What makes SwarmVault notable?

2.6K downloads. Trust evidence available

How should SwarmVault be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

SwarmVault

Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack,...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.6k

Updated

Oct 9, 2026

Version

3.20.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.6K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.6K downloadsadoption · observed Oct 9, 2026
Latest release: 3.20.0release · observed Jun 12, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s172jgfp1hrj42g10wkscjf0t583ttz6:swarmvault

Install using `clawhub skill install s172jgfp1hrj42g10wkscjf0t583ttz6:swarmvault` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/waydelyle/swarmvault before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-waydelyle-swarmvault/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: swarmvault
description: "Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and recurring source workflows."
version: "3.20.0"
metadata: '{"openclaw":{"requires":{"anyBins":["swarmvault","vault"]},"install":[{"id":"node","kind":"node","package":"@swarmvaultai/cli","bins":["swarmvault","vault"],"label":"Install SwarmVault CLI (npm)"}],"emoji":"🗃️","homepage":"https://www.swarmvault.ai/docs"}}'
---

# SwarmVault

Use this skill when the user wants a local-first knowledge vault built on the [LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) pattern — three layers (raw sources, wiki, schema) where the LLM maintains a durable wiki between you and raw sources. Also use it when the project already contains `swarmvault.config.json` or `swarmvault.schema.md`.

For onboarding, examples, command references, or troubleshooting, read the bundled `README.md`, `examples/`, `references/`, and `TROUBLESHOOTING.md` before improvising workflow advice.

## Quick checks

- Work from the vault root.
- Use `swarmvault next` when you need a read-only orientation command before deciding whether to initialize, ingest, compile, query, review, or refresh.
- If the vault does not exist yet, run `swarmvault init`.
- Use `swarmvault demo --no-serve` when the user wants the fastest zero-config walkthrough before pointing SwarmVault at their own sources.
- Use `swarmvault quickstart <file-or-directory-or-github-url>` as the beginner-friendly first-run path when the user wants init + ingest + compile + graph viewer in one command.
- Use `swarmvault scan <file-or-directory-or-github-url> --no-serve`, `swarmvault scan <file-or-directory-or-github-url> --no-viz`, or `swarmvault clone <file-or-directory-or-github-url> --no-viz` when the user wants the fastest scratch pass over a local file, local repo, public GitHub repo, or docs tree without manually stepping through init + ingest + compile first; for GitHub URLs add `--branch`, `--ref`, or `--checkout-dir` when the user needs a pinned checkout. Use `scan --mcp` or `clone --mcp` when the next step should be an MCP stdio server. Use `swarmvault graph share --post` for copyable text, `swarmvault graph share --svg [path]` for a visual card, or `swarmvault graph share --bundle [dir]` for a portable folder with markdown, post text, SVG, HTML preview, and JSON metadata.
- Use `swarmvault context build "<goal>" --target <path-or-node> --budget <tokens>` when the next agent, review, or handoff needs a bounded evidence pack instead of a broad vault search.
- Use `swarmvault chat "question"` when a multi-turn conversation should survive handoff; resume with `swarmvault chat --resume <id> "follow-up"` and inspect saved transcripts under `wiki/outputs/cha

README.md

# SwarmVault Skill

Use the SwarmVault skill when you want a local-first knowledge vault that compiles books, articles, notes, transcripts, chat exports, emails, calendars, datasets, spreadsheets, slide decks, screenshots, URLs, code, and research captures into durable markdown pages, a searchable graph, dashboards, resumable chat sessions, static AI export packs, context packs, a task memory ledger, and reviewable outputs on disk.

SwarmVault is built on the [LLM Wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) pattern: keep a durable wiki between you and raw sources using a three-layer architecture (raw sources, wiki, schema). The LLM does the bookkeeping — cross-referencing, consistency, updating — while you curate sources and think about what they mean. SwarmVault turns that pattern into a local toolchain with graph navigation, search, review flows, automation, and optional provider-backed synthesis.

## Install

Install the skill from ClawHub:

```bash
clawhub install swarmvault
```

Install the CLI it depends on:

```bash
npm install -g @swarmvaultai/cli
swarmvault --version
swarmvault quickstart ./your-repo
swarmvault quickstart ./whitepaper.pdf --no-serve
swarmvault next
swarmvault demo --no-serve
swarmvault source add https://github.com/karpathy/micrograd
swarmvault ingest ./meeting.srt --guide
swarmvault ingest ./customer-call.mp3
swarmvault ingest https://www.youtube.com/watch?v=dQw4w9WgXcQ
swarmvault ingest --video https://example.com/product-demo.mp4
swarmvault source session transcript-or-session-id
swarmvault chat "What should the next agent know?"
swarmvault export ai --out ./exports/ai
```

Requirements:

- Node `>=24`
- A working `swarmvault` or `vault` binary on `PATH`

Update paths:

```bash
clawhub update swarmvault
npm install -g @swarmvaultai/cli@latest
```

## When To Use This Skill

- You want knowledge work to stay on disk instead of disappearing into chat history.
- The repo already contains `swarmvault.config.json` or `swarmvault.schema.md`.
- You want markdown wiki pages, graph artifacts, local search, approvals, candidates, and MCP exposure from the same workspace.
- You want resumable conversations over the compiled wiki and static handoff bundles for other tools.
- You want a save-first compile/query/review loop for source collections, codebases, or research material.
- You want one workflow for mixed non-code material such as EPUBs, CSV/TSV files, XLSX workbooks, PPTX decks, transcripts, Slack exports, mailbox files, and calendar exports.

## Quickstart

```bash
swarmvault quickstart ./your-repo
swarmvault quickstart ./whitepaper.pdf --no-serve
swarmvault quickstart ./your-repo --no-serve
swarmvault next
swarmvault demo --no-serve
swarmvault init --obsidian --profile personal-research
swarmvault source add ./exports/customer-call.srt --guide
swarmvault source session file-customer-call-srt-12345678
swarmvault source add https://github.com/karpathy/micrograd
swarmvault ingest ./src --repo-ro

_meta.json

{
  "ownerId": "kn74zxcqv7s16twr0bpw2xtd5d827ean",
  "slug": "swarmvault",
  "version": "3.20.0",
  "publishedAt": 1781263666062
}

references/artifacts.md

# Artifact Reference

SwarmVault is save-first. The files on disk are the product.

## Canonical Inputs

- `swarmvault.schema.md` - vault instructions, naming rules, exclusions, freshness rules
- `raw/sources/` - immutable canonical sources
- `raw/assets/` - localized remote or imported assets
- `state/sources.json` - managed-source registry for recurring directories, public repos, and docs hubs
- `state/sources/<id>/` - managed-source working state such as shallow checkouts and crawl metadata

## Compiled Knowledge

- `wiki/sources/` - source pages
- `wiki/concepts/` and `wiki/entities/` - promoted canonical pages
- `wiki/code/` - parser-backed module pages
- `wiki/projects/` - project rollups
- `wiki/outputs/` - saved query and explore outputs
- `wiki/outputs/source-briefs/` - source-scoped onboarding briefs for managed sources
- `wiki/outputs/source-reviews/` - source-scoped review pages staged through approvals
- `wiki/outputs/source-guides/` - guided source-integration pages that stage broader wiki updates for review
- `wiki/outputs/source-sessions/` - resumable guided-session anchors plus question and answer state
- `wiki/outputs/chat-sessions/` - persisted chat transcripts from `swarmvault chat`
- `wiki/dashboards/` - recent sources, timeline, contradiction, and open-question dashboards
- `wiki/context/` - markdown companions for saved agent context packs
- `wiki/exports/ai/` - static AI handoff export with `llms.txt`, `llms-full.txt`, `graph.jsonld`, `manifest.json`, `ai-readme.md`, and optional per-page siblings
- `wiki/memory/` - task ledger index and markdown task pages
- `wiki/candidates/` - staged concept/entity pages
- `wiki/graph/report.md` - trust and orientation report
- `wiki/graph/*.html` - optional graph export artifacts such as report, standalone viewer, tree, and directed callflow output
- `wiki/graph/share-card.md` - post-ready graph summary generated by compile
- `wiki/graph/share-card.svg` - 1200x630 visual graph share card generated by compile or `swarmvault graph share --svg`
- `wiki/graph/share-kit/` - portable share bundle with markdown, post text, SVG, HTML preview, and JSON metadata generated by compile or `swarmvault graph share --bundle`

## State And Review

- `state/graph.json` - compiled graph artifact
- `state/context-packs/` - JSON context-pack artifacts with citations, token-budget accounting, included items, and omitted items
- `state/chat-sessions/` - structured session state for resumable `swarmvault chat` conversations
- `state/memory/tasks/` - JSON task ledger records with decisions, changed paths, outcomes, and follow-ups
- `state/retrieval/` - local retrieval index, SQLite FTS shard, and manifest
- `state/code-index.json` - repo-aware symbol/import index
- `state/extracts/` - extraction markdown and JSON sidecars for PDF, the full Word family, RTF, OpenDocument, EPUB, CSV/TSV, the full Excel family, the full PowerPoint family, Jupyter notebooks, BibTeX, Org-mode, AsciiDoc, transcript, Slack export, em

references/commands.md

# Command Reference

## Setup

```bash
swarmvault demo --no-serve
swarmvault quickstart ./apps/api
swarmvault quickstart ./docs/manual.pdf --no-serve
swarmvault next
swarmvault quickstart ./apps/api --no-serve
swarmvault init
swarmvault init --obsidian --profile personal-research
swarmvault init --obsidian --profile reader,timeline
swarmvault scan ./apps/api --no-serve
swarmvault scan ./apps/api --no-viz
swarmvault clone https://github.com/owner/repo --branch main --no-viz
swarmvault clone https://github.com/owner/repo --mcp
swarmvault --version
```

## Ingest and Capture

```bash
swarmvault source add https://github.com/karpathy/micrograd
swarmvault source add ./exports/customer-call.srt --guide
swarmvault source session <source-id-or-session-id>
swarmvault source list
swarmvault source reload --all
swarmvault source review <source-id>
swarmvault source guide <source-id>
swarmvault source delete <source-id>
swarmvault ingest <path-or-url>
swarmvault ingest ./customer-call.mp3
swarmvault ingest https://www.youtube.com/watch?v=dQw4w9WgXcQ
swarmvault ingest --video https://example.com/product-demo.mp4
swarmvault ingest <path-or-url> --commit
swarmvault ingest <path-or-url> --guide
swarmvault ingest <directory> --repo-root .
swarmvault add <url-or-doi-or-arxiv-id>
swarmvault inbox import <path>
```

## Compile, Query, Review

```bash
swarmvault compile
swarmvault compile --max-tokens 120000
swarmvault compile --approve
swarmvault diff
swarmvault query "<question>"
swarmvault query "<question>" --commit
swarmvault chat "What should the next agent know?"
swarmvault chat --resume <session-id> "What changed?"
swarmvault chat --list
swarmvault chat --delete <session-id>
swarmvault context build "<goal>" --target ./src --budget 8000
swarmvault context build "<goal>" --target concept:auth --format llms
swarmvault context list
swarmvault context show <context-pack-id>
swarmvault task start "<goal>" --target ./src --agent codex
swarmvault task update <task-id> --decision "Keep the change local-first"
swarmvault task update <task-id> --changed-path packages/engine/src/memory.ts
swarmvault task finish <task-id> --outcome "Task completed" --follow-up "Run release smoke"
swarmvault task resume <task-id> --format llms
swarmvault retrieval status
swarmvault retrieval doctor --repair
swarmvault doctor
swarmvault doctor --repair
swarmvault explore "<question>" --steps 3
swarmvault lint
swarmvault lint --conflicts
swarmvault review list
swarmvault review show <approval-id> --diff
swarmvault review accept <approval-id>
swarmvault candidate list
```

## Graph and Sharing

```bash
swarmvault graph serve
swarmvault graph serve --full
swarmvault graph share --post
swarmvault graph share --svg ./share-card.svg
swarmvault graph share --bundle ./share-kit
swarmvault graph blast ./src/index.ts
swarmvault graph callers "chargeCustomer"
swarmvault graph status ./src
swarmvault check-update ./src
swarmvault graph stats
swarmvault graph cycles
swarmvault graph validate --strict
s

Github ReposUpdated 2h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.