Skip to main content
Open Source AI Orchestration

Build Autonomous Agents That Actually Work

Radium is a next-generation orchestration platform that enables you to build, deploy, and manage multi-agent workflows with minimal code. Leverage intelligent agent selection, policy-driven execution, and seamless model integration.
terminal
$ cargo install radium-cli

$ radium-cli init my-project
✓ Created project structure
✓ Generated agent configs
✓ Set up policy engine

$ radium-cli agents create code-reviewer \
    --model claude-3-sonnet \
    --persona expert-reviewer
✓ Agent created successfully

$ radium-cli chat code-reviewer
> Review the authentication module
🤖 Analyzing codebase...
✓ Found 3 security improvements
✓ Suggested 5 optimization opportunities
📊 Generated detailed report
Loading GitHub stats...

Every Feature You Need, Nothing You Don't

Traditional agent frameworks force you to write boilerplate, manage complex orchestration logic, and deal with vendor lock-in. Radium provides a batteries-included platform that handles the complexity so you can focus on building intelligent workflows.

Easy to Use

Autonomous Orchestration

YOLO mode enables fully autonomous execution from high-level goals to complete implementations. Intelligent agent selection, resource allocation, and error recovery with multi-agent coordination.

Focus on What Matters

Multi-Agent Workflows

Define complex DAG workflows with behavior orchestration, checkpoint recovery, and policy-driven execution. Specialized agents collaborate to tackle multi-step tasks with full observability.

Powered by React

Provider Agnostic

Seamlessly switch between Claude, OpenAI, Gemini, and self-hosted models. Built-in cost tracking, quota management, and intelligent fallback chains keep your workflows running efficiently.

Easy to Use

Metacognitive Oversight

Vibe Check system provides Chain-Pattern Interrupt functionality to prevent reasoning lock-in. Research shows +27% success rate and -41% reduction in harmful actions.

Focus on What Matters

Policy Engine

Fine-grained tool execution control with rule-based policies and approval modes. Ensure security and prevent unwanted operations with context-aware policy enforcement.

Powered by React

Learning System

Track mistakes, preferences, and successes to build pattern recognition. ACE Skillbook learns and applies successful strategies from past work to continuously improve agent performance.

From Complexity to Clarity

Compare traditional multi-agent setup with Radium's declarative approach. Radium handles orchestration, error recovery, and agent selection automatically.

Without Radium

Manual orchestration, complex error handling
120+ lines
// Manual agent orchestration
import { Agent, Task, Workflow } from 'agent-lib';

const codeAgent = new Agent({
  model: 'gpt-4',
  temperature: 0.2,
  maxTokens: 4000,
});

const reviewAgent = new Agent({
  model: 'claude-3-sonnet',
  temperature: 0.1,
  maxTokens: 8000,
});

async function orchestrateWorkflow(task: Task) {
  try {
    // Step 1: Code generation
    const codeResult = await codeAgent.run({
      prompt: task.description,
      context: await loadContext(),
    });

    if (!codeResult.success) {
      throw new Error('Code generation failed');
    }

    // Step 2: Code review
    const reviewResult = await reviewAgent.run({
      prompt: `Review: ${codeResult.output}`,
      context: codeResult.context,
    });

    // Step 3: Error recovery
    if (reviewResult.issues.length > 0) {
      const fixedCode = await codeAgent.run({
        prompt: `Fix: ${reviewResult.issues}`,
        context: reviewResult.context,
      });
      return fixedCode;
    }

    return reviewResult;
  } catch (error) {
    // Manual fallback logic
    console.error('Workflow failed:', error);
    throw error;
  }
}

With Radium

Declarative workflow, automatic orchestration
12 lines
# agents/workflow.toml
[[agents]]
id = "code-generator"
model = "gpt-4"
persona = "expert-developer"

[[agents]]
id = "code-reviewer"
model = "claude-3-sonnet"
persona = "senior-reviewer"

[workflow]
steps = [
  { agent = "code-generator", input = "task.description" },
  { agent = "code-reviewer", input = "previous.output" }
]
policy = "require-approval"
error_recovery = "auto-retry"

Ready to Get Started?

Install Radium in minutes and start building autonomous agent workflows today. Join our growing community of developers building the future of AI orchestration.