One platform to plan, build, and ship
Every capability in JuhJuh, from Ideas to Observability, in a single overview built for agents and humans.
Everything it takes to ship, in one place.
Planning, code, automation, and operations have lived in four different tools for a decade. JuhJuh brings them under one roof and adds the thing none of them had: a runtime where agents do the work and gates that keep it safe.
- One overview for the whole Meridian workspace: tasks, agents, deployments, and live services on a single screen.
- The same Task carries from a KYC review or a dispute through code, brew, and production.
- Five safety gates sit between an agent and your live ledger, so nothing ships unreviewed.
The work you plan and the work you build.
JuhJuh splits cleanly into Work and Build. A Task created in Work flows straight into Build and back, carrying its full history with it.
- Work: plan the roadmap, run the agents, and keep the team's knowledge.
- Build: write the code, ship the infrastructure, and watch production.
- The output matches the work: a pull request for code, a finished document for a PRD or research, a sent message for outreach.
Plan, run, remember
Roadmap, the AI Pipeline, your agent roster, and the Knowledge Base that the whole team draws from.
Write, ship, watch
The Git host, the Cauldron that validates every change, deployments, and full production observability.
Every page on this site draws from one map.
Here is the whole set. Each capability has its own page, and they all share the same Task, the same vocabulary, and the same look.
Plan & Work
A modern tracker for agent and human teams: an AI Pipeline, a Board with WIP limits, Backlog, Goals and Cycles, a Gantt Roadmap, an Insights dashboard, Task templates, and a dependency graph. A person approves the spec where your rules ask for it, by type, size, priority and labels, per project or per ticket.
OpenAgents & Skills
A runtime for autonomous AI workers with event, schedule, and button triggers, pipelines, batch runs, and a marketplace. Skills are the reusable capabilities they draw on, with an editor, publishing, and a template library.
OpenCharms
Visual workflow automation on a drag-and-wire canvas with 28 kinds of step, subflows, a live run log, and human-in-the-loop forms you can publish to the public.
OpenCode & Connections
A Git host built for agents: code browser, commits, branches, tags, pull requests that are themselves Tasks, AI review, and an isolated workspace per Task, with a person deciding every merge. Plus 200+ integration connections and a built-in private container registry.
OpenCauldron / Brew
The CI/CD for agents. Each change is checked against the ticket's requirements and acceptance criteria before testing. After every step, JuhJuh checks the code inside a running copy of your services that mirrors production, then runs your tests and fixes what fails, before your pipeline and code review see it. Deployments carry it to production with vaults, a provisioning wizard, and a service topology diagram.
OpenObservability
An AIOps overview that surfaces root-caused, evidence-backed issues with fix actions, plus Uptime, Logs, Error Tracking, Metrics, Traces, Session Replay, database monitoring, and real user monitoring. Incidents, alerting, on-call, and a public status page round it out.
OpenKnowledge Base
A team wiki with a nested tree, wikilinks, revisions, comments, permissions, and an answer engine that replies with sources.
Open
See where the work stands without leaving the platform.
The Insights dashboard reads from the same Tasks your team runs, so goal progress and throughput stay honest. No exports, no second tool to reconcile.
- Goal progress and cycle throughput, pulled live from the Board.
- A Gantt Roadmap and dependency graph for the quarter ahead.
- How much of the work shipped through agents versus people, side by side.
It knows your team before your first Task runs.
JuhJuh knows who is on your team and what they are allowed to do from the start.
People & access
Roles, invitations, and teams, so the right people get the right reach.
Keys & voice
API keys plus brand voice and guidelines that shape what the agents produce.
Audit trail
Audit logs that record who did what, across every surface.
Billing & credits
Billing with usage and credits, so spend stays in view.
On our service, or inside your own boundary.
Most teams start on JuhJuh's hosted service. There is nothing to install, your teams are working within days, and we run, update and support it. A team that needs more control, or must keep sensitive data inside, self-hosts JuhJuh instead.
Hosted by JuhJuh
Sign in and connect your tools. We keep the service running, updated and supported, so your people spend their time on their own work.
Your organization gets a workspace of its own, and each organization sees only its own data. When an AI agent works, the prompts and files it needs go only to the AI model companies you allow, only to do the work, inside the regions you declare.
Self-hosted, inside your boundary
In your own cloud account (AWS, Google Cloud, Microsoft Azure or DigitalOcean) or on your own premises, connected or air-gapped, with open-weight models from the Mistral, DeepSeek, GLM and Kimi families running inside. Our engineers install it and tune it to your compliance obligations.
Your sensitive information, trade secrets and know-how never leave your boundary unless you connect an outside service or chat app, approve a website for your AI agents or approve sending them out. While your AI agents run only on your own models, no AI company receives them or trains a model on them.
Start hosted and move when you're ready: our engineers move your workspace across. Some companies run both, the hosted service for most teams and a self-hosted installation for the systems that must stay inside, and each installation is kept separate.
Everything it takes to ship, in one place.
Plan the work, build it, ship it, and watch it run, without leaving the product.
