OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

AgentSearch

AgentSearch is an open-source Python framework for building search agents that connect language models to search engines. It supports retrieval-augmented responses, search-result summaries, related-query generation, standalone search calls, and customizable local search using its dataset.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AgentSearch — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use AgentSearch when you are developing a Python application that needs to combine search-provider results with language-model responses, or when you want to build a custom search workflow.

Who it is for

  • Developers building search-backed assistants or research workflows.
  • Teams customizing search agents or exploring a local search engine using the AgentSearch dataset.

Documented uses

  • Retrieve search results for a user query through a supported provider.
  • Generate a response that summarizes retrieved results and suggests related queries.
  • Compose a custom retrieval-augmented workflow from search results and model completions.
  • Use the AgentSearch dataset with the framework to configure a customizable local search engine.
Before you choose

Requirements & limits

The repository is public and licensed under Apache-2.0. The documented quickstart requires a SciPhi API key.

  • The README documents Bing, SERP API, and AgentSearch as search-provider options.
  • Named language-model providers include SciPhi, Hugging Face, OpenAI, and Anthropic.
  • The quickstart demonstrates package installation and client use with a SciPhi API key.
  • Local search customization is described using the AgentSearch dataset alongside the framework. The cited usage examples focus on the client and provider calls.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up AgentSearch for a SciPhi-backed search workflow

Install the Python package and configure the documented SciPhi key before using the client.

Before you start

  • Python environment with pip
  • SciPhi API key

Steps

  1. Install the package with the command below.

    Documented command
    pip install agent-search

  2. Set SCIPHI_API_KEY in the environment to your SciPhi API key.

  3. Import SciPhi from agent_search and create a client with SciPhi().

  4. Use the client for a search or call get_search_rag_response with a query, a search provider, and an LLM model.

Expected outcome

A configured client can be used for the README's documented search and search-RAG calls.

Guide limitations

  • The example requires a SciPhi API key.
  • The guide describes the documented quickstart, not a deployment procedure or a compatibility guarantee.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AgentSearchRetrieve search results for a user query through a supported provider.CLI, Self-hosted, ServerThe repository is public and licensed under Apache-2.0. The documented quickstart requires a SciPhi API key.
Hydra — hassenhamdiIngest Markdown documents into a searchable knowledge base.CLI, Self-hosted, ServerThe repository is public and identifies an MIT license. Local setup requires Python 3.10+, a Gemini API key and Docker with Docker Compose for Milvus.
AgentnexusConfigure agents from stored models, tools, prompts, memory, and knowledge sources.Docker, Self-hosted, ServerThe project is documented as open source, and its README states that it uses the MIT License.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
SciPhi-AI/agent-search · Official homepage title · retained in its source language
How we review sourcesSuggest a correction