BoB (Big ol’ Brain) — Product Vision & Strategy

Last updated: 2026-04-11

Vision

BoB is a self-improving development framework for Claude Code that turns ephemeral AI sessions into a persistent, cross-project operating system. It turns Claude Code from a stateless chat interface into an orchestrated, autonomous engineering harness — one that carries conventions, memory, quality gates, and work-tracking across every project from a single source of truth, and that can be set loose to run unattended on well-defined work.

Problem Statement

Claude Code is powerful but stateless by default. Every project re-invents its own conventions, hooks, and workflows. Institutional knowledge evaporates between sessions. Autonomous work — where the agent runs for hours with minimal supervision — requires scaffolding that doesn’t exist out of the box: work discovery, state recovery, deterministic guardrails, dev environment reproducibility, and safe stopping points. Without this scaffolding, AI-assisted development stays firmly in “pair programming on demand” mode and never reaches “set it loose on a real backlog and come back to PRs.”

Target Users

PersonaDescriptionPrimary Need
Paul (primary)Solo developer running a portfolio of Cloudflare + SvelteKit + Drupal projects with Claude Code as the primary engineering partnerConsistent, autonomous, multi-project workflows without manual per-project setup
Future developers (secondary)Developers adopting Claude Code for structured, autonomous workA proven opinionated starting point that skips months of organic discovery

Product Principles

Ordered by priority — when principles conflict, higher wins.

  1. Declarative and version-controlled — Every piece of state is a file you can read, diff, and commit. No hidden state, no magic substitutions.
  2. Single source of truth, distributed by manifest — One place defines a thing. Projects opt in via provisions and symlinks. No copy-paste drift between projects.
  3. Deterministic guardrails — Hooks, not hopes. If a rule matters, enforce it in a hook the model can’t bypass.
  4. Remote-native — Tools must work over SSH and tmux as well as locally. Unattended runs on a VM are first-class, not an afterthought.
  5. Work tracked in GitHub — Capabilities and requirements live in GitHub Issues. Don’t reinvent project management in Markdown files.
  6. Depth before breadth — One agent going deep on a real problem beats ten agents producing demos. Parallelism is earned by use cases, not adopted for its own sake.
  7. Portable IaC — Nothing BoB ships should be tied to a specific host’s filesystem layout. Hardcoded paths are a bug.

What We Won’t Do (Non-Goals)

  • Modify or fork Claude Code itself — BoB wraps it, never forks it
  • Build IDE plugins or a GUI — CLI + tmux + optional HTML dashboards is the entire surface
  • Host a SaaS or provide multi-tenant auth — single developer, shareable but not multi-user
  • Train or fine-tune models — BoB uses Claude as-is
  • Reimplement platform capabilities Anthropic is about to ship — watch the release notes and adopt platform primitives over BoB-native ones

Strategy

Competitive Landscape

AlternativeStrengthsWeaknessesOur Differentiator
Vanilla Claude CodeZero setupStateless, no cross-project memory, no autonomy scaffoldingPersistent memory, manifest-driven tooling, warp-drive loop
Cursor / Copilot / IDE AIPolished UX, inline editsNo hours-long autonomy, no cross-project state, sealed workflowUnattended autonomous runs with deterministic guardrails
Conductor.build / CrystalPolished parallel-agent GUIsmacOS-only, cannot see code on a remote VM, no declarative harnessRemote-first CLI, declarative tooling, depth per agent
Agent frameworks (LangChain, Ruflo, etc.)Flexible abstractionsGeneric, heavy, no Claude Code integrationNative Claude Code skills/hooks/commands; not a separate runtime

Key Differentiators

  1. Warp-drive autonomous loop — Discover work from GitHub Issues, code, test, commit, report, merge. Runs unattended for hours with state-machine recovery and deterministic guardrails.
  2. Manifest-driven provisioning — Per-project manifests at ~/.claude/provisions/<project>.json declare which skills, commands, agents, and runbooks each project needs. cdprov resolves and symlinks them. No per-project duplication.
  3. Hooks as deterministic guardrails — Branch enforcement, AI-attribution stripping on commits, commit detection, worktree safety. Enforced at the tool-use layer, not on trust.
  4. Persistent memory — Auto-loaded file-based memory survives between sessions, scoped by user, project, feedback, and reference. Compounds over time.
  5. Dev lifecycle IaCdev.json + seeded test users + /dev-up brings any project to a testable state deterministically. Warp-drive integrates with it for health checks between chunks and auto-recovery on failure.
  6. Remote-first — Runs on any Linux box over SSH and tmux. Dual-mode: laptop for interactive work, farm-01 for unattended autonomous runs.

Phased Roadmap

PhaseFocusSuccess Signal
NowNanawall production use of warp-drive + cdfork (worktree fan-out: fork, status, drop, pair, --from-issues, serial-only filter — shipped 2026-04, see #110) for the headless migration3–4x throughput on nanawall module clusters; headless migration proceeds in contract-driven parallel chunks
NextAutonomous CI-fix and merge-conflict handling in warp-drive; IaC portability cleanup (purge remaining farm-01 symlink leakage); per-project .docs → docs standardizationWarp-drive reliably ships merge-ready PRs without human intervention on clean work; BoB repo checks out cleanly on any Unix host
LaterLesson recall system (currently write-only); Claude Agent Teams integration if it ships stable; aggregate cross-project health dashboard; memory query layerMemory compounds across sessions and is actively retrievable; multi-agent primitives adopted from the platform layer rather than reinvented

Success Metrics

MetricCurrentTargetTimeframe
Projects on manifest-driven provisions~6All active projects2026 Q2
Warp-drive unattended run success rate (merge-ready PR per autonomous run on approved work)Improving> 80%2026 Q2
Nanawall module-week throughput via cdforkTooling shipped, awaiting first nanawall production run3–4x vs serial2026 Q3
Cross-host portabilityPartial (farm-01 symlink leakage in project-management/templates/)Clean checkout on any Unix2026 Q2
Memory layer utilityWrite-onlyQueryable + auto-loaded with recall2026 Q3
Nanawall headless migration capabilities shipped (CAP-01..11)0112026 H2

Risks & Open Questions

  • Complexity creep — BoB grows faster than it gets pruned. Mitigation: regular simplification passes; “only build what’s been needed twice”; this vision doc as a brake on feature sprawl.
  • Claude Code platform drift — Anthropic’s underlying architecture may change (Agent Teams, skills, hooks APIs). Mitigation: loose coupling, test after Claude Code updates, willing to adopt platform primitives and retire BoB-native replacements.
  • Single-developer bottleneck — Only Paul understands every corner. Mitigation: self-documenting tools, this vision, CLAUDE.md, auto-memory system.
  • Portability leakage — Hardcoded farm-01 paths discovered in project-management/templates/ on 2026-04-11 (entire directory of broken symlinks pointing at /home/farm). Mitigation: treat IaC portability as a recurring audit; the earlier 2026-02-19 IaC audit already caught related cases.
  • RDB lesson (and its generalization) — Remote Decision Bridge was built, then deprecated when Claude native remote control shipped around 2026-03. Real cost: weeks of work on a feature the platform soon obviated. Mitigation: watch Claude Code releases before building anything the platform might absorb. This applies directly to the cdfork vs Agent Teams decision — check Agent Teams’ stability before committing to the full cdfork build-out.

Capabilities

Link to GitHub Issues labeled cap:

  • (BoB’s capabilities currently live in the legacy project-management/product-spec.md. Migrating them to GitHub Issues labeled cap is a separate cleanup task, tracked outside this vision.)

This document is the anchor for all BoB product decisions. Capabilities and requirements should trace back to this vision. If something doesn’t connect here, question whether it belongs.