Skip to content

Autonomous AI Teams
That Build Software

Deploy a full team of AI agents — product owner, architect, engineers, QA, SRE — that collaborate to spec, design, implement, review, test, and deploy your software. Fully containerized. Self-hosted and free.


How It Works

1. Create a project — describe what you want built via the dashboard’s guided onboarding, or import an existing repo.

2. Plan it — the planning pipeline decomposes your project into tasks on a kanban board with priorities and dependencies.

3. Assign agents to columns — Yukihiro watches “Ready” for implementation work, Chieko watches “Review” for testing, Stas watches for deployment. Each agent knows their lane.

4. Agents work autonomously — on pulse cycles, agents wake up, check the board, claim a task, spin up an isolated container, do the work, open a PR, and advance the task.

5. Watch it happen — streaming output in the dashboard, Slack threads, or the kanban board. Step in when you want, or let them run.

Pipelines handle structured workflows — the planning pipeline generates the task board, the engineering pipeline runs a full SDLC for a single task, and you can build custom pipelines for any repeatable process.


The Default Team

AgentRolePipeline StageWhat They Do
EricProduct OwnerSPECRequirements, user stories, acceptance criteria, scope management
FinnSolutions ArchitectDESIGN / REVIEWSystem architecture, tech decisions, code review, API design
ShigeoUX SpecialistUXUser flows, design systems, component specs, accessibility
YukihiroSenior SWEIMPLEMENT / FIXImplementation, bug fixes, writing production code
ChiekoTest EngineerTESTQA strategy, regression detection, test automation
StasSREDEPLOYInfrastructure, deployment, monitoring, incident response
YangDevEx SpecialistDX (on-demand)CI/CD pipelines, tooling, developer workflow optimization
HoltMarketing & SalesOn-demandSales strategy, outreach, deal management, positioning
LukeSEO SpecialistOn-demandContent strategy, keyword research, technical SEO
JimFinance LeadOn-demandBudget, pricing, runway management, financial modeling

The engineering pipeline is fully operational today. Marketing, sales, and finance agents work in chat and pulse modes, with structured pipeline support coming soon.


Why Not OpenClaw / Other Tools?

DjinnBotOpenClawTypical Agent Frameworks
Setup timedocker compose up — 5 minutesKubernetes + cloud config — hoursFramework wiring + custom code — hours to days
InterfaceFull dashboard, Slack bots, chat, CLI, APIBasic web UITerminal output or minimal web UI
SecurityEvery agent in isolated Docker container. No host access.Direct host access, shell executionDirect host access, shell execution
Agent memoryPersistent semantic memory with knowledge graph across runsStateless or basic file storageStateless or basic file storage
Multi-agent collaborationAgents review, critique, and build on each other's workLoose coordinationSingle-agent or sequential handoff
CustomizationYAML pipelines, markdown personas — no codeCode-level changesCode-level changes
Agent personasRich characters with opinions, beliefs, and anti-patternsGeneric system promptsGeneric system prompts
Tool systemMCP tools converted to native tools at runtimeManual tool configurationCustom tool integrations

DjinnBot is built for people who want autonomous AI teams working on real projects — not another framework to wire together.