The hub for your agentic ecosystem

Your agentic ecosystem, self-hosted.

Change the engines. Keep your ecosystem.

Ideal for solo work, project teams and small organisations.

Open source · CeCILL 2.1

Talk to your agents as colleagues: delegate research, revise a report together or launch a predefined business process. Find your documents, files and knowledge to carry the work forward. Choose local models, cloud models or both; your agents, tools and permissions stay together in Galaris.

Simple installation. An OpenRouter API key is enough to get started: models and a profile are preconfigured.

Signed-in home — Monthly usage, quick access and activity in the demo instance.
Signed-in home — Monthly usage, quick access and activity in the demo instance.C01

Three stories in Galaris

A question. A choice. A result to return to.

Follow fictional characters through scenarios run with Galaris agents and documents. Examples are in English.

Check energies at half height — 2 kg released from 20 m: height 10.00 m, speed 14.01 m/s and two energies of 196.2 J. Model without air resistance.
Check energies at half height — 2 kg released from 20 m: height 10.00 m, speed 14.01 m/s and two energies of 196.2 J. Model without air resistance.C59

Lina learns with Albert

Her intuition becomes an experiment and a personal revision sheet.

Follow their story
Compare 40 and 30 guests — Two detailed budgets: €1,500 and €1,200, each retaining €180 contingency.
Compare 40 and 30 guests — Two detailed budgets: €1,500 and €1,200, each retaining €180 contingency.C65

Malik prepares his open house

His team compares budgets, prepares the programme and collects requests.

Follow their story
The same room, a clearer photo — Synthetic source and enhancement of the same image: exposure, white balance and framing, with no renovation shown.
The same room, a clearer photo — Synthetic source and enhancement of the same image: exposure, white balance and framing, with no renovation shown.C68

Claire helps Emma with Iris

Photos, financing and renovation evolve in the same pack.

Follow their story

From conversation to action

Talk to your agents like colleagues.

Galaris has two agentic loops. The conversation loop uses history and memory, with a limited set of tools to stay focused on the exchange. The task loop executes work through the harness; business processes handle predefined workflows. You keep talking to your agent while it works, without mixing the discussion with execution details.

A task to carry out

Research, analyse, write: the harness drives the agent’s work as it adapts its steps and uses authorised tools to reach the goal.

Explore agentic tasks

A business process to start

The agent starts a configured business process assigned to it. Steps, rules and approvals are defined in advance; Galaris tracks the execution.

Explore business processes with n8n

Keep the conversation flowing while work continues. “How’s it going?” The agent checks the actual progress and answers naturally without interrupting its task. You can also start a task, request a stop or adjust its instructions along the way, depending on its state. You customise instructions, models, harnesses and the tools available to your agents. Understand the two loops

Need a model inside the workflow? The process can call the Galaris inference API, with call tracking and available cost data. Explore the API integration

The whole platform

Choose the work to delegate.

Six starting points to find the capabilities your team needs, their screens and their requirements.

Communicate

Reach agents through your conversations.

Delegate and follow

From individual tasks to lasting goals.

Produce

Deliverables to review, edit and share.

Organise

Build on work already completed.

Connect

Choose models, engines and services.

Administer and evaluate

Inspect access, results and costs.

From document to working tool

Build and use your tools, inside chat.

Turn an answer into working material: a report to revise with your agent, a form, a simulator or a 3D scene. Documents and their files remain accessible from the library and the conversation.

  • Enter information in a form connected to a Dataset.
  • Adjust a mini-application’s inputs and see the result.
  • Manipulate a 3D view embedded in the document.
Explore documents and Datasets
An interactive scene inside a document — A fictional 3D workshop study with rotation and zoom, prepared from the site’s demo code.
An interactive scene inside a document — A fictional 3D workshop study with rotation and zoom, prepared from the site’s demo code.C57
An interactive document in Chat — The property pack opened with Iris beside the conversation.
An interactive document in Chat — The property pack opened with Iris beside the conversation.C54
A request actually recorded — The form confirms saving; Malik confirms places himself.
A request actually recorded — The form confirms saving; Malik confirms places himself.C56

What your agents can do

One place to talk, act and keep work moving.

From the first message to background work, explore the features that make a difference.

01Missions & plans

Keep talking. Your missions keep moving.

Give an agent a lasting piece of work: the original request and attachments stay separate from supplementary context. Inspect its plan, steps and result while the conversation continues.

Use it toPrepare a document in several stages and return to check its progress.

Explore this feature
A task’s request and result — Albert’s lesson creation, with the requested objective and final feedback.
A task’s request and result — Albert’s lesson creation, with the requested objective and final feedback.C06

02Agent collaboration

Bring specialists together on the same job.

An agent can delegate a contribution to another, wait for its response and resume work with the result. Contributions remain linked to the mission.

Use it toHave one agent research sources and another prepare the summary.

Explore this feature
Three delegated checks, three results — Ariane combines Nora’s, Louis’s and Sacha’s checks: capacity, budget and programme. All three subtasks are completed.
Three delegated checks, three results — Ariane combines Nora’s, Louis’s and Sacha’s checks: capacity, budget and programme. All three subtasks are completed.C13

03Graph memory

See how your information connects.

Search documents and their syntheses, find indexed files and explore their links. Memories stay private to each agent; documents are shared with access rights. Previews let you return to the original file.

Use it toReturn to a project and find the documents and discussions behind it.

Explore this feature
A memory entry — The revision document’s summary, metadata and relationship and history views.
A memory entry — The revision document’s summary, metadata and relationship and history views.C16

04Dream mode

Build on work already done.

Dream organises memory, maintains the file catalogue and prepares thumbnails. Follow operations or launch an action from an authorised detail view. Attachment analysis and skill learning are enabled separately in settings.

Use it toOrganise accumulated context and inspect what has been consolidated.

Dream skill learning is disabled by default.

Explore this feature
Dream tracks background work — Actual progress of classification, memory and other maintenance actions.
Dream tracks background work — Actual progress of classification, memory and other maintenance actions.C20

05Voice conversations

Talk to your agents.

Speak with your agents using a compatible model. Session monitoring lets you inspect voice activity and the tools used.

Use it toDiscuss a request out loud.

Explore this feature
Voice-call history — Call filters and tracking; no voice calls recorded in this instance.
Voice-call history — Call filters and tracking; no voice calls recorded in this instance.C35

06Goals & cycles

Stay on track over time.

Define a goal to pursue over time. Cycles retain their work, evaluations and evidence, with a configurable schedule.

Use it toFollow a research topic and its new questions in each cycle.

Explore this feature
A cycle and its stop decision — Budget, capacity and duration checks; a STOP verdict from native tracking.
A cycle and its stop decision — Budget, capacity and duration checks; a STOP verdict from native tracking.C24

07Business processes

Start workflows from the conversation.

Your agent can start an authorised process configured on your instance. The request stays linked to the business workflow and its progress.

Use it toStart the processing workflow for a document.

Explore this feature
The process-engine connection — The n8n engine and its settings; its connection is not configured in this instance.
The process-engine connection — The n8n engine and its settings; its connection is not configured in this instance.C33

08Agents, models & skills

Build the team that suits you.

Start with the Galaris assistant and the preconfigured profile. With authorised AgentAdmin and ToolAdmin access, an agent can help create specialists, configure their connections and prepare tools. The system still checks rights and approvals.

Use it toEquip a research agent and a writing agent differently.

Explore this feature
Ariane’s identity — Manager, identity and role of the event-coordination agent.
Ariane’s identity — Manager, identity and role of the event-coordination agent.C10

What you build with Galaris

Your engines change. Your work stays.

Agent identities, memory, connections and permissions stay in Galaris. Evolve your ecosystem’s engines while keeping what you have built.

  1. Change the harness or model. Keep the rest.

    Choose fully local inference, cloud providers or both. Change compatible models or harnesses: your agents, their memory, connections and permissions stay managed in Galaris.

    Your research agent keeps its role, knowledge and authorised tools when you choose another harness or model provider.

  2. Build on useful knowledge from your missions.

    Find useful passages, authorised files and their sources. Each agent keeps private memories; shared documents give the team common working material, with a separate memory synthesis, revisions and access rights.

    “Find the project brief and the files behind this decision.”

  3. Give your team a goal that outlasts the chat.

    Set a direction and a schedule. Work cycles keep their results, evidence and evaluations to determine what comes next. A designated contact can be asked for a decision when needed.

    Follow a research topic and review progress from one cycle to the next.

  4. Delegate while staying in control.

    Follow your agents’ steps, results and actions. When delivery can be retried, the existing output is reused. Recovery takes account of known effects and uncertain situations.

    Retry a supported delivery without asking the agent to recreate the document.

  5. Build on your agents’ experience.

    Dream maintains memory and can derive skills from past missions.

    Find useful knowledge and review skills proposed from completed work.

    Skill learning is disabled by default. You choose whether to enable it and evaluate its results.

Explore the features

A shared system across the layers

Build your agentic ecosystem.

Galaris is the hub that preserves your working environment as its engines evolve. It connects models, harnesses and tools, and also provides its own chat, internal harness and applications.

Galaris: connections, permissions and tracking

Configure and authorise your tools in Galaris. Connect an MCP server, define which functions each agent can access, then choose its execution engine. Galaris presents the authorised catalogue to that engine. Tool configuration stays in the hub.

  • Applications

    Conversations, goals, documents and processes: the spaces where work takes shape.

  • Shared services

    Memory, skills and MCP configured in Galaris: functions exposed according to each agent’s permissions.

  • Agent execution

    Agents, roles and missions stay in Galaris; choose an execution harness suited to the work.

  • Model access

    API gateway, inference tracking, events, usage and available costs.

On the infrastructure and models you choose

Models and providers
Fully local inference on your servers, cloud providers or a mix of both, using compatible models and protocols.
Infrastructure
Servers, compute, storage and networking for your deployment.

Reach your agents where you already work.

For example, your business application can consume a model through Galaris and retrieve the associated inference without using Galaris chat.

Stay in control

Autonomy you can inspect.

Choose your agents’ access, follow useful steps and review the result before using it.

Understand the controls
Model activity — Actual scenario calls, models, durations, usage and costs.
Model activity — Actual scenario calls, models, durations, usage and costs.C28
  • Tools assigned to each role
  • Inspectable states and results
  • Sources and limitations to check

Your first test case

A concrete starting point. A result to compare.

Atelier Horizon is preparing a mobile repair service. Three synthetic notes, a contradiction and a decision give you a focused way to evaluate Galaris.

  1. 01

    Ask

    Request a launch brief with sources and open questions.

  2. 02

    Check

    Does the agent identify contradictory information?

  3. 03

    Decide

    Provide the correction and compare the result with the reference.

Download the test kitMarkdown · no registration

The kit contains a brief, sources and a human-written reference. It is not a result already produced by Galaris.

Follow the case step by step

Start at your own scale

Install. Add your key. Start talking.

A fresh installation comes with selected OpenRouter models and a configured profile. Enter your API key and start talking to the Galaris assistant. Customise your agents, models and connections at your own pace.

  1. 01

    Install Galaris

    Follow the quick start on GitHub.

  2. 02

    Enter your OpenRouter key

    The profile and models are preconfigured.

  3. 03

    Talk to your assistant

    Ask the Galaris assistant for guidance, a specialised agent or help preparing its connections, within the administrative rights you grant it.

Use your own OpenRouter account with access to the selected models. You can choose other providers or local models whenever you need them.

Your team, your knowledge, your goals. Explore Galaris’s strengths