Features

Everything you need to build, deploy, and manage agentic AI applications.

Interactive Chat

Multi-Provider LLM Support

Chat with 12+ LLM providers through a unified interface. Switch between OpenAI, Anthropic Claude, Google Gemini, Groq, and more without changing your workflow.

  • ◆One interface for all major LLM providers
  • ◆Provider failover and fallback chains
  • ◆Streaming responses with real-time token display
  • ◆Conversation history with search and export
terminal
$ cortex cortex chat --model claude-sonnet-4-20250514

Tool Use & Approval Gates

Controlled Agent Autonomy

Agents can use tools and call functions, with configurable approval gates that let you review and approve or reject tool calls before they execute.

  • ◆Built-in tool system for code execution, file I/O, web access
  • ◆Approval gates for sensitive operations
  • ◆Policy-based automatic approval rules
  • ◆Full audit log of all tool calls
terminal
$ cortex cortex chat --tools all

5-Tier Memory System

From Ephemeral to Procedural

A sophisticated memory architecture with five tiers: ephemeral (session), working (task), semantic (knowledge), archival (history), and procedural (skills).

  • ◆Ephemeral: In-session context only
  • ◆Working: Active task-related information
  • ◆Semantic: Long-term knowledge storage
  • ◆Archival: Compressed historical data
  • ◆Procedural: Learned skills and patterns
terminal
$ cortex cortex memory search --query "deployment config" --tier semantic

Parallax Security Model

Defense in Depth

A multi-layered security architecture with encrypted vault storage, granular policy engine, role-based access control, and approval workflows.

  • ◆Encrypted vault for secrets and credentials
  • ◆Policy engine with allow/deny rules
  • ◆Approval workflows for sensitive actions
  • ◆Sandboxed plugin execution isolation
terminal
$ cortex cortex policy add --allow code.execute.python

Sandboxed Code Execution

Run Code Safely

Execute Python, JavaScript, Wasm, and shell commands in isolated sandboxes. Perfect for data analysis, automation, and prototyping.

  • ◆Python sandbox with pip package support
  • ◆WebAssembly runtime with WASI support
  • ◆Resource limits (CPU, memory, timeouts)
  • ◆Read-only mode for untrusted scripts
terminal
$ cortex cortex run --sandbox python --script analyze.py

Model Router (RouteLLM)

Intelligent Model Selection

RouteLLM integration enables automatic model selection based on task complexity, cost optimization, and provider availability with intelligent failover.

  • ◆Automatic model selection by task type
  • ◆Cost optimization between providers
  • ◆Graceful failover on provider outages
  • ◆Custom routing rules and priorities
terminal
$ cortex cortex chat --router cost-optimized

Daemon Supervisor & Jobs

Background Processing

Persistent daemon mode with a built-in job scheduler. Run agents in the background, schedule recurring tasks, and monitor execution.

  • ◆Persistent background daemon process
  • ◆CRON-like job scheduling
  • ◆Job queue with priority levels
  • ◆Execution logs and monitoring
terminal
$ cortex cortex daemon start && cortex jobs add --schedule "0 9 * * 1" --task weekly-report

Plugin System

ESM, MCP & WASM

Extend CortexPrism with a powerful plugin system supporting ESM modules, Model Context Protocol servers, and WebAssembly plugins.

  • ◆Three plugin types: ESM, MCP, WASM
  • ◆Plugin marketplace for discovery
  • ◆Version management with dependency resolution
  • ◆Isolated plugin sandboxes
terminal
$ cortex cortex plugin install marketplace:cortexprism.io/plugins/python-executor

Web UI & REST API

Full-Featured Interface

Built-in web interface and comprehensive REST API for managing agents, monitoring sessions, and configuring the system remotely.

  • ◆Responsive dark-theme web dashboard
  • ◆REST API with OpenAPI documentation
  • ◆WebSocket for real-time streaming
  • ◆Session management and monitoring
terminal
$ cortex cortex serve --port 8080

Agent Manager

Multi-Agent Orchestration

Create, configure, and manage multiple specialized agents with different personalities, tools, and provider configurations.

  • ◆Multiple agent profiles with custom configurations
  • ◆Agent-specific system prompts and souls
  • ◆Per-agent tool and provider assignments
  • ◆Agent-to-agent collaboration
terminal
$ cortex cortex agent create --name code-reviewer --model claude-sonnet-4-20250514

Micro-Services

Distributed Architecture

Run CortexPrism as a distributed system with micro-service architecture. Scale components independently and deploy across multiple machines.

  • ◆Distributed agent execution
  • ◆Message queue integration
  • ◆Service discovery and health checks
  • ◆Horizontal scaling of components
terminal
$ cortex cortex serve --mode micro --workers 4