browseai 0.1.3

Python SDK for BrowseAI Dev — reliable research infrastructure for AI agents

browseai

Reliable research infrastructure for AI agents. Python SDK for BrowseAI Dev — the research layer for LangChain, CrewAI, and custom agent pipelines.

Install

pip install browseai

Quick Start

from browseai import BrowseAI

client = BrowseAI(api_key="bai_xxx")

# Research with citations
result = client.ask("What is quantum computing?")
print(result.answer)
print(f"Confidence: {result.confidence:.0%}")
for source in result.sources:
    print(f"  - {source.title}: {source.url}")

# Thorough mode — auto-retries if confidence < 60%
deep = client.ask("What is quantum computing?", depth="thorough")

# Web search
results = client.search("latest AI news", limit=5)

# Page extraction
page = client.open("https://example.com")

# Structured extraction from a URL
extract = client.extract("https://example.com", query="pricing info")

# Compare raw LLM vs evidence-backed
compare = client.compare("Is Python faster than Rust?")

Async

from browseai import AsyncBrowseAI

async with AsyncBrowseAI(api_key="bai_xxx") as client:
    result = await client.ask("What is quantum computing?")
    # Thorough mode works with async too
    deep = await client.ask("What is quantum computing?", depth="thorough")

Streaming (REST API)

For real-time progress events, use the streaming endpoint directly:

import httpx

with httpx.stream("POST", "https://browseai.dev/api/browse/answer/stream",
    json={"query": "What is quantum computing?"},
    headers={"X-Tavily-Key": "tvly-xxx", "X-OpenRouter-Key": "sk-or-xxx"}
) as response:
    for line in response.iter_lines():
        if line.startswith("data: "):
            print(line[6:])

Events: trace (progress), sources (discovered early), result (final answer), done.

Research Memory (Sessions)

Persistent research sessions that accumulate knowledge across multiple queries. Later queries recall prior knowledge — faster, cheaper, more coherent.

from browseai import BrowseAI

client = BrowseAI(api_key="bai_xxx")

# Create a session
session = client.session("wasm-research")

# Each query builds on previous knowledge
r1 = session.ask("What is WebAssembly?")
r2 = session.ask("How does WASM compare to JavaScript performance?")
# ^ r2 recalls WASM knowledge from r1, only searches for JS perf

# Query accumulated knowledge without new searches
recalled = session.recall("WASM")
for entry in recalled.entries:
    print(f"  {entry.claim} (from: {entry.origin_query})")

# Export all knowledge
knowledge = session.knowledge()

Async sessions work the same way:

async with AsyncBrowseAI(api_key="bai_xxx") as client:
    session = await client.session("my-project")
    r1 = await session.ask("What is WASM?")
    r2 = await session.ask("WASM vs JS?")

BYOK (Bring Your Own Keys)

client = BrowseAI(tavily_key="tvly-xxx", openrouter_key="sk-or-xxx")

LangChain

pip install browseai[langchain]

from browseai.integrations.langchain import BrowseAIAskTool

tools = [BrowseAIAskTool(api_key="bai_xxx")]

CrewAI

pip install browseai[crewai]

from browseai.integrations.crewai import BrowseAITool

researcher = Agent(tools=[BrowseAITool(api_key="bai_xxx")])