AgentOS · TypeScript AI Agent Framework

<div align="center">

<a href="https://agentos.sh">
  <img src="https://raw.githubusercontent.com/framerslab/agentos/master/assets/agentos-primary-no-tagline-transparent-2x.png" alt="AgentOS: TypeScript AI Agent Framework with Cognitive Memory" height="100" />
</a>

<br />

# **AgentOS** · TypeScript AI Agent Framework

**Agents that remember, forge their own tools, and survive long-running sessions.** Persistent cognitive memory, optional HEXACO personality, multi-agent orchestration, and one dispatch interface across 11 LLM providers. Apache-2.0.

[![npm](https://img.shields.io/npm/v/@framers/agentos?style=flat-square&logo=npm&color=cb3837)](https://www.npmjs.com/package/@framers/agentos)
[![CI](https://img.shields.io/github/actions/workflow/status/framerslab/agentos/ci.yml?branch=master&style=flat-square&logo=github&label=CI)](https://github.com/framerslab/agentos/actions/workflows/ci.yml)
[![tests](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/framerslab/agentos/master/.github/badges/tests.json&style=flat-square&logo=vitest&logoColor=white)](https://github.com/framerslab/agentos/actions/workflows/ci.yml)
[![codecov](https://codecov.io/gh/framerslab/agentos/graph/badge.svg)](https://codecov.io/gh/framerslab/agentos)
[![TypeScript](https://img.shields.io/badge/TypeScript-5.4+-3178c6?style=flat-square&logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue?style=flat-square)](https://opensource.org/licenses/Apache-2.0)
[![NVIDIA Inception](https://img.shields.io/badge/NVIDIA_Inception-Member-76B900?style=flat-square&logo=nvidia&logoColor=white)](https://www.nvidia.com/en-us/startups/)
[![LongMemEval-S](https://img.shields.io/badge/LongMemEval--S-85.6%25-2ea043?style=flat-square)](https://docs.agentos.sh/blog/2026/04/27/longmemeval-s-83-with-semantic-embedder)
[![LongMemEval-M](https://img.shields.io/badge/LongMemEval--M-70.2%25-2ea043?style=flat-square)](https://docs.agentos.sh/blog/2026/04/29/longmemeval-m-70-with-topk5)
[![agentos-bench](https://img.shields.io/badge/bench-public-blue?style=flat-square)](https://github.com/framerslab/agentos-bench)
[![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?style=flat-square&logo=discord)](https://wilds.ai/discord)

[**Benchmarks**](https://github.com/framerslab/agentos-bench/blob/master/results/LEADERBOARD.md) * [Website](https://agentos.sh) * [Docs](https://docs.agentos.sh) * [npm](https://www.npmjs.com/package/@framers/agentos) * [Discord](https://wilds.ai/discord) * [Blog](https://docs.agentos.sh/blog)

</div>

---

AgentOS is an open-source TypeScript framework for AI agents that **remember, adapt, and write their own tools**.

- **Top open-source memory benchmarks:** [85.6% on LongMemEval-S](https://github.com/framerslab/agentos-bench/blob/master/results/LEADERBOARD.md) at $0.0090/correct (gpt-4o), and 70.2% on LongMemEval-M, the only open-source library above 65% on M with reproducible methodology.
- **Runtime tool forging.** An agent writes a TypeScript function with a Zod schema, an LLM judge approves it, and it runs in a hardened `node:vm` sandbox before joining the catalog for the rest of the session.
- **Persistent [cognitive memory](https://docs.agentos.sh/features/cognitive-memory)** with 8 neuroscience-backed mechanisms: Ebbinghaus decay, retrieval-induced forgetting, reconsolidation, source-confidence decay.
- **Optional [HEXACO personality](https://docs.agentos.sh/features/hexaco-personality)**, [6 orchestration strategies](https://docs.agentos.sh/features/agency-collaboration), [guardrails](https://docs.agentos.sh/features/guardrails-architecture), and [voice](https://docs.agentos.sh/features/voice-pipeline) across **11 LLM providers**; 100+ extensions and 88 skills auto-load at startup.

---

<div align="center">

<picture>
  <source srcset="https://raw.githubusercontent.com/framerslab/agentos/master/assets/agentos-forge-demo.webp" type="image/webp" />
  <img src="https://raw.githubusercontent.com/framerslab/agentos/master/assets/agentos-forge-demo.gif"
       alt="Three AgentOS agents with distinct HEXACO personalities collaborate on a code review, forge a new tool at runtime once they hit a gap their static toolkit can't cover, the LLM judge approves the spec, and all three invoke it on the next turn."
       width="900" />
</picture>

<sub>Runtime tool forging + multi-agent collaboration. Reproduce with <code>node <a href="https://github.com/framerslab/agentos/blob/master/examples/emergent-hierarchical-spawning.mjs">examples/emergent-hierarchical-spawning.mjs</a></code>.</sub>

</div>

---

## Install

```bash
npm install @framers/agentos
```

```typescript
import { agent } from '@framers/agentos';

const tutor = agent({
  provider: 'anthropic',                          // resolves to claude-sonnet-4-6 (provider default)
  // model: 'claude-opus-4-8',                    // pin a specific model to override the default
  instructio

... (truncated)