elizaOS
TypeScript multi-agent framework for persistent AI characters across social platforms
View on GitHubWhat it solves
Giving an AI a persistent identity: elizaOS builds agents that remember who they've talked to, maintain consistent personas, and act continuously across multiple platforms without resetting.
Overview
elizaOS is a TypeScript framework for building AI agents that maintain consistent identities, memories, and relationships across Discord, Twitter/X, Telegram, and custom apps. The agent runtime manages a continuous event loop, plugin system, and cross-platform message routing. Each agent gets persistent memory, a personality configuration, and optional on-chain integrations. The primary choice for projects where persistent character identity across social platforms is the core requirement.
Key facts
- Language
- TypeScript
- License
- MIT
- Maturity
- Fast-moving
- Maintainer
- elizaOS
- Reviewed
- 2026-06-11
Where to start
The AgentRuntime class shows how memory, actions, providers, and evaluators compose into a persistent agent loop, the architecture is clearer in the source than the docs.
packages/core/src/runtime.tsTechnologies
More in this domain
LangGraph
Stateful multi-agent orchestration for LLM applications
The state management problem in multi-agent systems: how you build agents that pass context across turns without losing the execution thread.
AutoGen
Multi-agent conversation framework from Microsoft Research
How to coordinate multiple specialized agents toward a shared goal without writing low-level orchestration logic by hand.
CrewAI
Role-based multi-agent orchestration for collaborative task execution
The boilerplate problem in multi-agent setup: defining roles, delegation rules, and task routing without writing a custom orchestration graph.