Skip to content

AWS Partner · Software Sushi documentation

Ready-to-run software on AWS, documented end to end

Guides for Software Sushi products on AWS Marketplace: AMIs and SageMaker model packages you run in your own account, with your data and your keys.

77
products documented
7
categories
AWS
Partner · billed through your AWS account

Products

OpenClaw AI Agent

AI Agents · v1.27.0

Self-hosted OpenClaw AI agent on hardened Ubuntu. Connect Telegram, Slack or Discord with your own keys.

Read the docs → Launch on AWS

Hermes AI Agent

AI Agents · Hermes v0.23.1

Nous Research's Hermes AI agent on hardened Ubuntu, chatting on Telegram with your own model key.

Read the docs → Launch on AWS

Hermes AI Agent + n8n

AI Agents

Hermes AI agent and n8n workflow automation, preconnected on hardened Ubuntu. Hermes builds and runs your workflows.

Read the docs → Launch on AWS

Sushi OpenShell

AI Agents · OpenShell v0.1.2

NVIDIA OpenShell on Graviton: policy-controlled Docker sandboxes behind a private mTLS gateway.

Read the docs → Launch on AWS

OpenHands Core

AI Agents · OpenHands v1.24.0

Self-hosted OpenHands Agent Canvas with Python, terminal and Git tools, plus optional private Telegram.

Read the docs → Launch on AWS

Nanobot AI Agent

AI Agents · Nanobot 0.3.5

Self-hosted nanobot agent with a password-protected web UI, workspace file tools and private Telegram.

Read the docs → Launch on AWS

Agent Zero Core

AI Agents · AgentZeroCore v2.13

Focused Agent Zero workbench with file, Bash and Python tools, your own cloud model and private Telegram.

Read the docs → Launch on AWS

Aider AI Pair Programmer

AI Agents · Aider 0.86.2+sushi.2

Terminal AI pair programmer that edits and commits to your git repo, with the model provider you choose.

Read the docs → Launch on AWS

Goose CLI Agent

AI Agents · Goose v1.54.0

Open-source CLI agent that plans tasks, edits files and runs commands on a private instance.

Read the docs → Launch on AWS

Open Interpreter

AI Agents · Open Interpreter 0.4.2+sushi.2

Let a model write and run code from plain-English requests, with confirmation before every run.

Read the docs → Launch on AWS

Tabby Coding Assistant

AI Agents · Tabby v0.32.0

Self-hosted AI code completion and chat server on loopback; attach the model you choose after launch.

Read the docs → Launch on AWS

OpenCode Coding Assistant

AI Agents · OpenCode 1.19.4

OpenCode 1.19.4 terminal coding assistant with a sample workspace, a local file-edit check, and your own model provider after launch.

Read the docs → Launch on AWS

CrewAI Agent Starter

AI Agents · CrewAI 1.15.28

Two-agent CrewAI 1.15.28 starter that turns a sample sales CSV into checked JSON, using Amazon Bedrock Nova Lite or an offline fixture.

Read the docs → Launch on AWS

Agno AgentOS API

AI Agents · Agno 3.1.11

Agno 3.1.11 AgentOS API on loopback, with a CSV calculation tool and SQLite sessions. You bring an OpenAI-compatible model.

Read the docs → Launch on AWS

Browser Use Browser Agent

AI Agents · Browser Use 0.10.1

Browser Use 0.10.1 with local headless Chromium. The included walkthrough uses a local fixture; other tasks use a model you configure.

Read the docs → Launch on AWS

LangGraph Workflow Starter

AI Agents · LangGraph 1.2.18

LangGraph 1.2.18 workflow with SQLite checkpoints and a human-approval step. You bring a JSON-object model.

Read the docs → Launch on AWS

Mem0 Self-Hosted Memory API

AI Agents · Mem0 2.2.1

Mem0 2.2.1 memory API on loopback HTTPS, with a separate Qdrant store and SQLite history per API user. You bring the embedding provider.

Read the docs → Launch on AWS

Sushi ML Studio

AI Platform & Data · v1.2.0

No-code machine learning in your browser: upload a spreadsheet, train scikit-learn models, predict.

Read the docs → Launch on AWS

DuckDB Analytics

AI Platform & Data · DuckDB v1.5.6

DuckDB CLI for fast local CSV and Parquet queries, with pinned extensions for reading your S3 data.

Read the docs → Launch on AWS

Open WebUI

AI Platform & Data · Open WebUI v0.11.4

Private ChatGPT-style chat UI for any OpenAI-compatible endpoint, reached through Session Manager.

Read the docs → Launch on AWS

AnythingLLM RAG Workbench

AI Platform & Data · AnythingLLM v1.17.0

Self-hosted AnythingLLM workspace to chat with your documents (RAG) using the models you choose.

Read the docs → Launch on AWS

Flowise

AI Platform & Data · Flowise 3.1.4

Drag-and-drop Flowise builder for LLM chatbots, RAG pipelines and agents, on loopback-only HTTPS.

Read the docs → Launch on AWS

LiteLLM Proxy

AI Platform & Data · LiteLLM 1.104.2

LiteLLM gateway: one OpenAI-compatible HTTPS endpoint in front of all your LLM providers.

Read the docs → Launch on AWS

Qdrant Vector Database

AI Platform & Data · Qdrant v1.19.2

Private single-node Qdrant vector database for RAG and semantic search, with a per-instance API key.

Read the docs → Launch on AWS

Docling document conversion

AI Platform & Data · Docling

Convert born-digital PDF and DOCX files into Markdown and structured JSON on CPU. Local layout and table models are included; OCR and remote enrichment are disabled.

Read the docs → Launch on AWS

Typesense search server

AI Platform & Data

Index a product catalog and query typo-tolerant text search, filters and facets on one instance. The source-built single-node server uses local persistent storage behind a private authenticated HTTPS gateway.

Read the docs → Launch on AWS

Whisper CPU transcription

AI Platform & Data

Transcribe English and Spanish recordings on CPU with faster-whisper and a bundled multilingual small model. Responses include text, segments and word timestamps. No model-provider account or GPU is required.

Read the docs → Launch on AWS

Presidio text redaction

AI Platform & Data

Detect and replace selected sensitive entities in English and Spanish text using local Presidio analysis and bundled spaCy models. Responses include redacted text and input spans.

Read the docs → Launch on AWS

Langflow

AI Platform & Data · Langflow 1.13.0

Langflow 1.13.0 visual editor, package 0.2.1, with an administrator login, SQLite storage, a local demo, and your own model provider.

Read the docs → Launch on AWS

Gradio AI Interface

AI Platform & Data · Gradio 6.30.0

Authenticated Gradio 6.30.0 page for a local sentiment model, with SQLite results you can read back on Ubuntu 24.04.

Read the docs → Launch on AWS

Chroma Vector Database

AI Platform & Data · chroma 1.5.9

Persistent Chroma 1.5.9 vector database on loopback for embeddings you supply, with a demo that checks the saved vectors.

Read the docs → Launch on AWS

MLflow Experiment Tracker

AI Platform & Data · mlflow 3.17.2

MLflow 3.17.2 tracking server for parameters, metrics and artifacts, with a per-instance sign-in and local SQLite storage.

Read the docs → Launch on AWS

LibreChat

AI Platform & Data · LibreChat 0.8.8

LibreChat 0.8.8 chat workspace on Ubuntu 24.04. Bring your own TLS MongoDB and Amazon Bedrock Nova Lite. No database server is included.

Read the docs → Launch on AWS

Sentiment Studio

AI Platform & Data · Streamlit 1.66.1

Sentiment Studio 0.1.0 local Streamlit page for one text field or a small CSV. Sign in through a Session Manager tunnel. No model provider or external database.

Read the docs → Launch on AWS

Vane Search

AI Platform & Data · Vane 1.12.2

Vane 1.12.2 answer engine with SearxNG citations on Ubuntu 24.04. You bring the chat and embedding models. Package 0.2.2.

Read the docs → Launch on AWS

Chatterbox Text-to-Speech

AI Platform & Data · Chatterbox TTS

Chatterbox Nano text-to-speech on CPU. One English sentence at a time, in the voice of a short sample you provide. Package 0.1.7.

Read the docs → Launch on AWS

PDF Translator

AI Platform & Data · PDF Translator, BabelDOC 0.6.2

Translate digital English PDFs into Spanish and keep the page layout. BabelDOC 0.6.2 with your own translation model. Package 0.1.4.

Read the docs → Launch on AWS

Crawl4AI Web Extractor

AI Platform & Data · Crawl4AI 0.9.5

Crawl4AI 0.9.5 turns pages into Markdown and JSON with a headless browser. Token-protected HTTPS on the instance. Package 0.2.7.

Read the docs → Launch on AWS

PaddleOCR Text Recognition

AI Platform & Data · PaddleOCR 3.7.0

PaddleOCR 3.7.0 reads English text from PNG and JPEG images on CPU and returns words, scores, and boxes. Package 0.1.3.

Read the docs → Launch on AWS

BentoML Prediction Server

AI Platform & Data · BentoML 1.4.39

BentoML 1.4.39 prediction API on CPU with a bundled scikit-learn sample model and a Swagger page. Package 0.1.3.

Read the docs → Launch on AWS

DeepEval Evaluation Workbench

AI Platform & Data · DeepEval 4.2.4

DeepEval 4.2.4 checks on fixed synthetic answers, with saved JSON reports and an optional model judge you configure.

Read the docs → Launch on AWS

Evidently Data Drift Reports

AI Platform & Data · Evidently 0.7.23

Evidently 0.7.23 tabular drift reports on one instance, with a loopback UI and HTML and JSON export. No model account is required.

Read the docs → Launch on AWS

Haystack Document API

AI Platform & Data · Haystack 3.4.1

Haystack 3.4.1 and Hayhooks 2.1.0 document API with local BM25 retrieval. Optional answers use a chat model you supply.

Read the docs → Launch on AWS

LocalAI CPU Model API

AI Platform & Data · LocalAI 4.12.0

LocalAI 4.12.0 CPU API for a bundled Qwen2.5-0.5B-Instruct model, authenticated on loopback. No external inference account.

Read the docs → Launch on AWS

Caddy HTTPS Gateway

Networking & Security · caddy v2.11.7

Caddy reverse proxy, private by default, with a per-instance local CA and automatic HTTPS.

Read the docs → Launch on AWS

HAProxy Community LTS

Networking & Security · HAProxy 3.4.6

HAProxy LTS HTTP load balancer with a password-protected stats page.

Read the docs → Launch on AWS

WireGuard Private Access

Networking & Security · wireguard-tools 1.0.20260223

WireGuard endpoint with keys generated on first boot and UDP 51820 closed until you add peers.

Read the docs → Launch on AWS

Unbound DNS Resolver

Networking & Security · Unbound 1.26.1

Validating, caching DNS resolver that answers on loopback only until you open it up.

Read the docs → Launch on AWS

OpenSSH SFTP Drop Box

Networking & Security · OpenSSH 9.6p1

OpenSSH SFTP drop box: key-only users locked to their own folder, with no shell.

Read the docs → Launch on AWS

Uptime Kuma Monitoring

Observability · uptime-kuma v2.5.5

Uptime monitoring with HTTP, TCP, DNS and ping checks behind a private HTTPS dashboard.

Read the docs → Launch on AWS

Gatus Status Page

Observability · gatus v5.37.0

Status page with HTTP, TCP and DNS checks, SQLite history and per-instance TLS.

Read the docs → Launch on AWS

Fluent Bit Log Gateway

Observability · FluentBit v5.1.3

Fluent Bit log gateway with HTTPS ingest, a bounded disk buffer and a local file output.

Read the docs → Launch on AWS

Vector Log Pipeline

Observability · Vector 0.58.0

Vector log pipeline with authenticated HTTPS and file ingest, VRL redaction and a disk buffer.

Read the docs → Launch on AWS

OpenTelemetry Collector Gateway

Observability · otelcol 0.162.0

OpenTelemetry Collector OTLP gateway for traces, metrics and logs, with TLS and file export.

Read the docs → Launch on AWS

Gotify Notification Server

Observability · Gotify 3.1.1-sushi1

Private Gotify notification server with a REST API, web UI, live WebSocket stream and history.

Read the docs → Launch on AWS

Langfuse LLM Observability

Observability · Langfuse 4.56.0

Self-hosted Langfuse to trace, evaluate and debug LLM apps, with the full single-node stack.

Read the docs → Launch on AWS

VictoriaMetrics single-node

Observability

Store time-series samples and query them with MetricsQL on one instance. The community single-node server uses local disk and one-month retention behind a private authenticated HTTPS gateway.

Read the docs → Launch on AWS

Promptfoo Evaluation Workbench

Observability · Promptfoo 0.124.1

Promptfoo 0.124.1 workbench to compare prompt variants and inspect JSON and SQLite results, including a model-free example.

Read the docs → Launch on AWS

Valkey Single-Node Cache

Messaging & Data Services · Valkey 9.1.2

Valkey single-node cache with loopback TLS, an ACL user, an LRU memory cap and no persistence.

Read the docs → Launch on AWS

PgBouncer Connection Pooler

Messaging & Data Services · PgBouncer 1.26.0

PgBouncer PostgreSQL connection pooler with required client TLS and SCRAM authentication.

Read the docs → Launch on AWS

NATS Core Broker

Messaging & Data Services · nats-server v2.15.0

NATS Core broker with loopback TLS, per-user subject permissions and the nats CLI.

Read the docs → Launch on AWS

Mosquitto MQTT Broker

Messaging & Data Services · mosquitto v2.1.2

Eclipse Mosquitto MQTT broker with loopback TLS, users, topic ACLs and persistence.

Read the docs → Launch on AWS

OpenTofu Runner

Automation & Backup · OpenTofu 1.13.1

OpenTofu with a pinned offline AWS provider mirror for validate and plan. Nothing auto-applies.

Read the docs → Launch on AWS

Ansible Core Runner

Automation & Backup · ansible-core 2.21.4

ansible-core runner with pinned collections, a localhost inventory and a vault password.

Read the docs → Launch on AWS

Restic Backup Worker

Automation & Backup · restic v0.19.1

restic backup worker: daily encrypted backups, a safe restore script and an optional S3 repository.

Read the docs → Launch on AWS

Rclone Transfer Worker

Automation & Backup · rclone v1.76.0

rclone transfer worker: a daily checksum copy that never deletes, with an optional S3 target.

Read the docs → Launch on AWS

Gitea Git hosting

Automation & Backup

Host private Git repositories, issues and pull requests on one instance with SQLite storage and native HTTPS authentication. The first boot creates a private administrator account.

Read the docs → Launch on AWS

Brazilian Personal Data Redaction for Portuguese Text (LGPD)

SageMaker models

Finds Brazilian personal data in Portuguese text and can replace, mask, remove, or report it, inside your SageMaker account. It can miss items.

Read the docs → Launch on AWS

Support Ticket Classifier

SageMaker models

Classifies Spanish, Portuguese, and English support tickets into intent, urgency, sentiment, and language. Scores can be wrong, and a person still reviews them.

Read the docs → Launch on AWS

Multilingual Relevance Reranker (ES/PT/EN)

SageMaker models

Reorder English, Spanish and Portuguese passages with original BAAI relevance scores and stable source IDs in your SageMaker account. Inspect the source before using ranked context.

Read the docs → Launch on AWS

LatAm Identifier Redaction

SageMaker models

Redact supported Latin American identifiers and email syntax in Spanish text. Names and addresses remain outside this release.

Read the docs → Launch on AWS

E-Invoice Extractor — XML and PDF Preview

SageMaker models

Extract selected XML invoice fields and supported printed or scanned PDF fields, preserving decimal strings and explicit missing values.

Read the docs → Launch on AWS

Source-Grounded Business Summaries (ES/PT/EN)

SageMaker models

Create review-required summaries and action candidates linked to literal source segments in English, Spanish and Portuguese.

Read the docs → Launch on AWS

NextChat Web Assistant

AI Platform & Data · NextChat v2.16.1

NextChat 2.16.1 browser frontend with a private tunnel, your OpenAI-compatible endpoint and saved API walkthroughs.

Read the docs → Launch on AWS

DSPy Classifier Workspace

AI Platform & Data

Prepublication: DSPy 3.4.1 Python SDK and a saved-result classifier workflow. Limited availability; no public subscription.

Read the docs → Launch on AWS

vLLM GPU Model API

AI Platform & Data

Prepublication: vLLM 0.32.0 on one L4, with vendor runtime download at first boot and your local model. Not publicly available.

Read the docs → Launch on AWS

Assisted Business Document Type Suggestions (ES/PT/EN)

SageMaker models

Offer two type suggestions for extracted ES/PT/EN business text, with mandatory manual choice or rejection and generated-only validation.

Read the docs → Launch on AWS

How an AMI works

  • 1. Subscribe

    Pick the product on our AWS Marketplace seller profile. Most products include a free trial.

  • 2. Launch

    Start an EC2 instance from the listing with your own key pair, VPC and security group. Secrets are generated on first boot. The launch kit does this with no inbound ports.

  • 3. Follow the guide

    Each product's getting-started page takes you from launch to a working service, then configuration and day-two operations.

Billing runs through your AWS account: the product's hourly software fee plus the usual EC2, EBS and data-transfer charges. Stop any time by terminating the instance.

How a SageMaker model package works

  • 1. Subscribe

    Open the model on AWS Marketplace and subscribe in your own account. The model package primer is the shared path.

  • 2. Create the model

    Create a SageMaker model from the subscribed package, with network isolation. Real-time endpoints and batch transform jobs run on instance types the product guide names.

  • 3. Clean up

    Delete the endpoint, its configuration, and the model when the test is finished. A batch job stops when it ends. S3 objects remain until you delete them.

Software charges and SageMaker infrastructure charges are billed separately. Your text stays in your account. Each model's guide states its inputs and the limits of its published evaluation.

Need help?

Write to info@softwaresushi.com with the product name, its version and your AWS Region. Software Sushi is an AWS Partner; every product is supported by the engineers who build it.