CrewAI integration for wigolo — local-first web intelligence tools
Project description
wigolo-crewai
CrewAI tools for wigolo — local-first web intelligence for your crews. Give agents web search, page fetch, multi-step research, site crawl, and structured extraction, with results returned as JSON your agents can reason over.
Thin wrapper over the wigolo Python SDK: no API keys required for the core tools, and a zero-setup embedded daemon starts automatically.
Install
pip install wigolo-crewai[crewai]
This pulls in the wigolo SDK. crewai is an optional extra so the core
helpers can be imported without it.
Quickstart
from crewai import Agent
from wigolo_crewai import wigolo_tools
# Spawns a local wigolo daemon by default (local=True). Point at a running
# server instead with wigolo_tools(base_url="http://127.0.0.1:8787", token="...").
tools = wigolo_tools()
researcher = Agent(
role="Web Researcher",
goal="Find and summarize current information from the web",
backstory="You dig through the web and return well-sourced findings.",
tools=tools,
)
You can also add individual tools:
from wigolo_crewai import WigoloSearchTool, WigoloResearchTool, build_client
client = build_client(local=True)
agent_tools = [WigoloSearchTool(client=client), WigoloResearchTool(client=client)]
Tools
| Tool | Class | What it does |
|---|---|---|
wigolo_search |
WigoloSearchTool |
Search the web; ML-reranked results with extracted content |
wigolo_fetch |
WigoloFetchTool |
Fetch a page as clean markdown (JS rendering optional) |
wigolo_research |
WigoloResearchTool |
Multi-step research brief: topics, findings, cross-references, gaps |
wigolo_crawl |
WigoloCrawlTool |
Crawl a site (sitemap / breadth-first / depth-first / map) |
wigolo_extract |
WigoloExtractTool |
Structured extraction: tables, metadata, key-values, schema fields |
Every tool returns a JSON string; wigolo errors are returned as a clean
{"error": "..."} string rather than raised into the agent loop.
Configuration
wigolo_tools(base_url=None, token=None, local=True):
local=True(default) — spawn an embedded local daemon, zero setup.base_url/token— target a running wigolo server (setlocal=False).
Environment variables WIGOLO_BASE_URL, WIGOLO_API_TOKEN, and WIGOLO_LOCAL
are honored by the underlying SDK when the corresponding argument is left unset.
License
GNU AGPL-3.0-only — see the root LICENSE.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file wigolo_crewai-0.2.0.tar.gz.
File metadata
- Download URL: wigolo_crewai-0.2.0.tar.gz
- Upload date:
- Size: 9.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
201da802091bb2dd07ce36c988b9f0fd42aa14a2249bc95f387e92f28ceb160c
|
|
| MD5 |
3de82fb00b73a071bdb8133814d2efa9
|
|
| BLAKE2b-256 |
cc8bade2d1f371142fd1b77bd0f18f49fcc9c3528ab77515b410deaa6136199c
|
File details
Details for the file wigolo_crewai-0.2.0-py3-none-any.whl.
File metadata
- Download URL: wigolo_crewai-0.2.0-py3-none-any.whl
- Upload date:
- Size: 8.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.15
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9b1dd7b4d69f14539cc14f70a7ad81d06a43e1e996e577e6bf8dd7e937c04793
|
|
| MD5 |
3af6b0d69c15522ffe6b7cc3e945c52c
|
|
| BLAKE2b-256 |
9f208dbb4c4cc22b8bacc23da5a25a2501d953885f688141beefedfc8dab96b2
|