symbiont

Official

Policy-driven AI agent runtime

AuthorThirdKeyAI
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Symbiont provides a secure, policy-driven runtime to build autonomous AI agents with typestate-enforced ORGA reasoning, Cedar policy authorization, knowledge bridge, zero-trust security, multi-tier sandboxing, webhook verification, markdown memory, skill scanning, metrics, scheduling, and a declarative DSL

Core Features & Use Cases

  • Typestate-enforced Observe-Reason-Gate-Act ORGA loop with compile-time safety.
  • Cedar policy engine for runtime authorization and policy-as-code.
  • Knowledge bridge with vector-based memory for contextual reasoning and learning.
  • Multi-tier sandboxing (Docker, gVisor, Firecracker) for safe agent execution.
  • Webhook verification, AgentPin/SchemaPin cryptography, and Markdown memory persistence.
  • Scheduling, metrics, and agent delivery/routing capabilities across channels.

Quick Start

Define your Symbiont agent in the DSL, then parse the DSL and launch the runtime to execute the agent.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: symbiont
Download link: https://github.com/ThirdKeyAI/Symbiont/archive/main.zip#symbiont

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.