OpenSail

v1.0.0Cloud Servicesstable

OpenSail is the open-source alternative to Codex App, Claude Desktop, Cursor, and Cowork for agentic software work.

agentsaiautomationbtrfsconnectors
Share:
539
Stars
0
Downloads
0
Weekly
0/5

What is OpenSail?

OpenSail is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to opensail is the open-source alternative to codex app, claude desktop, cursor, and cowork for agentic software work.

OpenSail is the open-source alternative to Codex App, Claude Desktop, Cursor, and Cowork for agentic software work.

This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • OpenSail is the open-source alternative to Codex App, Claude

Use Cases

Open-source alternative to Codex App
Agentic software development
Desktop and cloud deployment
TesslateAI

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx opensail

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use OpenSail

OpenSail is an open-source agentic software development platform that functions as a self-hostable alternative to Codex App, Claude Desktop, Cursor, and similar AI coding tools. It provides a desktop app, a full-stack backend (FastAPI, PostgreSQL, LiteLLM), a Kubernetes-ready deployment pipeline, and 30+ connectors to business systems including GitHub, Slack, Linear, Salesforce, and MCP servers. Engineering teams and solo developers use it to build, orchestrate, and deploy AI agents that can write code, manage files, make network calls, run git operations, and trigger deployments across 22 cloud platforms.

Prerequisites

  • Docker and Docker Compose installed (for the recommended setup)
  • Git to clone the repository
  • A LiteLLM-compatible API key (LITELLM_MASTER_KEY) and model proxy endpoint (LITELLM_API_BASE)
  • A SECRET_KEY value for backend security (generate a random string)
  • macOS, Linux, or Windows with sufficient resources for Docker
1

Clone the repository

Clone OpenSail from GitHub to your local machine.

git clone https://github.com/TesslateAI/OpenSail
cd opensail
2

Configure environment variables

Copy the example .env file and populate it with required values. The three critical variables are SECRET_KEY, LITELLM_API_BASE, and LITELLM_MASTER_KEY.

cp .env.example .env
# Edit .env and set:
# SECRET_KEY=<random-value>
# LITELLM_API_BASE=<your-model-proxy-endpoint>
# LITELLM_MASTER_KEY=<your-litellm-key>
3

Start with Docker Compose

Build and start the full OpenSail stack. The web UI will be available at http://localhost after startup.

docker compose up --build -d

# Check status
./scripts/docker.sh status

# View logs for a specific service
./scripts/docker.sh logs backend
4

macOS native install (alternative)

On macOS, use the guided install script instead of Docker Compose for a native development setup.

./scripts/install-macos.sh
5

Configure project permissions

Each project can have fine-grained agent permissions defined in .tesslate/permissions.json. Set which operations agents are allowed to perform (allow, deny, or ask for approval).

# .tesslate/permissions.json example
{
  "shell_access": "ask",
  "network_calls": "allow",
  "git_push": "ask",
  "file_writes": "allow",
  "process_spawn": "deny"
}
6

Access the dashboard and create an agent

Open http://localhost in your browser. Use the @agent-builder to describe the agent you want — it drafts an agent with instructions, model preference, tool permissions, and MCP server connections.

OpenSail Examples

Client configuration

MCP server configuration to connect Claude Desktop to a running OpenSail instance.

{
  "mcpServers": {
    "opensail": {
      "command": "npx",
      "args": ["opensail"],
      "env": {
        "LITELLM_API_BASE": "http://localhost:8000",
        "LITELLM_MASTER_KEY": "your-litellm-master-key",
        "SECRET_KEY": "your-secret-key"
      }
    }
  }
}

Prompts to try

Example prompts for interacting with an OpenSail agent once deployed.

- "@agent-builder, create an agent that monitors our GitHub repo for new issues and posts summaries to Slack"
- "Deploy the current main branch to Vercel and report back the deployment URL"
- "Schedule a daily workflow that pulls Linear tickets, updates their status, and sends a digest to the team"
- "Connect to our internal API and create a report of all open customer support tickets"
- "Set up an agent that reviews PRs and adds comments when it finds potential bugs"

Troubleshooting OpenSail

Docker Compose startup fails or services are unhealthy

Ensure all required .env values are populated (SECRET_KEY, LITELLM_API_BASE, LITELLM_MASTER_KEY). Run ./scripts/docker.sh logs backend to see backend errors. Check that Docker has enough memory allocated (at least 4GB recommended).

Agents cannot access external APIs or network resources

Check .tesslate/permissions.json in your project root and ensure network_calls is set to 'allow'. If the file does not exist, create it with the desired permission policy.

LiteLLM model proxy returns authentication errors

Verify that LITELLM_MASTER_KEY matches your LiteLLM configuration and that LITELLM_API_BASE points to the correct endpoint. If running LiteLLM locally, confirm it is started and accessible at the configured port.

Frequently Asked Questions about OpenSail

What is OpenSail?

OpenSail is a Model Context Protocol (MCP) server that opensail is the open-source alternative to codex app, claude desktop, cursor, and cowork for agentic software work. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install OpenSail?

Follow the installation instructions on the OpenSail GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with OpenSail?

OpenSail works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is OpenSail free to use?

Yes, OpenSail is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Cloud Services MCP Servers

Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "opensail": { "command": "npx", "args": ["-y", "opensail"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use OpenSail?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides