SDD Observatory

BMAD-Method established

Agile AI development framework that simulates a full team of specialized agent personas across a four-phase lifecycle, scaling its ceremony to project complexity.

Reviewed 2 months ago · Jul 18, 2026

Website GitHub · bmad-code-org/BMAD-METHOD Compare with other frameworks →

Stars
52.5K
Contributors
159
Open issues
32
Age
1.4 years
Last push
1 hour ago
Latest release
v6.11.0 Aug 10, 2026
Week of Sep 7, 2025: 6 commits Week of Sep 14, 2025: 1 commit Week of Sep 21, 2025: 0 commits Week of Sep 28, 2025: 52 commits Week of Oct 5, 2025: 12 commits Week of Oct 12, 2025: 41 commits Week of Oct 19, 2025: 29 commits Week of Oct 26, 2025: 49 commits Week of Nov 2, 2025: 32 commits Week of Nov 9, 2025: 31 commits Week of Nov 16, 2025: 30 commits Week of Nov 23, 2025: 27 commits Week of Nov 30, 2025: 46 commits Week of Dec 7, 2025: 58 commits Week of Dec 14, 2025: 38 commits Week of Dec 21, 2025: 32 commits Week of Dec 28, 2025: 25 commits Week of Jan 4, 2026: 16 commits Week of Jan 11, 2026: 39 commits Week of Jan 18, 2026: 43 commits Week of Jan 25, 2026: 47 commits Week of Feb 1, 2026: 51 commits Week of Feb 8, 2026: 22 commits Week of Feb 15, 2026: 30 commits Week of Feb 22, 2026: 25 commits Week of Mar 1, 2026: 18 commits Week of Mar 8, 2026: 117 commits Week of Mar 15, 2026: 78 commits Week of Mar 22, 2026: 38 commits Week of Mar 29, 2026: 23 commits Week of Apr 5, 2026: 27 commits Week of Apr 12, 2026: 9 commits Week of Apr 19, 2026: 20 commits Week of Apr 26, 2026: 23 commits Week of May 3, 2026: 5 commits Week of May 10, 2026: 4 commits Week of May 17, 2026: 7 commits Week of May 24, 2026: 21 commits Week of May 31, 2026: 2 commits Week of Jun 7, 2026: 9 commits Week of Jun 14, 2026: 10 commits Week of Jun 21, 2026: 24 commits Week of Jun 28, 2026: 11 commits Week of Jul 5, 2026: 12 commits Week of Jul 12, 2026: 6 commits Week of Jul 19, 2026: 3 commits Week of Jul 26, 2026: 27 commits Week of Aug 2, 2026: 12 commits Week of Aug 9, 2026: 27 commits Week of Aug 16, 2026: 9 commits Week of Aug 23, 2026: 24 commits Week of Aug 30, 2026: 6 commits
Commits per week, last 12 months · 1.4K total
View weekly commit data
Week startingCommits
Aug 30, 20266
Aug 23, 202624
Aug 16, 20269
Aug 9, 202627
Aug 2, 202612
Jul 26, 202627
Jul 19, 20263
Jul 12, 20266
Jul 5, 202612
Jun 28, 202611
Jun 21, 202624
Jun 14, 202610
Jun 7, 20269
May 31, 20262
May 24, 202621
May 17, 20267
May 10, 20264
May 3, 20265
Apr 26, 202623
Apr 19, 202620
Apr 12, 20269
Apr 5, 202627
Mar 29, 202623
Mar 22, 202638
Mar 15, 202678
Mar 8, 2026117
Mar 1, 202618
Feb 22, 202625
Feb 15, 202630
Feb 8, 202622
Feb 1, 202651
Jan 25, 202647
Jan 18, 202643
Jan 11, 202639
Jan 4, 202616
Dec 28, 202525
Dec 21, 202532
Dec 14, 202538
Dec 7, 202558
Nov 30, 202546
Nov 23, 202527
Nov 16, 202530
Nov 9, 202531
Nov 2, 202532
Oct 26, 202549
Oct 19, 202529
Oct 12, 202541
Oct 5, 202512
Sep 28, 202552
Sep 21, 20250
Sep 14, 20251
Sep 7, 20256

Metrics updated Sep 1, 2026 · collected automatically from the GitHub API

Core approach

Simulates an agile team of 12+ specialized AI agent personas (PM, Architect, Developer, UX, and more) that facilitate structured workflows across a four-phase lifecycle. Planning depth auto-adjusts to project complexity, from bug fixes to enterprise systems. Installed via npx as a module ecosystem with 34+ workflows in the core module.

Workflow

  1. Phase 1 · Analysis (optional) — brainstorming, idea forging, domain/market/technical research, product brief
  2. Phase 2 · Planning — PRD and UX workflows
  3. Phase 3 · Solutioning — architecture, epic and story creation, implementation-readiness gate
  4. Phase 4 · Implementation — sprint planning, story development, code review, course correction, retrospective
  5. Parallel Quick Flow track — quick-dev and an unattended dev loop for small changes

Supported tools

Strengths

  • Broadest lifecycle coverage of the frameworks tracked here — ideation through retrospective, not just spec-to-code
  • Modular ecosystem (builder, test architect, game dev, creative suite) plus web bundles that offload planning to Gemini Gems or ChatGPT Custom GPTs on flat-rate LLM subscriptions
  • Scale-adaptive planning depth, with a help workflow that guides users to the next step
  • Free and open source with a large, active community and frequent releases

Limitations

  • Heavyweight and ceremony-rich compared to lighter SDD kits — many agents, phases, and workflows to learn
  • V6 was a breaking restructure; upgrading from v4/v5 requires a dedicated migration guide
  • Prerequisites span Node.js 20.12+, Python 3.10+, and uv
  • The repo does not visibly dogfood its own story/PRD artifacts in-tree, and BMAD/BMad are trademarks with usage restrictions

Tracked projects using BMAD-Method

Notes

BMAD reads less like a spec format and more like an operating model: it recreates the roles of an agile team as agent personas and routes work through their ceremonies. That makes it the most complete lifecycle of the tracked frameworks and also the heaviest. Its repository moved from bmadcode/BMAD-METHOD to the bmad-code-org organization, and GitHub reports its license as “Other” because the MIT text carries a custom preamble. Well-starred active adopters are hard to observe in public — code search finds ~400 v4-era .bmad-core configs, but the most visible ones have gone idle — so evidence of long-term outcomes is currently thin.

Added Jul 18, 2026 · Assessment last reviewed Jul 18, 2026 · How we track