
- valyuValyu provides a Python SDK for accessing web search, content…
- databricks-ai-bridgeProvides a shared Python API layer for building agents and…
- azure-ai-projectsProvides a Python client for Microsoft Foundry projects, enabling…
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 langchain-exa · seltz · firecrawl-py · livekit-plugins-azure · tavily-python · sap-ai-sdk-gen · notebooklm-py · genagent · icalendar-searcher