Mission LLMDownload

Intelligence, in house.

A self-hosted assistant for your documents and agents. No cloud or internet required.

Download FreeSecurity

Private AI that runs on your network

The Mission LLM app answering a question about change control, with the workspace sidebar, the model picker and the two source documents it cited.
  • Ollama
  • LM Studio
  • LocalAI
  • KoboldCPP
  • Docker
  • Kubernetes
  • Helm
  • OpenShift
Model providers
38
Vector databases
10
Embedding engines
14
Deployment methods
5

Ready on day one.

Equipped for the mission.

An answer drawn from workspace documents, with the Sources panel showing each document and its match score.

Files you add are parsed and indexed on your server. Answers drawn from them list their sources.

See how sources work

Type @agent to hand off a task. Agents use the skills and MCP servers your admins turn on.

How admins control tools

Pick from 38 model providers, local or cloud, and set a different one for each workspace.

Where your data goes

Each workspace keeps its own documents, prompt and model. Threads keep lines of work apart.

Set up your first workspace

In multi-user mode, everyone signs in with their own account and an admin, manager or default role.

See access controls

Grounded answers

Answers you can trace.

When a workspace has documents, Mission LLM searches them before the model answers. Open Sources on an answer to see the documents it used, the passages it retrieved and how closely each one matched.

  • Sources listed under grounded answers
  • Retrieved passages with match scores
  • A similarity threshold per workspace

Learn more

A Mission LLM answer in light mode with the Sources panel open, listing each cited document with its match score.

Security and control

You set the boundary.

The Event Logs admin page in Mission LLM.

Pair it with a local model runtime and stage the built-in models. Chat, embeddings and search then run offline.

Learn more about offline use

In Docker, bind the published port to 127.0.0.1 (-p 127.0.0.1:3001:3001) and only that machine can connect.

Learn more about hardening

Admin, manager and default roles, with workspace membership. Admins issue and revoke keys for the developer API.

Learn more about access

Sign-ins, failed sign-ins, and changes to users, API keys, invites, workspaces and documents, in one log for admins.

Learn more about oversight

Set DISABLE_TELEMETRY="true" before the first start and no usage events are sent. Admins can also turn it off in Settings.

Learn more about telemetry

Four steps from install to answers.

  1. 1

    Install with Docker

    One container serves the app and API on port 3001, with your data in one storage folder.

  2. 2

    Connect a local model

    Point it at Ollama, LM Studio or another runtime on your network. Cloud providers work too.

  3. 3

    Add your documents

    Drop files into a workspace. Mission LLM parses, embeds and indexes them on your server.

  4. 4

    Invite your team

    Turn on multi-user mode, invite people, and give each person a role and workspaces.

Self-hosted

Deploy it where your data already lives.

Mission LLM ships as one container that serves the app and API on port 3001. Run it with Docker, Compose, Kubernetes, Helm or OpenShift, on a workstation, a server in your rack or a cloud account you control.

See every install option

Docker on Linux or macOS
export STORAGE_LOCATION=$HOME/missionllm && \
mkdir -p $STORAGE_LOCATION && \
touch "$STORAGE_LOCATION/.env" && \
docker run -d --rm -p 3001:3001 \
--cap-add SYS_ADMIN \
-v ${STORAGE_LOCATION}:/app/server/storage \
-v ${STORAGE_LOCATION}/.env:/app/server/.env \
-e STORAGE_DIR="/app/server/storage" \
REGISTRY/mission-llm:latest
REGISTRY is a placeholder. Public images are not published yet. Today you build the image from source (see Download).

Resources

  • See where your data goes and which controls ship today.

    A plain-language data flow, every outbound connection and how to avoid it, and seven steps to harden an install.

    Security overview

  • Install it on one workstation or a whole cluster.

    Build the image from source, then run it with Docker, Docker Compose, Kubernetes, Helm or OpenShift.

    Install guide

  • Start free, and add support when you need it.

    Community is the full application, free to self-host. Enterprise adds planned support, deployment help and governance features.

    Editions

MIT licensed foundation.

Open at the core. Yours to run.

Mission LLM is built on the open-source AnythingLLM project (MIT License) and adds what an organization needs to run it with confidence.

License
MIT
User roles
3
Cloud templates
3
DownloadSecurity overview
What Mission LLM adds, on top of the AnythingLLM core

  1. In-place upgrade from AnythingLLM

    The database, settings and vector collections carry over.

  2. Documented outbound connections

    Every connection the server can make, and how to avoid it.

  3. Templates that pull only your image

    Deployment templates run the image you build and host.

AnythingLLM core (MIT License)

  • Ingestion
  • Retrieval
  • Agents
  • Providers

Stand it up on your own hardware.

Start with one container and a local model. Add users, workspaces and documents when you are ready.

Download Mission LLM