T20: Multi-Agent. Orchestrator-delegate model. TAS. Goal -> plan -> delegate. Agents: Gemini family. Autonomous, traceable. Logs sessions. CLI. Usage: t20-cli "goal string". Artifacts of high value.

T20 Multi-Agent System

[🧮MTC|LCP] [🪬Demo] [📖Docs]

T20 is a sophisticated, multi-agent framework designed to tackle complex tasks through collaborative AI. It empowers you to solve complex problems by assembling a team of specialized AI agents that work together, orchestrated by a central planner.

Philosophy

The T20 system is built on the idea of Cognitive Cadence: a structured, iterative process where AI agents with different "cognitive roles" collaborate to build knowledge and produce results. This approach mirrors a human team, where planners, researchers, and specialists work in a coordinated fashion. Our goal is to create a system that is not only powerful but also transparent and traceable, allowing you to understand and debug the entire problem-solving process.

How It Works

T20 employs an orchestrator-delegate model. The workflow is simple yet powerful:

1. Goal Definition: You provide a high-level goal (e.g., "Create a landing page for a new app").
2. Dynamic Planning: A lead Orchestrator agent analyzes the goal and generates a step-by-step plan.
3. Task Delegation: The Orchestrator assigns each task to the most suitable specialist agent.
4. Iterative Execution: Agents execute their tasks, building upon each other's work.
5. Transparent Logging: Every step, prompt, and output is logged for full traceability.

Here is a simplified view of the process:

[User Goal] -> [Orchestrator] -> [Step 1: Agent A] -> [Step 2: Agent B] -> [Final Output]
                      |
                  [Plan.json]

The Team

The system comes with a diverse team of pre-configured agents, each with a specific role. Agents are defined in simple YAML files in the agents/ directory.