Understands project context
Reads authorized issues, versions, wiki pages, discussions, files, and historical decisions.
Bunny Redmine by Appar
Redmine AI Agent
A governed AI agent that creates projects and issues, follows up on delivery, verifies results, and keeps every decision inside Redmine.
What is a Redmine AI Agent?
An AI teammate that works in Redmine—not another chat window
Bunny Redmine turns objectives, documents, conversations, and issue history into structured project work. It can act continuously while people retain approval and the final decision.
Creates executable work
Builds projects, subprojects, milestones, parent issues, subtasks, acceptance criteria, and schedules.
Closes the operating loop
Follows up on work, detects risk, verifies results, updates Redmine, and asks humans when approval is required.
Redmine AI Agent capabilities
From one instruction to organized, verifiable project work
Give Bunny a high-level objective or a single ticket. It plans the work, uses approved tools, and keeps every output attached to the right Redmine context.
Illustrative product walkthroughAsk Bunny. Watch work appear in Redmine.
Illustrative product walkthrough
Give Bunny the goal and the documents your team already has.Bunny reads the permitted project context and breaks the goal into work.Approved tools create the issues and organize the project Wiki.Review the work structure before the next stage begins.
Project and issue creation
Create projects, subprojects, versions, milestones, issues, subtasks, relations, and reusable ticket structures.
Autonomous follow-up
Inspect stale work, missing information, blockers, due dates, ownership, and dependencies on a schedule.
Documents and knowledge
Write or update Wiki, News, Forum, reports, templates, and project decisions where the team already works.
QA and browser evidence
Run browser checks, capture screenshots and recordings, attach evidence, and create structured QA issues.
Multi-agent coordination
Assign approved tasks to Cursor, Claude, Codex, Playwright, and specialized enterprise agents.
Recurring reporting
Create project dashboards, weekly reports, risk summaries, and notifications automatically.
How Bunny works
A continuous cycle from understanding to human approval
Understand and plan
Read the available context, clarify the goal, create the work structure, and define what success means.
Execute and verify
Use approved tools and agents, run checks, collect evidence, and update the relevant Redmine records.
Report and improve
Surface decisions for human review, publish results, and improve future work through private skills and notebook memory.
Enterprise-ready autonomy
Let AI work continuously without giving up control
Every AI Employee is bound to a Redmine identity, a controlled toolset, a monthly budget, and a complete execution history.
ADMINISTRATOR CONTROLSGive AI a clear scope. Keep every action traceable.
AI EmployeeProject assistant
AI can access only what its Redmine account can access.
Only the tools you allow are available to this Employee.
At the monthly limit, the next job stops.
See what ran, what was blocked, and why.
Bound Redmine accountProject manager · pm-teamSame project permissions as this account
Permitted projectAccessible
Restricted projectNot accessible
Tool allowlist
Only selected tools are available to this AI Employee.
create_issueAccessiblemanage_wikiAccessiblecreate_projectNot accessibleHard limit$50 USD
Budget reached. Execution stopped.
Start next scheduled jobBudget stop
Execution logs.json
ActionResult
Read permitted issueCompleted
Read restricted projectPermission denied
Start next scheduled jobBudget stop
View example JSON record
{
"example": true,
"account": "pm-team",
"tool": "get_issue_content",
"status": "completed",
"monthly_budget_usd": 50,
"next_execution": "budget_exceeded"
}Configured by system administrators
Illustrative product walkthrough
Bunny inherits the bound account's access. Restricted projects stay restricted.Administrators choose the tools each AI Employee can use.A monthly hard limit stops execution when the configured budget is reached.Review the outcome and execution context in a structured JSON record.
Redmine-bound identity
The AI cannot access projects or issues that its assigned Redmine account cannot see.
Admin-managed tools
Administrators control which models, tools, prompts, skills, schedules, and notebooks may be used.
Human approval points
Prompts define which actions take effect directly and where the AI must stop for confirmation.
Complete execution records
Prompts, tool calls, modifications, outputs, errors, tokens, costs, and timestamps remain traceable.
Bring your own model
Use customer-provided API keys, cloud models, local models, or models selected per Employee.
Monthly hard limits
Apply company-wide and per-Employee budgets; when the limit is reached, execution stops.
FAQ
Redmine AI Agent FAQ
Does Bunny replace Redmine?
No. Redmine remains the system of record, permission boundary, and project workspace. Bunny adds an AI execution layer.
Can the AI update issues automatically?
Yes, inside the permissions and confirmation rules defined by administrators and prompts.
Can each employee configure their own AI?
Each employee can maintain private prompts and skills. Administrators can govern every AI Employee centrally.
Can Bunny work on a schedule?
Yes. It can create, modify, and run one-time or recurring schedules within its authorized scope.
Start with one workflow
Design your first Redmine AI Agent with Appar
Tell us which project work consumes the most time. We will map the account, tools, model, approval points, and deployment path.