Platform
Every feature, one foundation.
Every interaction is logged, auditable, and mapped to your own policies.
Ask Anything, Safely
- Governed and audited every conversation runs under your organisation's rules, with a full audit log of what was said and by whom.
- Safeguarded conversations are monitored for safeguarding concerns as they happen, with alerts sent directly to admins or safeguarding leads.
- Grounded in your own knowledge on local models, responses draw on your organisation's own documentation and policy, not general internet knowledge.
Know Whats Happening
- Safeguarding at a glance flagged conversations route straight to designated safeguarding leads, with the context they need to act, not just an alert.
- Full audit trail every interaction, every model used, every user, logged and searchable, ready for an internal review or an external audit.
- Usage and cost reporting see exactly what's being used, by whom, and what it costs, with spend caps you control rather than discover after the fact.
Build on Your Terms
- Model-routed eLLM's VSCode plugin routes requests to whichever model has the right coding capability for the task, without developers needing to manage that choice themselves.
- Grounded in your own codebase on local models, suggestions and answers draw on your organisation's own code and standards, not general internet training data.
- Built for how coding actually works coding mode skips document search and passes tool calls straight through the way agents expect, and safeguarding observes rather than blocks.
One Platform, Different Goals
- A teacher marking a stack of essays who needs a first pass, not a replacement for their judgement.
- A safeguarding lead who needs to know the moment a conversation raises a concern, not weeks later.
- A college support team answering the same enrolment and finance questions, hundreds of times a term.
- A council caseworker drafting responses to residents without waiting on a template.
- A council FOI officer triaging requests and flagging what shouldn't be released.
- An IT lead who needs proof, not promises, that student or citizen data never left the building.
- A developer inside a government department shipping code without their tooling calling out to the open internet.
- A department head who needs a straight answer on what AI cost this term and who used it.
Everything Included
Using the eLLM chat
Reliable, cited answers from your documents, with model choice, attachments, and side-by-side model comparison.
Skills
Save a format, tone, or instruction set once and apply it with a click; organisation skills set a house style, personal skills handle recurring tasks.
Personal Memory
Remembers lasting facts about each user to personalise answers, fully reviewable and can be switched off.
Personal Notebook
A private, searchable timeline for notes, images, and files, visible only to the user.
Exporting Answers as Documents
Turn any answer into a finished PDF, Word, or Excel file, generated securely on your own servers.
Workflows
Chain steps into repeatable, named pipelines for routine multi-step tasks, pausing for approval where needed.
Coding with eLLM (code API)
Dedicated coding assistant modes with centralised access, usage logging, and local-model options to keep code secure.
Automatic Model Routing
Chooses the best available model for each question on your behalf, balancing capability and cost.
Local Models
Run entirely on your own servers for data privacy and cost savings.
Cloud Models
Optional access to external AI services for heavier tasks, with privacy controls and budget management.
Scaling eLLM
Grow capacity independently: more local models, cloud models, or spare desktops as a private worker pool (Edge Mesh) — without rebuilding or moving data.
Query Governance
Monitors and controls questions asked to the assistant, flagging or blocking harmful content before any model runs.
The Audit Log
A complete, searchable record of activity, used to investigate events, answer compliance questions, and export records.
Tool Approvals
Administrators review and approve or reject sensitive tool actions before they run, ensuring human oversight.
Reports
Usage insights, popular questions, and content gaps, to help administrators support users and strengthen the document library.
The eLLM Admin Console
Central hub for managing models, permissions, access keys, settings, and tools, live-updating with no restart required.
Permissions, Users & Groups
Manage access through users, groups, and capabilities, ensuring the right people have the right access.
System Settings
Control web search, document relevance, upload limits, and cloud usage organisation-wide.
API Keys
Create and revoke keys for external software, scoped to exactly what each integration is allowed to access.
The eLLM External API
An OpenAI-compatible interface for document-grounded answers, plain chat, or automatic model selection from your own systems.
Understanding MCP (connected tools)
Connect external tools and services to the assistant, with configurable approval processes.