Moterra
Managed private deployment of Claude Cowork and Code inside the customer's own AWS or Azure account for regulated industries, with permission aware retrieval, read and write connectors and agents built on Dify.
Moterra deploys Anthropic's Claude Cowork and Claude Code as a managed private service inside the customer's own AWS or Azure account, for regulated industries such as legal, financial services, insurance and healthcare. The customer owns the account, the network, the customer managed encryption keys and the choice of region. Moterra recommends London, Frankfurt or Ireland for UK and EU customers, and Google Cloud and on premises deployment are available on request.
On top of Claude, Moterra's AI Bridge layer adds an admin console, MCP plugins and Dify based agents, deployed single tenant into the same account. The plugins cover permission aware SharePoint retrieval, Text-to-SQL over customer databases, web search and scrape, and Dify workflows and agents that reach Salesforce, Jira, Zendesk, Confluence, SAP and internal systems.
Connectors read and write across CRM, comms, support, docs, code and data while inheriting existing permissions, and after go live the customer builds further agents in Dify's visual workflow builder with conditional logic. Retrieval impersonates each user's Entra ID identity, so answers come only from documents that user can see.
Every prompt, model response, plugin call and administrative action is logged to CloudTrail and a log bucket in the customer's account, with SIEM forwarding for enterprise deployments, and the admin console tracks cost per user and per model. The models are Anthropic's Claude family, served through Bedrock or Azure AI Foundry, with per user model access and token quotas. ISO 27001 and ISO 42001 are badged as aligned, and Moterra attributes its ISO certificates and SOC 2 Type II reports to AWS and Anthropic, with its own setup independently validated by cyber security specialists.
The company is UK based with a London team, positions itself as a European alternative to US vendor dependency, is an AWS Advanced Tier Partner with GenAI Competency, and sells through the AWS Marketplace as a managed service with a setup fee and a monthly fee.
Vendor details
Canonical URL
https://moterra.ai
Category
Agent builder
Subcategory
Secure agentic AI and enterprise search deployed inside the customer's own cloud for regulated industries
Funding status
Independent, UK-based with a London team. AWS Advanced Tier Partner with Generative AI Competency, selling through AWS Marketplace under a professional-services delivery method with private-offer pricing. Positions itself as a European alternative to US vendor dependency. No funding is disclosed.
Company status
independent
Use cases & customers
Primary use cases
Deployment options
Integrations
Connectors read and write across CRM, comms, support, docs, code and data while inheriting existing permissions. The most popular named are Salesforce, Slack, Microsoft Teams, SharePoint, Jira and Google Workspace, beside a 100+ figure, and the full list is not published. The AI Bridge layer adds permission aware SharePoint retrieval, Text-to-SQL against customer databases, web search and scrape, and Dify based tools reaching Salesforce, Jira, Zendesk, Confluence, SAP and custom internal systems through MCP and standard APIs. Inference runs on Claude models through Amazon Bedrock or Azure AI Foundry in the customer's own account. The admin console manages API tokens, but no API reference is published.
In practice
Compliance won't let you ship your documents to another vendor's servers. Moterra runs entirely inside your own cloud perimeter, so you hold the encryption keys and your data never leaves your control.
You need an agent that answers from your contracts, not the open internet. Moterra grounds answers in your own SharePoint documents, logs every prompt and response in your account, and answers only from documents the user can already see.
Your team isn't going to write code to build an agent. After go live your power users build agents in Dify's visual workflow builder, combining knowledge bases, MCP tools and workflows, and share them across teams.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
7.0 / 14 capabilities · 50%
| Integrations & Tool Calling | Full |
|---|---|
|
Every connector reads and writes, by Moterra's account. Agents pull data and push updates across CRM, comms, support, docs, code and data while inheriting the permissions already in place. The most popular connectors are Salesforce, Slack, Microsoft Teams, SharePoint, Jira and Google Workspace, named beside a figure of 100+. Bridge adds Text-to-SQL against customer databases and tools built on Dify that reach Salesforce, Jira, Zendesk, Confluence, SAP and custom internal systems through MCP and standard APIs. The full connector list is not published. Sourcemoterra.ai home and moterra-ai-bridge pagesread 2026-09-29 |
|
| Workflow Orchestration | Full |
|
The Bridge layer ships Dify Workflows and Agents as a standard plugin hosted inside the customer's VPC. After go live, the customer builds more agents in Dify's visual workflow builder, and complex workflows use APIs and conditional logic. Agents can combine knowledge bases, MCP tools, Dify workflows and built in capabilities, and Claude runs multi step automations built on those workflows. The engine is the open source Dify platform, which Moterra deploys and operates as part of Bridge, so the customer does not wire it in. Sourcemoterra.ai moterra-ai-bridge pageread 2026-09-29 |
|
| Knowledge Grounding & RAG | Full |
|
Permission aware SharePoint RAG supports multiple knowledge bases, each scoped to specific SharePoint sites, folders or files. Retrieval is hybrid, using vector based chunks for large document sets and whole files where they fit the context window. The vector stores stay in the customer's AWS environment. Queries impersonate the user's Entra ID identity, so answers are grounded only in documents that user can access. Text-to-SQL adds an automatically built semantic layer over connected databases with schema modeling, view management and query templates. Sourcemoterra.ai moterra-ai-bridge pageread 2026-09-29 |
|
| Human Oversight & Guardrails | Partial |
|
Admins control which models each user can access, set token quotas per person and enforce device policies through MDM with Intune or Jamf. These settings limit what users and their agents can do. No approval step, checkpoint, review queue or escalation is named while an agent runs. Sourcemoterra.ai moterra-ai-bridge and private-claude-cowork pagesread 2026-09-29 |
|
| Security, Identity & Governance | Partial |
|
Access controls sit in the customer's own identity system. Sign in runs through the customer's own identity provider with Microsoft Entra ID or Google Workspace SSO, and provisioning runs through MDM with IAM or Entra ID. ACL groups and API tokens are managed in the admin console, access is controlled per database, and Entra ID impersonation means retrieval honors each user's SharePoint permissions. Customer managed KMS keys and private endpoints protect the data. Moterra presents itself as ISO 27001 and ISO 42001 aligned. The ISO certificates and SOC 2 Type II reports it cites are held by AWS and Anthropic. Cyber security specialists independently validated Moterra's own setup, but no report is named, and Moterra publishes no attestation of its own. Sourcemoterra.ai home, private-claude-cowork and moterra-ai-bridge pagesread 2026-09-29 |
|
| Observability & Auditability | Full |
|
By default every user prompt, model response, plugin call and administrative action is captured in AWS CloudTrail and a dedicated log bucket in the customer's AWS account. The customer controls retention and access. Enterprise deployments can forward logs to a SIEM such as Splunk, Sentinel or Datadog, or to a custom destination. The record covers the agent's own execution call by call, not activity in the customer's other systems. The admin console adds real time cost tracking per user and per model. Moterra does not say how much of the per call record Bridge writes itself and how much comes from AWS logging. Sourcemoterra.ai moterra-ai-bridge and home pagesread 2026-09-29 |
|
| Memory & State Persistence | Not documented |
|
Moterra describes no memory that agents write, no conversation persistence and no learned context. Skills package prompts, tools, knowledge bases and workflows and are shipped to users as configuration. The vector stores Bridge keeps in the customer's account index customer documents for retrieval. Moterra does not say whether conversations persist between sessions. Sourcemoterra.ai moterra-ai-bridge and private-claude-cowork pagesread 2026-09-29 |
|
| Deployment & Data Residency | Full |
|
The private deployment runs entirely inside the customer's own AWS account. The customer owns the account and network, the customer managed KMS keys and the choice of region. Any AWS region where Claude on Bedrock is available can be selected, and Moterra recommends London eu-west-2, Frankfurt eu-central-1 or Ireland eu-west-1 for UK and EU customers. A Microsoft Azure AI Foundry tenant is the second customer environment, and Google Cloud and on premises deployment are available on request. The Bridge layer deploys single tenant into the same AWS account and VPC. Sourcemoterra.ai private-claude-cowork, home and moterra-ai-bridge pagesread 2026-09-29 |
|
| Prebuilt Agents, Templates & Packs | Partial |
|
The customer's power users build agents once and share them across teams. During onboarding Moterra builds an initial set of agents for standard use cases such as document analysis, meeting summaries and structured data extraction. Agents can draw on 12 built in capabilities, including charts, artifacts, translation, deep research and image generation, though not all 12 are named. The onboarding agents are built for each customer as a service, and there is no published catalog of agents. The named, priced MCP plugins connect systems and are not agents themselves. Sourcemoterra.ai moterra-ai-bridge and home pagesread 2026-09-29 |
|
| Triggers & Channel Coverage | Not documented |
|
Users get Claude Cowork's multi step task automation, and Claude can run multi step automations built on Dify workflows hosted in the customer's VPC. Moterra names no scheduled, cron, webhook or external event trigger, and no channel beyond the Cowork and Code applications. It describes no way for an agent to start without a user. Sourcemoterra.ai moterra-ai-bridge, private-claude-cowork and home pagesread 2026-09-29 |
|
| Model Flexibility & Routing | Not documented |
|
The private deployment offers every Claude model, naming Haiku, Sonnet, Opus and Fable, served through AWS Bedrock or Azure AI Foundry. The Bridge control table lets the customer set LLM and Claude model access per user. Every model named comes from Anthropic, and no other maker's model is named. Bedrock and Azure are two ways to serve the same models. Sourcemoterra.ai private-claude-cowork, home and moterra-ai-bridge pagesread 2026-09-29 |
|
| APIs, SDKs & MCP Extensibility | Partial |
|
API tokens are managed in the admin console, which points to an API for the Bridge platform. Moterra publishes no API reference, endpoint or authentication guide. Bridge's four standard MCP plugins expose the customer's own systems and third party tools to Claude. They are SharePoint RAG, Text-to-SQL, Web Search and Scrape, and Dify Workflows and Agents. Sourcemoterra.ai moterra-ai-bridge and home pagesread 2026-09-29 |
|
| Testing, Debugging & Optimization | Not documented |
|
When Anthropic releases a model, Moterra's team tests it against the customer's setup and MCP plugins before making it available. Customers do not run those tests themselves, and Moterra names no evaluation, scoring, benchmark, comparison or regression tools. Automated use case discovery sorts anonymized conversations into business use cases and reports time saved per case. It measures adoption and does not score or compare agent output. Sourcemoterra.ai moterra-ai-bridge and private-claude-cowork pagesread 2026-09-29 |
|
| Browser & Computer Use | Not documented |
|
The Web Search and Scrape plugin searches, retrieves and scrapes web content for research tasks, and it does not operate software. The Claude Cowork capabilities in Moterra's deployment are files, artifacts, code execution, web search, skills and multi step task automation. None of them is browser control, navigation, form filling or screen interaction, and Moterra names no such capability. Sourcemoterra.ai moterra-ai-bridge and private-claude-cowork pagesread 2026-09-29 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
Custom pricing (contact sales)
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agenta — Agenta is an open source workspace where teams build AI agents by…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
Alternatives to Moterra
The closest documented capability profiles to Moterra among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Aigensei8.0 / 14Adds documented Memory & State Persistence and Triggers & Channel Coverage
- ReN36.0 / 14Adds documented Model Flexibility & Routing
- Tektonic AI10.0 / 14Adds documented Triggers & Channel Coverage and Model Flexibility & Routing, among others
- Turbotic9.0 / 14Adds documented Triggers & Channel Coverage and Model Flexibility & Routing, among others
- AI Library6.0 / 14Adds documented Memory & State Persistence and Triggers & Channel Coverage
- Cohere North11.0 / 14Adds documented Triggers & Channel Coverage and Model Flexibility & Routing, among othersMoterra vs Cohere North →
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded