ai-evals

AgentOS: Build AI Agents with Enterprise-Grade Memory

Name: AgentOS: Build AI Agents with Enterprise-Grade Memory
Author: framersai

Create multi-agent AI systems with cognitive memory and runtime tool generation. Perfect for founders building intelligent, adaptive AI applications in TypeScript.

563 stars76 forksTypeScriptUpdated 6/2/2026100% free · open source

What it does

Creates adaptive AI systems with multiple intelligent agents that can dynamically generate tools and remember past interactions

When to use it

•Building complex customer support chatbots with memory and context
•Developing research assistants that can autonomously explore and solve multi-step problems
•Creating interactive simulation environments with intelligent, learning agents

Quick start

1Install via npm: npm install agentos
2Define agent classes with memory and tool generation capabilities
3Create agent networks with specified interaction protocols
4Configure LLM provider and runtime parameters

Ready-to-paste prompt

const researchAgent = new Agent({ memory: 'contextual', tools: ['search', 'summarize'] })

Topics

agent-framework

agent-memory

agentic-ai

ai-agent-framework

ai-agents

autonomous-agents

cognitive-memory

emergent-behavior

guardrails

hexaco

llm

llm-orchestration

long-term-memory

multi-agent

rag

runtime-tool-generation

tool-use

vector-search

voice-ai

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

24.2M

repo size

Apache-2.0

license

Key files

eslint.config.js

MAINTAINERS.md

package.json

README.md

release.config.js

tsconfig.build.json

File tree

.github/

assets/

docs/

examples/

scripts/

src/

tests/

.coderabbit.yaml

.gitignore

CHANGELOG.md

CITATION.cff

codecov.yml

CONTRIBUTING.md

eslint.config.js

LICENSE

MAINTAINERS.md

package.json

pnpm-lock.yaml

README.md

release.config.js

SPONSORS.md

SUPPORT.md

tsconfig.build.json

tsconfig.json

Quick Actions

Details

Creator

framersai

Language

TypeScript