Shannon

Normal
GitHub Go MIT

Description

Shannon is a production-oriented multi-agent orchestration framework built in Go, focusing on efficient and reliable agent coordination and task scheduling for enterprise-grade multi-agent systems.

Key Features

  • Production-grade multi-agent orchestration with 8 execution strategies — Simple, DAG, ReAct, Research, Exploratory, Browser Use, Domain Analysis, and Swarm — auto-routed by task complexity
  • Temporal workflow engine with time-travel debugging — replay any agent execution step-by-step for full observability and post-mortem analysis
  • Hard token budget control per task/agent with automatic model fallback and cost optimization — research strategy reduces costs 50-70%
  • WASI sandbox for secure code execution with OPA policy enforcement, multi-tenant isolation, and Prometheus/OpenTelemetry observability
  • OpenAI-compatible API with Python SDK, REST API, SSE streaming, and desktop app — drop-in replacement for existing OpenAI integrations
  • Human-in-the-loop approval workflows via OPA policies with WebSocket-based daemon clients, scheduled tasks, and session continuity

Use Cases

💡 Enterprise multi-agent systems requiring production reliability, cost controls, and compliance with audit trails
💡 Research-heavy workloads using tiered model strategies to optimize cost while maintaining quality across deep analysis tasks
💡 Autonomous swarm teams for complex problem decomposition with lead-orchestrated multi-agent convergence detection
💡 Browser automation tasks using Playwright-backed web interaction agents with session continuity and real-time streaming
💡 Scheduled autonomous analysis pipelines with token budget enforcement and automatic model selection based on task complexity

Tags

multi-agent framework go agent automation

Categories

🧠 Multi-Agent 🤖 Agent Framework

Quick Start

Run the one-command install: `curl -fsSL https://raw.githubusercontent.com/Kocoro-lab/Shannon/main/scripts/install.sh | bash`. Set your LLM API key (OpenAI or Anthropic), then submit tasks via REST API (`POST /api/v1/tasks`) or Python SDK. Shannon auto-routes tasks to optimal strategies and streams results via SSE.
Visit GitHub Visit Website

Related Projects