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

Cortico

Cortico is a TypeScript event-stream agent framework and harness for building autonomous, continuously running agents that process mixed real-time inputs. It organizes session lifecycles, event streams, model invocations, persona behavior, persistent memory and external environments into separate layers, and supports extensible Worlds for event ingestion and tool calls.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Cortico — 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 Cortico when the project needs an autonomous agent that remains active, handles mixed real-time inputs and can interact with external environments through a modular extension boundary.

Who it is for

  • Developers building persistent persona bots
  • Builders creating AI streamers or roleplay agents
  • Teams connecting agents to multiple real-time environments
  • Developers who need custom extensions around event delivery and tool calls

Documented uses

  • Build an agent that continues operating around incoming events
  • Combine multiple real-time input sources through external extensions
  • Define custom persona behavior, context handling and memory protocols
  • Operate multiple isolated bot deployments
  • Create or adapt extensions with conversational development assistance
Before you choose

Requirements & limits

The repository is publicly accessible and MIT-licensed. Local setup requires Node 22 or later. The README describes the project as pre-release.

  • Its event-stream design targets continuously running agents rather than isolated request-and-response interactions.
  • The four-layer separation lets builders distinguish core runtime, persona logic, memory and external Worlds.
  • Model-provider components support the Responses protocol, upstream model APIs and locally deployed models.
  • External extensions use event delivery and tool calls as their integration boundary.
  • Cortina provides a documented conversational workflow for developing or adapting extensions.

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 a local Cortico deployment

Install Cortico, start its default deployment and reach the local web console for initial configuration.

Before you start

  • Node 22 or later
  • The Cortico repository cloned to the local machine

Steps

  1. Run corepack pnpm install.

  2. Run pnpm start.

  3. Open the local web console at http://127.0.0.1:7788/.

  4. Configure a model endpoint, inspect active Worlds and adjust the system prompt in the onboarding flow.

Expected outcome

A default `mybot` deployment starts with the reference `cormini` bot and terminal chat enabled, with configuration available in the web console.

Guide limitations

  • The documented steps cover local startup and initial configuration; they do not establish that a particular model endpoint or external World will work in a given environment.
  • Cortico is marked pre-release in the repository README.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 October 2026
Original website title
Pal-AI-Lab/Cortico · Official homepage title · retained in its source language
How we review sourcesSuggest a correction