OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Agentica

Agentica is an Apache-2.0 Python-based multi-agent framework and local application that coordinates agents across terminal sessions and exposes them through CLI, Web, desktop, SDK and messaging-gateway interfaces.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentica — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Agentica when agent collaboration, local operation, persistent context or repeatable skills matter more than a single conversational interface. The CLI fits direct terminal work; the Web and desktop interfaces provide local graphical access; the SDKs fit applications built around an existing Agentica setup.

Who it is for

  • Developers building Python applications around multiple collaborating agents.
  • Individuals who want a local workspace for delegated or long-running agent tasks.
  • Teams or operators connecting local agents to WeChat, WeCom or Feishu gateways.
  • Users who need persistent session context and reusable agent skills.

Documented uses

  • Delegate independent work to temporary or separate agents.
  • Coordinate agents across multiple terminal sessions.
  • Keep persistent session information and retrieve older content from long conversations.
  • Reuse task experience through self-evolving skills.
  • Interact with local agents through CLI, browser, desktop or supported messaging gateways.
Before you choose

Requirements & limits

The project documents CLI and gateway installation with uv, local Web access, Docker self-hosting and desktop builds for macOS, Windows and Linux. A model-provider API key is required for configuration. Desktop builds are described as unsigned and may require first-launch steps.

  • The system is designed around local operation, with CLI, Web and desktop interfaces using the same local workspace.
  • Separate terminal sessions can collaborate through peer messages, while delegated agents can handle independent work.
  • Persistent memory and searchable session records support longer workflows without relying solely on generated summaries.
  • The documented gateway connects agents with WeChat, WeCom and Feishu; configuration details should be checked before planning a deployment.
  • The Python SDK is documented for building applications, while the TypeScript SDK is documented for connecting to an already running gateway.

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

Install the Agentica CLI

Set up the documented CLI package and configure a model provider.

Before you start

  • A supported machine with uv installed.
  • An API key for a model provider.

Steps

  1. Install uv using the project’s documented installation route, or use an existing uv installation.

  2. Install the CLI with the command below.

    Documented command
    uv tool install agentica

  3. Set the provider base URL and API key through shell environment variables, or configure them through the documented .env or config.yaml options.

  4. Start the interactive terminal with agentica.

Expected outcome

The Agentica CLI is installed and ready for interactive agent tasks after model configuration.

Guide limitations

  • This setup recipe does not establish task success or model-provider compatibility beyond the configuration paths named by the project.
  • The supplied instructions do not provide a single required provider or fixed model.
Documentation 1 ↗Documentation 2 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

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
AgenticaDelegate independent work to temporary or separate agents.CLI, Desktop, Linux, macOSThe project documents CLI and gateway installation with uv, local Web access, Docker self-hosting and desktop builds for macOS, Windows and Linux. A model-provider API key is required for configuration. Desktop builds are described as unsigned and may require first-launch steps.
MassgenRun multiple AI agents against the same user task.CLIThe repository documents installation through pip or uv and requires Python 3.11 or later. Setup can configure API keys for OpenAI, Anthropic, Google and xAI; credentials are needed for the selected model backends.
Langchain Multi Agents BoilerplateRoute incoming football questions to model and agent workflows according to task complexity.WebThe repository is public and specifies an MIT license. Running the application requires OpenAI and Groq API keys and a Redis server.
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
shibing624/agentica · Official homepage title · retained in its source language
How we review sourcesSuggest a correction