{"id":48965282,"url":"https://github.com/iurykrieger/claude-bedrock","last_synced_at":"2026-05-05T14:11:56.800Z","repository":{"id":351115949,"uuid":"1209548003","full_name":"iurykrieger/claude-bedrock","owner":"iurykrieger","description":"Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills","archived":false,"fork":false,"pushed_at":"2026-04-13T18:09:25.000Z","size":202,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-13T18:20:10.831Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iurykrieger.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-13T14:36:56.000Z","updated_at":"2026-04-13T18:09:26.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/iurykrieger/claude-bedrock","commit_stats":null,"previous_names":["iurykrieger/claude-bedrock"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/iurykrieger/claude-bedrock","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iurykrieger%2Fclaude-bedrock","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iurykrieger%2Fclaude-bedrock/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iurykrieger%2Fclaude-bedrock/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iurykrieger%2Fclaude-bedrock/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iurykrieger","download_url":"https://codeload.github.com/iurykrieger/claude-bedrock/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iurykrieger%2Fclaude-bedrock/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31955919,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T00:39:45.007Z","status":"online","status_checked_at":"2026-04-18T02:00:07.018Z","response_time":103,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-04-18T04:00:44.626Z","updated_at":"2026-05-05T14:11:56.793Z","avatar_url":"https://github.com/iurykrieger.png","language":"HTML","funding_links":[],"categories":["Documentation, Knowledge \u0026 Learning"],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/banner.png\" alt=\"Bedrock — Knowledge graph visualization\" width=\"600\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eBedrock\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eTurn any Obsidian vault into a structured Second Brain with AI agents\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/iurykrieger/claude-bedrock/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-MIT-blue.svg\" alt=\"License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/iurykrieger/claude-bedrock\"\u003e\u003cimg src=\"https://img.shields.io/badge/claude--code-plugin-a882ff\" alt=\"Claude Code Plugin\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/iurykrieger/claude-bedrock\"\u003e\u003cimg src=\"https://img.shields.io/github/v/tag/iurykrieger/claude-bedrock?label=version\" alt=\"Version\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\nBedrock is a [Claude Code](https://docs.anthropic.com/en/docs/claude-code) plugin that automates Obsidian vault management through AI-powered skills. It organizes knowledge into **7 entity types** following adapted [Zettelkasten](https://zettelkasten.de/overview/) principles — entity detection, bidirectional linking, ingestion from external sources, deduplication, and sync.\n\nNo build system. No runtime. Just markdown files, AI agents, and your Obsidian vault.\n\n## Features\n\n- **8 AI-powered skills** — setup, ask, teach, preserve, compress, sync, healthcheck, and vaults\n- **7 entity types** — actors, people, teams, topics, discussions, projects, and fleeting notes\n- **External source ingestion** — Confluence, Google Docs, GitHub repositories, and any file format supported by [docling](https://github.com/docling-project/docling) (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and more)\n- **Bidirectional wikilinks** — automatic cross-referencing with Obsidian graph view\n- **Hierarchical tags** — multi-dimensional filtering (`type/`, `status/`, `domain/`, `scope/`)\n- **Zettelkasten structure** — permanent, bridge, index, and fleeting note roles\n- **Trunk-based git workflow** — structured commit conventions built in\n\n## Installation\n\n```bash\n/plugin marketplace add iurykrieger/claude-bedrock\n/plugin install bedrock@claude-bedrock\n```\n\nFor local development:\n\n```bash\nclaude --plugin-dir ./claude-bedrock\n```\n\n## Quick Start\n\nAfter installing, run the setup wizard:\n\n```\n/bedrock:setup\n```\n\nThis will guide you through:\n\n1. **Language selection** — choose the vault content language (default: English)\n2. **Dependency check** — verify `graphify` is installed (required)\n3. **Vault objective** — pick a preset (engineering team, product management, company wiki, personal second brain, open source project, or custom)\n4. **Scaffold** — create directories, templates, config, and connected example entities\n\nThe setup creates all entity directories, copies templates, generates a vault-level `CLAUDE.md`, and scaffolds example entities with bidirectional wikilinks so you can see the graph in Obsidian immediately.\n\n## Skills\n\n| Skill | Purpose |\n|---|---|\n| `/bedrock:setup` | Interactive vault initialization and configuration |\n| `/bedrock:ask` | Orchestrated vault reader — decomposes questions, searches graph and vault, cross-references entities |\n| `/bedrock:learn` | Ingest external sources — extract and create entities |\n| `/bedrock:preserve` | Single write point — detect, match, create/update entities with bidirectional links |\n| `/bedrock:compress` | Deduplication and vault health — broken links, orphans, stale content |\n| `/bedrock:sync` | Re-sync entities with external sources |\n| `/bedrock:healthcheck` | Read-only vault health diagnostic — graphify-out integrity, orphans, dangling content, stale entries |\n| `/bedrock:vaults` | Manage registered vaults — list, set default, remove |\n\n## Vault Structure\n\n```\nyour-vault/\n├── actors/          # Systems, services, APIs (permanent notes)\n├── people/          # Contributors, team members (permanent notes)\n├── teams/           # Squads, organizational units (permanent notes)\n├── topics/          # Cross-cutting subjects with lifecycle (bridge notes)\n├── discussions/     # Meeting notes, conversations (bridge notes)\n├── projects/        # Initiatives with scope and deadline (index notes)\n└── fleeting/        # Raw ideas, unstructured captures (fleeting notes)\n```\n\nEach directory contains a `_template.md` defining the frontmatter schema for that entity type.\n\n## How It Works\n\nBedrock turns your vault into a living knowledge graph by combining **8 skills** you invoke from Claude Code. You never write entities by hand — skills detect, create, and link them for you, with Obsidian rendering the result as a graph.\n\n### First-time use\n\n1. Open a folder you want to turn into a vault (or an existing Obsidian vault).\n2. Run `/bedrock:setup` — answers a few questions and scaffolds directories, templates, and example entities.\n3. Open the folder in Obsidian. You'll already see a connected graph.\n\n### Day-to-day loops\n\n- **Capture knowledge from a source** — paste a Confluence page, Google Doc, GitHub repo, remote URL, or any local file (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and any other docling-supported format) into `/bedrock:learn`. Bedrock extracts entities and writes them to the vault with bidirectional links.\n- **Ask the vault questions** — use `/bedrock:ask` for anything like *\"who owns the billing API?\"* or *\"what's the status of project X?\"*. It searches the graph, follows wikilinks, and answers with citations.\n- **Keep sources fresh** — run `/bedrock:sync` to re-pull external sources, or `/bedrock:sync --github` / `--people` to surface recent activity and contributors.\n- **Clean up drift** — run `/bedrock:compress` to fix broken backlinks, merge duplicates, and consolidate fragmented concepts. Run `/bedrock:healthcheck` for a read-only report.\n- **Manage multiple vaults** — register several vaults with `/bedrock:vaults`; target a specific one with `--vault \u003cname\u003e`.\n\n### What you get in Obsidian\n\nEvery entity has YAML frontmatter (type, status, domain, sources), hierarchical tags (`type/actor`, `status/active`, `domain/payments`), and bidirectional wikilinks. The graph view becomes a navigable map of people, systems, teams, topics, and projects — updated automatically as you teach Bedrock new content.\n\n## Dependencies\n\n| Tool | Purpose | Required? |\n|---|---|---|\n| [graphify](https://github.com/iurykrieger/graphify) | Semantic code extraction and knowledge-graph pipeline used by `/bedrock:learn` and `/bedrock:sync` | Yes |\n| [docling](https://github.com/docling-project/docling) | Universal file → markdown converter used by `/bedrock:learn` to ingest DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and other non-markdown formats | Yes |\n\nBoth `graphify` and `docling` are auto-installed by `/bedrock:setup` (and lazily by `/bedrock:learn` on first use if missing). You can also install them manually via `pipx install graphify` / `pipx install docling`.\n\nConfluence and Google Docs ingestion are built into the plugin as internal skills (`/bedrock:confluence-to-markdown`, `/bedrock:gdoc-to-markdown`) invoked by `/bedrock:learn` and `/bedrock:sync` — no external installation required.\n\n## Configuration\n\nConfiguration is stored in `.bedrock/config.json` inside your vault. Run `/bedrock:setup` again at any time to reconfigure.\n\n## Error Reporting\n\nThe `bedrock` plugin auto-reports framework errors as GitHub issues on\n[iurykrieger/claude-bedrock](https://github.com/iurykrieger/claude-bedrock) so\nmaintainers learn about real-world failures.\n\n**What gets reported**\n- Python tracebacks from skill scripts\n- Non-zero exit codes from skill bash commands\n- Known logical-failure phrases in Claude's text (small auditable regex catalog)\n\n**What never gets reported**\n- Vault content (markdown bodies, frontmatter values)\n- Absolute filesystem paths (replaced with `.../`)\n- Vault entity names (people, teams, projects, etc.)\n- URLs from your vault (Confluence, Google Docs, internal repos)\n\n**How to opt out**\n\nAdd `\"error_reporting\": false` to your vault's `.bedrock/config.json`:\n\n```json\n{\n  \"error_reporting\": false\n}\n```\n\nDefault is `true`. The hook silently skips reporting if `gh` is not installed\nor you're not authenticated, and logs the would-be report to\n`~/.claude-bedrock-cache/error-reporter.log`.\n\n## Contributing\n\nContributions are welcome! Here's how to get started:\n\n1. **Fork** the repository\n2. **Clone** your fork and install the plugin locally:\n   ```bash\n   claude --plugin-dir ./claude-bedrock\n   ```\n3. **Create a branch** for your feature or fix\n4. **Make your changes** — skills live in `skills/`, entity definitions in `entities/`, templates in `templates/`\n5. **Test** by running the plugin against a test vault\n6. **Open a PR** against `main`\n\n### Project Structure\n\n```\nclaude-bedrock/\n├── .claude-plugin/    # Plugin manifest (plugin.json)\n├── skills/            # Skill definitions (SKILL.md per skill)\n│   ├── setup/\n│   ├── query/\n│   ├── teach/\n│   ├── preserve/\n│   ├── compress/\n│   └── sync/\n├── entities/          # Entity type definitions\n├── templates/         # Frontmatter schema templates\n├── docs/              # Documentation assets\n├── CLAUDE.md          # AI agent instructions\n└── README.md\n```\n\n## License\n\n[MIT](LICENSE) — Iury Krieger\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiurykrieger%2Fclaude-bedrock","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiurykrieger%2Fclaude-bedrock","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiurykrieger%2Fclaude-bedrock/lists"}