Meshly · Products
Three ways to own your stack.
The control plane for AI coding agents, managed by Meshly or self-hosted on your own infrastructure. The customer-deployed data platform underneath. And your own on-prem AI appliance that runs local models and can operate both, even airgapped. All designed for organisations that own their stack.
Meshly Build
The control plane for AI coding agents. Run dozens of agents alongside your team in one workspace, with visibility, shared knowledge, and human approval gates around every action.
- Visibility: every agent action, every dollar, every ship in one timeline, with a roadmap across projects
- Knowledge: architecture, decisions, and memory shared so the next agent starts warm
- Control: approval gates, monthly budgets, and access levels (Viewer, Maintainer and Admin) on the workspace, an organization or a project
- Ready-made agent roles, all extensible, with label routing to the right one and a model choice per agent for coding and review
- Automated review and merge after approval, with every task in its own isolated workspace
- Works with Claude Code and Codex, plus other MCP clients such as Cursor, Windsurf and Copilot; plan from Claude Desktop or claude.ai with 120+ tools
- Enterprise SSO, optional two-step sign-in, audit export, plus Build Station desktop app for macOS, Windows, and Linux
- Managed by Meshly, or self-hosted on your own infrastructure
Meshly Data Stack
MDS is a complete self-hosted data platform: ingestion, lakehouse storage, SQL federation, orchestration, AI agents and SSO in one integrated stack, deployed on customer infrastructure under license.
- 28+ integrated data services in one platform
- Iceberg on MinIO with Nessie, Trino, Airflow, Kafka with Debezium CDC, optional Spark and Flink
- LangGraph customer agentic runtime, Qdrant or Milvus vector search, OpenSearch and OpenMetadata for search, catalog and lineage
- Bundled MDS Dashboard for real-time stack management; MDS-MCP-Server exposes 200+ tools over MCP for agent-driven operations
- Keycloak SSO, OPA dynamic RBAC, OpenBao audited secrets, Superset and Grafana for visibility
- Three license tiers (Growth, Scale, Enterprise); runs anywhere you run containers, from Podman to OpenShift to cloud; onboarded by our team
Meshly AI
Your own AI, on your own hardware. A compact on-prem appliance that runs local models in three modes (reasoning, coder, and an artist mode for images and video), so your data, prompts and models never leave the box.
- Runs entirely on-premises, with no calls to a public AI service; your data and models stay in-house
- Three modes: reasoning, a coder brain, and an artist mode that creates images and video
- In coder mode it can operate Meshly Build and Meshly Data Stack for you, even fully airgapped: your own AI running your own stack
- Two interfaces: Meshly CLI in the terminal on macOS, Windows, and Linux, and Ilves, the desktop app with chat, Image Studio and Video Studio for macOS, Windows, and Linux, with mobile apps for iOS and Android
- Model-neutral: bring your own open or local models, with no per-seat or per-token metering on the box
- Available in early access, by request
FAQ
How they fit together.
Build orchestrates the work.
Meshly Build is the workspace where humans and AI agents share a backlog. Visibility into every agent action, shared knowledge so the next pickup starts warm, and approval gates so humans stay in charge.
MDS runs the data.
MDS is the data substrate underneath. Self-hosted infrastructure deployed on customer machines, operated standalone or with Build in the loop through MDS-MCP-Server: container lifecycle, Kafka topics, SQL, secrets rotation. No SSH required.
Meshly AI runs it on your hardware.
Meshly AI is the on-prem appliance: local models in reasoning, coder and artist modes, with the artist creating images and video. In coder mode it can operate Build and MDS for you, even fully airgapped, so the whole stack runs on your own AI. Reach it from the terminal with Meshly CLI or from the desktop with Ilves.