HomeProjectsArticlesPK BoardAbout
Explore Projects

Suna

Active
GitHub TypeScript NOASSERTION

Description

An autonomous company operating system powered by AI agents, providing intelligent workflow automation for research, data analysis, customer communication and other business processes.

Key Features

  • Company-as-code operating system with agents, skills, connectors, and memory in a git repo
  • Each session runs in an isolated cloud sandbox on its own branch with disposable Linux environment
  • 3000+ app connectors via MCP, OpenAPI, GraphQL, and raw HTTP with server-side token brokering
  • Change request workflow ensuring human review before work merges to main
  • Encrypted secrets manager with per-person scoping, injected at runtime and never exposed to models
  • Self-hostable on laptop, VPC, or air-gapped infrastructure with full audit trail

Use Cases

💡 Enterprise-scale autonomous workflow automation across multiple business processes
💡 AI agent orchestration for research, data analysis, and customer communication
💡 Self-hosted AI workforce deployment with enterprise security and compliance
💡 Parallel execution of thousands of isolated agent sessions simultaneously

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (20.2k stars)
  • • Responsive to issues, low backlog

⚠️ Limitations

  • • No clear open-source license

Tags

agent multi-agent typescript workflow automation

Categories

🔄 Workflow 🧠 Multi-Agent

Quick Start

curl -fsSL https://kortix.com/install | bash && kortix init && kortix ship
Visit GitHub

Related Projects

Cultivation World Simulator

2.1k · Python
Active A

An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world. Showcases multi-agent collaboration in complex scenarios.

multi-agentworkflowagent +1
  • · Every NPC is an independent LLM-driven agent with unique personality, memory, relationships, and decision-making logic
  • · Emergent storytelling with no preset scripts — sect wars, rivalries, and character arcs arise from world rules and AI interactions
  • · Rich cultivation world system including spirit roots, realms, techniques, sects, alchemy, artifacts, and martial tournaments
View on GitHub

make-it-heavy

1.1k · Python
Stale C

A Python framework that emulates Grok Heavy functionality using intelligent multi-agent orchestration. Deploy 4 (or more) specialized AI agents in parallel to deliver comprehensive, multi-perspective analysis on any query.

multi-agentworkflowpython +1
  • · Grok Heavy emulation: multi-agent system delivering deep, comprehensive multi-perspective analysis
  • · Parallel intelligence: deploy 4 (configurable) specialized AI agents simultaneously for different analytical perspectives
  • · Dynamic question generation: AI automatically creates customized research sub-questions from user queries
View on GitHub

OpenMontage

55.7k · Python
Active A

World's first open-source, agentic video production system with 12 pipelines, 52 tools, and 500+ agent skills. Turn your AI coding assistant into a full video production studio.

multi-agentautomationagent +2
  • · 12 production pipelines, 52 tools, and 500+ agent skills for video creation
  • · Real video production — retrieves actual motion footage, not just still image animation
  • · AI-powered scripting, narration, asset generation, editing, and final composition
View full details → View on GitHub

Ralph Orchestrator

3.1k · Rust
Active A

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration, built in Rust for reliable multi-agent task coordination and scheduling.

multi-agentrustagent +1
  • · Ralph Wiggum autonomous iteration technique - Keeps AI agents in a continuous loop until task completion or iteration limit
  • · Hat system - Specialized personas coordinating through events with built-in patterns (code-assist, debug, research, review, pdd-to-code-assist)
  • · Multi-backend support - Compatible with Claude Code, Kiro, Gemini CLI, Codex, Amp, Copilot CLI, OpenCode
View on GitHub