Hush Assistant. Your private AI assistant with 50+ built-in tools.
Ask it in plain English and it gets on with the work, searching, reading, drafting, organising files, and remembering what matters. The same capability a developer would call an agent runtime, with the technical depth still here when you want it. Every instruction runs on hardware we own, never a US cloud, and the memory it keeps for you is yours, to wipe whenever you want.
Request Hermes access →Everything an agent needs. Nothing it does not.
Hush Assistant ships with 50+ tools that let it interact with terminals, files, the web, browsers, code, images, and its own memory. No plugins to install.
Terminal execution
Run shell commands in a sandboxed environment. Install packages, run scripts, pipe outputs.
File management
Read, write, search, and organise files. Parse PDFs, CSVs, DOCX, and structured data.
Browser automation
Navigate pages, extract data, fill forms, take screenshots. Headless Chromium on our own hardware.
Code execution
Run Python, JavaScript, bash, and more. Analyse data, generate visualisations, test logic.
Vision
Analyse images, screenshots, charts, and documents. Extract text, describe content, identify patterns.
Persistent memory
Store and recall facts across sessions via PostgreSQL and vector semantic search.
Agent delegation
Spawn specialised sub-agents for complex tasks. Coordinate multi-step workflows autonomously.
Three ways to talk to Hush Assistant. One sovereign runtime.
Access the agent through a REST API, server-sent events for streaming, or the MCP protocol for tool-native integration. All routes execute on the same hardware we own.
Access Methods
- REST API with JSON request/response
- Streaming via Server-Sent Events (SSE)
- Async task queue with polling
- MCP protocol for tool ecosystems
Infrastructure
- GPU compute we own
- PostgreSQL persistent memory
- Vector embeddings
- Sandboxed execution containers
Synchronous, streaming, or fire-and-forget.
Choose the execution model that fits your workflow. All three modes are available on every endpoint.
Synchronous
Send a request, wait for the complete response. Ideal for simple queries and integrations.
POST /v1/agent/runStreaming (SSE)
Receive tool calls and reasoning in real time as the agent works through a task.
POST /v1/agent/streamAsync Tasks
Submit long-running tasks and poll for results. Background processing for complex workflows.
POST /v1/agent/taskOne request. The agent handles the rest.
Send a natural language instruction. Hush Assistant selects the right tools, executes them, and returns structured results.
curl -X POST https://api.hush-ai.uk/v1/agent/run \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"instruction": "Search for the latest UK AI regulation updates, summarise the key points, and save to a report file.",
"model": "auto",
"tools": "all"
}'
One agent delegates. Specialists execute.
Hush Assistant can spawn sub-agents with constrained tool sets and specific roles. A research agent searches and summarises. A code agent writes and tests. A review agent validates. The orchestrator coordinates them all.
Research Agent
Searches the web, reads documents, extracts facts, and produces structured summaries.
Code Agent
Writes, tests, and debugs code. Runs in a sandboxed environment with full terminal access.
Review Agent
Validates outputs against criteria. Checks facts, verifies formatting, flags inconsistencies.
Data Agent
Extracts, transforms, and loads data. Parses files, queries APIs, builds datasets.
Session continuity that actually works.
Hush Assistant remembers context across conversations. Facts, preferences, and project state are stored in PostgreSQL with semantic recall powered by vector embeddings. Your agent picks up exactly where it left off.
Structured Storage
- PostgreSQL for relational facts
- Session history and turn logs
- User preferences and project state
- Exportable and auditable
Semantic Search
- Vector embeddings
- Recall by meaning, not keywords
- Cross-session context retrieval
- Automatic relevance ranking
From compliance reports to code reviews.
Hush Assistant handles multi-step workflows that would take a human hours. Here are some examples.
Compliance report generation
Gather regulatory data, cross-reference requirements, draft structured compliance reports with citations.
Literature review
Search academic sources, extract key findings, synthesise into a structured review with references.
Data extraction pipelines
Scrape websites, parse documents, transform data, and output clean structured datasets.
Customer onboarding
Process applications, verify documents, generate welcome packs, update CRM records automatically.
Document processing
Ingest PDFs, extract key fields, classify documents, route to appropriate workflows.
Automated accounting
Invoices and receipts flow straight into LedgerCore, parsed, categorised, and posted to the ledger with VAT handled. Books that keep themselves.
Code review automation
Analyse pull requests, identify bugs, check style compliance, generate review comments.
Infrastructure monitoring
Check service health, parse logs, identify anomalies, generate alerts and incident summaries.
From API key to autonomous agent in four steps.
Get API key
Sign up and receive your API credentials. Takes under two minutes.
Send first task
POST a natural language instruction to the agent endpoint. Hush Assistant selects tools automatically.
Review execution
Watch the agent work via streaming. Every tool call is logged and auditable.
Deploy workflows
Chain tasks, configure memory, set up multi-agent pipelines. Scale as needed.
Your data stays on hardware we own, and stays yours.
Every tool call, file operation and memory write runs on hardware we own, never a US cloud. The memory your assistant keeps is yours, and you can wipe it any time. No CLOUD Act exposure.
Our Hardware, Our Rules
All compute on servers we own. No rented cloud, no third party, and your memory is yours to wipe any time.
Our own hardware, not Big Tech
Hardware we own. US law does not apply.
Sandboxed Execution
Each agent session runs in an isolated container. No cross-tenant leakage.
Full Audit Trail
Every tool call logged with timestamp. Exportable compliance records.
No Conversations Kept
Session data purged on completion unless you enable persistent memory.
ICO Registered
Data controller ZC126901. Built to GDPR & DPA 2018. DPA draft available; signed before any live personal data flows.
Deploy an autonomous agent on our own hardware.
50+ tools. Multi-agent orchestration. Persistent memory. All on hardware we own you can audit.
Request Hermes access →Or email [email protected] directly.