OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Workflow Agents

Agenticseek

An open-source, locally run AI assistant for autonomous web browsing, code generation, task planning and voice interaction. It is a Python project intended for self-hosted desktop use and is described as having no cloud dependency.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agenticseek — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Agenticseek when local execution, self-hosting and keeping data on the user’s device are important requirements for research, coding or task automation.

Who it is for

  • Users who want a private, local AI assistant.
  • Developers seeking an on-device coding assistant.
  • People building self-hosted research or automation workflows.
  • Users with suitable hardware for running local reasoning models.

Documented uses

  • Browse the web for local research and task work.
  • Generate or modify code on the user’s device.
  • Plan and execute suitable autonomous tasks.
  • Interact with a locally run assistant by voice.
  • Build a self-hosted alternative to cloud-based autonomous agents.
Before you choose

Requirements & limits

The project is identified as public, open source and active. It is intended for self-hosted desktop use; no API availability is documented.

  • Local execution is central to the project’s design.
  • The primary implementation language is Python.
  • The project is licensed under GPL-3.0.
  • The documented workflow includes web browsing, coding, task planning and voice interaction.
  • A specific replacement local model is not verified; that adaptation is marked Experimental.

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 AgenticSeek for a local Ollama provider

Prepare AgenticSeek to use a locally hosted Ollama reasoning model.

Before you start

  • Git
  • Python 3.10.x
  • Docker Engine and Docker Compose
  • Hardware capable of running a supported 14B-class model
  • A local Ollama installation

Steps

  1. Clone the repository, enter its directory, and create the environment file from .env.example.

  2. Set the required .env values, including the working-directory path and service ports; leave API keys empty when using a local model.

  3. Set OLLAMA_HOST=0.0.0.0:11434 unless running AgenticSeek in host CLI mode, then start Ollama with ollama serve.

  4. Edit config.ini to set is_local = True, provider_name = ollama, a model supported by the provider, and the provider server address; remove comments from the configuration file because its format does not support them.

  5. Start Docker and the bundled services with ./start_services.sh full. The documented web interface is then available at localhost:3000.

Expected outcome

AgenticSeek is configured for a local Ollama model and its documented web services are started.

Guide limitations

  • The documentation recommends Python 3.10.x and warns that other versions may cause dependency errors.
  • Local use requires sufficient hardware; the stated minimum is a GPU capable of running Magistral, Qwen, or DeepSeek 14B.
  • The documentation does not establish successful execution for a particular model or hardware configuration.
  • Voice input is documented as CLI-only and experimental.
  • After changing .env, the backend must be restarted because the file is read at process start.
Documentation 1 ↗Documentation 2 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

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
AgenticseekBrowse the web for local research and task work.Desktop, Self-hostedThe project is identified as public, open source and active. It is intended for self-hosted desktop use; no API availability is documented.
Dark Factory ExperimentExamine a workflow that routes GitHub issues through triage, implementation, validation, and merge.Cloud
LayaGather notifications from services such as Slack, Gmail, GitHub, Jira, Notion and Outlook.Cloud, Self-hostedThe project is identified as open source under the Apache-2.0 license. The documented local development setup requires Python 3, Node.js, npm and Cargo.
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
Fosowl/agenticSeek · Official homepage title · retained in its source language
How we review sourcesSuggest a correction