workflowstacks
ai-evals

Build AI Agents with Agentos

Get a TypeScript AI agent framework for multi-agent orchestration.
606 stars90 forksTypeScriptGuide quality 8/10Updated 7/26/2026100% free · open source
What it does

Agentos is a TypeScript AI agent framework that enables the creation of autonomous AI agents for multi-agent orchestration with cognitive memory and runtime tool forging capabilities.

When to use it
  • •When building autonomous systems that require multiple AI agents to interact and make decisions
  • •When needing to integrate multiple large language models (LLMs) from different providers into a single application
  • •When developing complex, dynamic workflows that require adaptive decision-making and execution
Ready-to-paste prompt
Create an agent that uses the OpenAI LLM provider to generate text based on user input: `const agent = new Agent({ provider: 'openai' }); agent.setup(); agent.loop('generate text based on user input');`
Heads up: Make sure to set the `OPENAI_API_KEY` environment variable before running the agent, as it is required for the OpenAI LLM provider to function
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/agentos && curl -fsSL https://workflowstacks.com/api/skills/agentos/claude-skill -o ~/.claude/skills/agentos/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Build AI Agents with Agentos works
Codeflow
Free to inspect

Build AI Agents with Agentos is a very large TypeScript project (~252k lines across 1014 code files, plus 632 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit a month ago, Apache-2.0 license, has a test suite.

Size
Very large codebase
~252k lines · 1014 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Node.js
No API keys detected
TypeScript 99%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    src/index.ts
    Where the program starts running
  3. 3
    package.json
    Dependencies and the commands it exposes
  4. 4
    examples/agency-graph.mjs
    A worked example — copy this to get going
What's in each folder
src/Core code — the actual logic1519 files
docs/Documentation95 files
examples/Examples you can copy37 files
scripts/Helper scripts13 files
tests/Tests — proof it works106 files
assets/Images & static assets24 files
.github/CI / automation (GitHub Actions)12 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated 1 mo ago
Quick Actions
Details
Creator
framerslab
Language
TypeScript
Category
ai-evals
Published
10/28/2025

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More ai-evals tools founders pair with this one.

ai-evals★ 9,107
Baml: Boost Prompt Engineering
Get structured output with Baml, for founders using AI.
ai-evals★ 6,192
Adversarial Robustness Toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
ai-evals★ 2,152
Adversary Emulation Library
An open library of adversary emulation plans designed to empower organizations to test their defenses based on real-world TTPs.
ai-evals★ 547
agentsight: System-Level AI Tracing
Get system-level AI agent insights with agentsight, a zero instrument tracing tool, using eBPF.
ai-evals★ 345
VerifyWise: AI Governance
Get comprehensive AI governance with VerifyWise, for founders needing AI compliance and risk management.