Bodhiorchard™

Bodhiorchard replaces sprint, scrum, and Jira ceremony with Agent-Driven Development (ADD) — twelve specialised AI agents handle the busywork (triage, specs, estimates, test plans, retrospectives) while humans keep the decisions that matter, and developers earn XP for the work that actually reaches production. It's a self-hosted Jira alternative for the full lifecycle: intake → spec → design → development → testing → deploy → retrospective. The data plane stays on your hardware; inference runs through your choice of agent — Claude Code, GitHub Copilot, OpenAI Codex, or Ollama for fully-local inference — picked per organization in setup.

Less process. More shipped. The full methodology lives at bodhiorchard.ai.

The fastest path — no clone, no build. Needs only Docker (running) and Node.js 18+:

npx bodhiorchard init     # detect ports, generate secrets, pull prebuilt images
cd bodhiorchard
npx bodhiorchard start    # start the stack and open the setup wizard

The wizard opens at http://localhost:3000/setup — finish there (organization, admin account, AI provider, repositories). bodhiorchard stop brings it down; your data volumes persist.

Prefer to build from source?

git clone https://github.com/mickyarun/bodhiorchard.git
cd bodhiorchard
docker compose up

Already running claude on your laptop? Hybrid mode reuses your Claude Pro/Max login instead of an API key:

npm install && npm run setup && npm run dev

→ All three paths, the full bodhiorchard CLI command list, prerequisites, mode-switching, and a ready-made demo dataset: Deployment Guide

Slack triage — a message in, a BUD out	One BUD per feature — spec to prod

AI drafts the tech spec, you decide	Feature registry — every feature, every dev

Cross-repo code graph — one map	Bring your own AI — MCP knowledge

The gamification layer rebuilds developer skill profiles nightly — skills compound, badges unlock, and the leaderboard reflects shipped value, not ticket count:

And yes — your codebase is a living orchard. Repos as trees, features as fruit, your team walking the garden:

More walkthroughs: Setup · Slack triage & MCP tools · Requirements & estimation · Design phase · Development & retrospective

The rest of the company can use Bodhiorchard too. HR and Sales staff get a People workspace with leave, the team calendar and their own details. Everything engineering is hidden from them in the UI and refused at the API, MCP, WebSocket and multiplayer layers.

• Leave and work from home. Balances per leave type, half days, optional holidays with a yearly quota, and backdating up to a limit HR sets. The request dialog counts working days, skipping weekends and holidays, before anything is sent.
• Loss of pay. Leave past someone's balance is not refused. The extra days are marked unpaid, shown to the employee before they send the request and to the approver before they decide, and handed back if the request is cancelled or a holiday is added later.
• Approvals. Anyone can have several reporting managers. Any one of them can decide, the first decision wins, and HR covers when no manager is left. Approvers get a Slack DM with Approve and Reject buttons, so most decisions never need a login.
• Leave policies per location. Each policy has its own leave types and quotas, working days, timezone, leave year, proration for new joiners, and work-from-home rule (always ask, never ask, or approve automatically up to N days a month). Public holidays are imported for the country and region, then HR edits them.
• Offices and remote work. Each office follows a leave policy, so moving someone to London moves them onto the UK calendar. Remote people have no office and never show as working from home.
• Team calendar and a daily Slack post. One calendar for who is out and who is at home. A short post every working morning lists names only, never the leave type or reason, and nobody on leave is @mentioned.
• Employee records. Work and personal details, bank and ID numbers, and documents. Sensitive fields and files are encrypted with AES-256-GCM under a separate HR key. Bank and ID numbers stay masked until someone reveals them, every reveal and download is logged, and each employee can see who opened their records.

Leave home — balances and loss of pay	Request dialog — days counted before you send

Approvals — balance and overlaps on every card	Team calendar — leave, WFH and holidays

Leave policies per location	Employee directory — offices, remote and hybrid

Every feature lives in one BUD (Business Understanding Document) that moves through the lifecycle, with an agent driving each phase and a human gate between phases:

bud → design → tech_arch → development → testing → uat → prod → closed
                                                              ↳ discarded (any time)

• Slack-native intake — post in #feature-requests, the Triage Agent interviews you in-thread, checks duplicates via vector search, and queues for PM approval.
• Multi-repo code intelligence — a tree-sitter code-graph indexer scans your repos, detects feature clusters across them, and answers blast-radius queries ("what breaks if I change this?").
• Smart quality loops — production bugs auto-link to the originating BUD; threshold breaches trigger reassignment; every fix feeds the knowledge base.
• Developer skill profiling — per-module expertise scores rebuilt nightly from git history, with bus-factor alerts and best-fit assignment.
• Living knowledge — git repos, agent skills, the central DB, and vector search stay auto-synced and feed every agent prompt.
• Enterprise-grade security — multi-tenant isolation, role-based access with a ceiling (nobody grants more than they hold), separate engineering and People workspaces, AES encryption at rest with key rotation, JWT auth, full audit trail.

Every agent action is audited and reviewable in the UI. Triggers, hand-offs, and capabilities: AGENTS.md.

Eight principles, deliberately echoing the Agile Manifesto's "X over Y" structure:

Stack: FastAPI + SQLAlchemy 2.0 (async) on Python 3.12 · Vue 3 + Vuetify + PlayCanvas (3D) · Colyseus multiplayer · PostgreSQL 16 + pgvector · Redis · local ONNX embeddings (fastembed).

backend/     FastAPI — REST API, 12 agents, MCP server, code-graph indexer
frontend/    Vue 3 SPA — BUD board, Living Tree 3D dashboard, settings
multiplayer/ Colyseus server — shared 3D world state
shared/      World layout consumed by frontend + multiplayer
examples/    TaskFlow demo repos (cross-repo feature detection)

The agent layer is engine-independent: a per-org provider selector runs the agents through Claude Code, GitHub Copilot, OpenAI Codex, or Ollama — each org picks one in setup. The three CLIs reach the same tools via one STDIO MCP bridge; Ollama has no CLI, so it speaks HTTP and runs those same tools in-process. Adding an engine is a thin adapter, not a rewrite. A provider's limits are declared, not discovered: Ollama has no file access, so the features needing it are refused outright rather than answered from guesswork. Bodhiorchard also runs its own MCP server so any of those CLIs (or any MCP client) can drive the BUD lifecycle, query the code graph, and read team context.

A methodology where specialised AI agents — not humans running status meetings — drive every phase of the software lifecycle, while humans review, decide, and steer. It sits in the slot Agile occupied in 2001: a reorganisation of work around new capabilities. The methodology is free to adopt with or without Bodhiorchard — see bodhiorchard.ai.

Yes — for the full workflow layer (intake through retrospective). It's especially relevant for teams affected by Atlassian sunsetting self-hosted Jira licences (new licences end March 2026, full shutdown 2029).

The data plane — Postgres, embeddings, BUDs, scanned repos, audit log — is always local. Only LLM prompts leave, and only when you choose cloud inference. Pick the Ollama provider and nothing leaves at all — at the cost of the features that need repository access (see AI Engines).

No — and you're not tied to Claude at all. Pick your agent CLI per organization in setup: Claude Code, GitHub Copilot, or OpenAI Codex. For each you can either paste an API key / token (pay-per-token) or, in Hybrid mode, inherit the host's existing login (claude login, gh/Copilot login, or codex login) so the agents run on your flat-rate subscription.

Those are IDE-side coding assistants for an individual developer. Bodhiorchard is the orchestration and project-management layer above them — intake, specs, estimation, assignment, test plans, bug linking, retrospectives. Pair them freely.

Copilot Workspace is cloud-only and GitHub-bound. Bodhiorchard is self-hosted, repo-agnostic (GitHub, GitLab, self-hosted Git), and AI-engine-agnostic.

Business Understanding Document — one markdown document per feature holding spec, tech spec, test plan, acceptance criteria, and full history.

Yes — Apache 2.0, including embedding in proprietary products. Contributions require DCO sign-off (git commit -s). Commercial licences with support are available separately from the maintainer.

Yes. Give someone the HR or Sales role and they get the People workspace only: leave, the team calendar and their own details, with HR also handling approvals, policies and employee records. The engineering side is hidden from them and refused by the API, so it isn't just a hidden menu.

Yes — natively (no WSL required) in Hybrid mode, as well as via WSL2 or Full Docker. npm run dev handles the Windows specifics for you. If you run the backend directly with uvicorn on native Windows, don't use --reload (it forces an event loop that can't spawn the subprocesses scans/agents need) — run python backend\dev_server.py instead. See backend/README.md → Native Windows. Redis is optional: if it isn't running, re-scans fall back to a direct scan.

• Shipped — core platform (auth, multi-tenant, RBAC), BUD lifecycle, feature registry with vector search, repo scanning + code intelligence, skill profiling, 3D Living Tree, Slack-native triage and real-time Slack bot conversations, GitHub webhook pipeline (PR-merge → BUD status + repo re-scan), automated test-plan generation from BUDs (unit / integration / e2e / security / UAT), CI/CD integration (QA-automation repo wired via MCP; test commits flow back to the BUD), MCP server, 12 agent definitions, npx bodhiorchard installer, People workspace (leave and WFH with Slack approvals, holidays per location, offices and remote work, loss of pay, encrypted employee records)
• Next — autonomous agent execution engine: small, low-risk BUDs run tech spec → code → review → test end to end, with a human approval gate before release (deliberately not lights-out)
• Future — multi-org marketplace, custom agent builder, analytics dashboards, mobile companion, plugin ecosystem

Contributions welcome — fork, branch, lint (ruff / vue-tsc), and open a PR. All commits need DCO sign-off (git commit -s); see CONTRIBUTING.md.

Bodhi (Sanskrit: "awakening") is what the Buddha attained under the Bodhi tree. An orchard is a grove tended with intention so it can bear fruit. The software industry builds tools to make life better, yet the process of building them consumes our lives — ceremonies, status updates, and busywork that were meant to help but became the work itself.

Bodhiorchard exists because AI should give humans their time back. The agents are the orchardists: they water, prune, and tend the soil so the trees can grow and the humans who planted them can step back and enjoy the harvest.

Build well. Then go outside.

Apache License 2.0 — see LICENSE and NOTICE.