tinycrab
Developer Experience First

You're building something for AI agents.

You need one running ā€” for your test.

DevTestCIProd
$ tinycrab spawn dev
šŸ¦€ Running on :8080

One line. Running in seconds.

Get StartedI'm an AI Agent

One agent. From dev to prod.

Same tinycrab everywhere.

Local Dev

Debug your agent integration

$ tinycrab spawn dev
šŸ¦€ Agent running on :8080
Your MCP server logs:
ā†’ Agent called weather-api
ā†’ Agent called search-api

Tests

Multiple agents test your platform

šŸ¦€šŸ¦€šŸ¦€ 3 agents simultaneously:
ā†’ calling your MCP server
ā†’ using your skill.md
ā†’ testing concurrency

CI/CD

Runs on every PR

- run: tinycrab spawn ci
- run: npm test
Same agent as local
Automatic verification

Prod

Production deployment

$ docker run tinycrab
šŸ¦€ Agent running on :8080
Same agent, runs anywhere
Regression testing in prod

You don't need the most powerful agent.

You need an AI agent running right now.

Three Ways to Spawn

Choose your interface. Same agent underneath.

SDK

For TypeScript/JavaScript projects

import { Tinycrab } from 'tinycrab';

const tc = new Tinycrab({ apiKey: process.env.OPENAI_API_KEY });
const agent = await tc.agent('worker');

const result = await agent.chat('Write a hello world script');
console.log(result.response);
// ā†’ I've created hello.py with a simple hello world script.
//   The file prints "Hello, World!" when run.

await agent.destroy({ cleanup: true });

CLI

For quick testing in terminal

$ npm install -g tinycrab

$ tinycrab spawn my-agent
# ā†’ Agent 'my-agent' spawned
# ā†’ Server running on port 9000

$ tinycrab chat my-agent "Create a README"
# ā†’ [my-agent]: I've created README.md with project
#   documentation including installation and usage.
# ā†’ (session: abc123)

$ tinycrab cleanup my-agent
# ā†’ Agent 'my-agent' cleaned up

Docker

For CI/CD or cloud deployment

$ docker run -p 8080:8080 \
  -e OPENAI_API_KEY=sk-xxx \
  ghcr.io/jt-wang/tinycrab
# ā†’ Agent server running on port 8080

$ curl -X POST localhost:8080/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello"}'
# ā†’ {"response": "Hello! How can I help you?",
#    "session_id": "session-a1b2c3..."}

What You Get

Everything you need, nothing you don't.

Full coding capabilities

bash, read, write, edit, grep, find

Isolated workspaces

Each agent has its own directory

Session persistence

Multi-turn conversations with context

Cross-session memory

remember/recall for persistent knowledge

Autonomous scheduling

Agents schedule future actions, wake up, act

Self-spawning

Agents can spawn new agents via bash

Works Everywhere

Same code, same behavior. Test locally, deploy anywhere.

docker run -p 8080:8080 -e OPENAI_API_KEY=sk-xxx ghcr.io/jt-wang/tinycrab
Deploy Guide

Ready to spawn?

npm install -g tinycrab && tinycrab spawn my-agent

Coming soon: Agent Swarm - coordinate multiple agents working together