# Rig Docs

> Research, proposals, and reference documentation for the rig — a shared autonomous-engineering platform serving multiple orgs and projects. Authored for humans and AI agents together. All content is markdown with YAML frontmatter; diagrams are Mermaid source.

## Start here

- **Brain (read first):** https://rig-research.pages.dev/brain/ — repo manifest, surfaces, agents, primary flows. One fetch, ~10 KB.
  Raw markdown (public, no auth): https://rig-research.pages.dev/BRAIN.md
- **Full content dump:** https://rig-research.pages.dev/llms-full.txt — every doc concatenated, one fetch = whole hub.

## For agents

- Source repo: https://github.com/dashecorp/rig-docs
- Raw markdown: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/<path>.md
- Rendered site: https://rig-research.pages.dev
- Sitemap: https://rig-research.pages.dev/sitemap-index.xml
- Mermaid diagrams: rendered client-side, source preserved in <details class="mermaid-source"> blocks
- Frontmatter fields: title, description, type, audience, created, updated, topic, source_refs, supersedes, superseded_by, user_story, research_docs, proposal, source_research, github_issue

## User stories

- [User story: how should the rig handle docs vs memory (2026-04-18)](https://rig-research.pages.dev/user-stories/2026-04-18-docs-memory-strategy/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/user-stories/2026-04-18-docs-memory-strategy.md
  Parent user story tying together the three research docs (DASHE-11/12/13) for the docs/memory strategy refinement.
- [User story: memory-to-docs promotion pipeline](https://rig-research.pages.dev/user-stories/2026-04-19-memory-to-docs-promotion/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/user-stories/2026-04-19-memory-to-docs-promotion.md
  Memory accumulates agent experience; brain holds canonical truth. Close the loop: a weekly lint promotes high-value memories into docs PRs so the brain gets smarter over time.
- [User story: onboard Tablez to the rig](https://rig-research.pages.dev/user-stories/2026-04-19-onboard-tablez-to-rig/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/user-stories/2026-04-19-onboard-tablez-to-rig.md
  Tablez leadership wants a dedicated autonomous engineering capacity on its product backlog. First onboarded project against the multi-project brain design.
- [User story: two-layer brain for multi-project support](https://rig-research.pages.dev/user-stories/2026-04-19-two-layer-brain-multi-project/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/user-stories/2026-04-19-two-layer-brain-multi-project.md
  Split the brain into an invariant rig brain (how agents work) and per-project brains (what each project is) so the same agents serve multiple product portfolios (Dashecorp iOS, Tablez, future).

## Proposals

- [Docs tooling decision: Starlight + Cloudflare Pages (2026-04-18)](https://rig-research.pages.dev/proposals/2026-04-18-docs-tooling-decision/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/proposals/2026-04-18-docs-tooling-decision.md
  Final tooling decision for Dashecorp rig documentation, superseding the research report's Notion recommendation.
- [Stage A — Compiled AGENTS.md with Schema Validation](https://rig-research.pages.dev/proposals/2026-04-18-stage-a-compiled-agents-md/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/proposals/2026-04-18-stage-a-compiled-agents-md.md
  One PR to rig-gitops replacing hand-written AGENTS.md with a compiled, schema-validated, size-budgeted version

## Research

- [Research: anti-drift lint rules between docs and memory (2026-04-18)](https://rig-research.pages.dev/research/2026-04-18-docs-memory-drift-lint/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research/2026-04-18-docs-memory-drift-lint.md
  Automated lint rules to prevent docs and memory from drifting apart as the rig operates.
- [Research: current docs and memory inventory (2026-04-18)](https://rig-research.pages.dev/research/2026-04-18-docs-memory-inventory/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research/2026-04-18-docs-memory-inventory.md
  Snapshot of what lives in docs vs memory at the time the docs-memory strategy arc started.
- [Documentation state audit — dashecorp rig (2026-04-18)](https://rig-research.pages.dev/research/2026-04-18-docs-state-audit/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research/2026-04-18-docs-state-audit.md
  Ground-truth snapshot of docs across all 7 active dashecorp repos: frontmatter compliance, CLAUDE.md/AGENTS.md presence, broken patterns
- [Documentation tools evaluation (2026-04-18)](https://rig-research.pages.dev/research/2026-04-18-docs-tools-evaluation/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research/2026-04-18-docs-tools-evaluation.md
  Comparison of 25 documentation tools against 12 weighted criteria for the Dashecorp rig. Verdict: Starlight picked over Notion/Outline after Plane rejected.
- [Research: principles for docs vs memory separation (2026-04-18)](https://rig-research.pages.dev/research/2026-04-18-docs-vs-memory-principles/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research/2026-04-18-docs-vs-memory-principles.md
  Five candidate principles for deciding what belongs in canonical docs versus in operational memory MCP.
- [LLM Wiki pattern — Karpathy analysis](https://rig-research.pages.dev/research/2026-04-18-llm-wiki-pattern-analysis/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research/2026-04-18-llm-wiki-pattern-analysis.md
  Analysis of Karpathy's LLM Wiki gist and how it applies to an autonomous coding-agent rig
- [Production agent docs patterns — Vercel, Cloudflare, HumanLayer, Anthropic](https://rig-research.pages.dev/research/2026-04-18-production-docs-patterns/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research/2026-04-18-production-docs-patterns.md
  What production coding-agent rigs actually put in their AGENTS.md / CLAUDE.md files, with measured eval data

## Reference

- [Rig Brain](https://rig-research.pages.dev/brain/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/brain.md
  Fresh-agent entry point — repo manifest, deployed surfaces, agent instances, primary flows, schema, event types, backlog.
- [Brain map](https://rig-research.pages.dev/map/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/map.md
  Visual map of the rig brain, project brains, and the user-story ↔ research ↔ whitepaper graph. Auto-derived from facts + frontmatter at build time.
- [Proposals](https://rig-research.pages.dev/proposals/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/proposals.md
  Ship plans — one per decision. Each links to the research it synthesises and the user story it answers.
- [Reference](https://rig-research.pages.dev/reference/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/reference.md
  Durable reference material — AGENTS.md, facts, conventions.
- [AGENTS.md (rig-docs)](https://rig-research.pages.dev/reference/agents/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/reference/agents.md
  Agent-facing reference for this repo — where user-stories/research/proposals live, how to author, what the CI schema requires.
- [Facts](https://rig-research.pages.dev/reference/facts/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/reference/facts.md
  Source-of-truth YAML for compiled AGENTS.md. CI fails if AGENTS.md drifts from these files.
- [Research](https://rig-research.pages.dev/research/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/research.md
  All research docs. Dated, one file per focused question. Each links to the user story it supports.
- [User stories](https://rig-research.pages.dev/user-stories/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/user-stories.md
  Stories captured from human stakeholders. Each links to its research and (once approved) its proposal.
- [Whitepapers](https://rig-research.pages.dev/whitepapers/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/whitepapers.md
  Strategic, leadership-facing architecture papers. Visual and diagram-heavy. Meant to be shared outside the engineering team.
- [Brain and Memory — architecture for autonomous engineering](https://rig-research.pages.dev/whitepapers/2026-04-19-brain-and-memory/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/whitepapers/2026-04-19-brain-and-memory.md
  Visual whitepaper for engineering leadership. The rig is a shared autonomous-engineering platform: brain + memory + agents. Works two ways — building the rig itself, and shipping products on top of it. Multi-org, multi-project from day one.

## Other

- [Rig Docs](https://rig-research.pages.dev/index/)  
  Source: https://raw.githubusercontent.com/dashecorp/rig-docs/main/src/content/docs/index.md
  Documentation hub for the rig — a shared autonomous-engineering platform. Research, proposals, architecture, diagrams.