workflowstacks
automation

JamAIBase: AI Automation

Build AI apps with real-time collaboration.
1,101 stars46 forksPythonGuide quality 8/10Updated 8/17/2026100% free · open source
What it does

JamAIBase allows founders to build AI apps with real-time collaboration, chaining cells into powerful pipelines and evaluating LLM responses together seamlessly

When to use it
  • •When you need to collaborate with team members on AI application development in real-time
  • •When you want to experiment with prompts and models in a shared, interactive environment
  • •When you need to evaluate and refine large language model (LLM) responses in a collaborative setting
Ready-to-paste prompt
Create a pipeline with a prompt cell containing 'Write a product description for a new smartwatch' and connect it to a model cell using the 'LLaMA' model to generate a response
Heads up: Make sure you have Python installed on your system, as well as the required dependencies specified in the JamAIBase README, before attempting to run the `python -m jamai` command
Saves to your device
Use with Claude
New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/jamaibase && curl -fsSL https://workflowstacks.com/api/skills/jamaibase/claude-skill -o ~/.claude/skills/jamaibase/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 JamAIBase: AI Automation works
Codeflow
Free to inspect

JamAIBase: AI Automation is a very large Python project (~89k lines across 573 code files, plus 73 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~89k lines · 573 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
Needs API keys (.env)
Python 60%Svelte 25%TypeScript 14%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    .env.example
    The API keys and settings you must provide
  4. 4
    services/app/README.md
    Inside services/app/ — the main logic begins here
What's in each folder
services/app/Core code — the actual logic474 files
services/api/Backend / API212 files
docs/Documentation3 files
clients/SDKs / client libraries115 files
docker/Deployment / infrastructure25 files
scripts/Helper scripts14 files
services/gateway/Folder3 files
services/replication/Folder3 files
READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
EmbeddedLLM
Language
Python
Category
automation
Published
5/30/2024

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

Related skills

More automation tools founders pair with this one.

automation★ 203,208
n8n: Automate Workflows
Streamline tasks with n8n, a fair-code automation platform for founders, with 191k+ GitHub stars.
automation★ 152,739
Langflow: AI-Powered Automation
Build AI-powered agents with Langflow. For founders needing automation.
automation★ 115,543
MoneyPrinterTurbo: AI Video Automation
Generate short videos with one click using AI. For founders needing automation.
automation★ 90,205
Core: Local Home Automation
Founders get private home automation with Core. For IoT startups.
automation★ 79,709
deer-flow: Automate Tasks
Founders automate tasks with deer-flow, a Python SuperAgent harness. Simplify workflows with this open-source tool.
automation★ 73,052
Strapi: Customizable Headless CMS
Get a developer-first CMS with Strapi. For founders needing flexible content management.