Meshia Docs
Documentation
Practical guides for launching compute, using the workspace, tracking experiments, and understanding the current platform surface.
Tutorial: Your first experiment
A guided 8-step walkthrough from sign-in to a completed training run. Takes about 8 minutes.
Getting started
Core concepts
Agent roles
Coming soonSpecialized agent roles are being wired into the workspace UI.
Experiments
Track training runs, metrics, artifacts, and comparisons from the research workspace.
Research plans
Use the research flow to turn a goal into structured hypotheses and runs.
Canvas
Coming soonSpatial research surfaces are being prepared for the main workspace.
Workflows
Coming soonRepeatable multi-step agent pipelines are under active buildout.
Integrations
External AI agents (MCP)
Connect an external AI agent to Meshia workspaces, compute, files, teams, and swarms through OAuth and MCP.
Connect Meshia
Connect your AI agent to Meshia and optionally mount workspace files on your computer.
GitHub
Connect GitHub in chat and clone repositories your account can access.
Webhooks
Coming soonWebhook delivery foundations are in place; the public settings UI is coming soon.
Notifications
Configure the product notifications that are live in Settings.
Platform
Reference
GPU catalog
Available GPU catalog, fallback rates, capacity notes, and picking guidance.
Agent tools
A practical guide to the tool families surfaced in agent logs.
Security
Data isolation, authentication, secrets, Git safety, and retention.
Limits and quotas
Current quota, runtime, API, pod, and storage limits.