ov_dream
installsforks
How to install ov_dream?
volcengine/openviking/ov_dream
$npx -y skills add volcengine/OpenViking --skill ov_dreamUse when the user explicitly types ov dream or ov recall <query> and the request should be routed to the OpenViking sync/recall CLI instead of handled as normal chat.
SKILL.md
| 1 | # OV Dream |
| 2 | |
| 3 | Use this skill for manual OpenViking sync and recall without occupying the OpenClaw `contextEngine` slot. |
| 4 | |
| 5 | ## When To Use |
| 6 | |
| 7 | Use this skill when the user message begins with one of these exact prefixes: |
| 8 | |
| 9 | - `ov dream` |
| 10 | - `ov recall ` |
| 11 | |
| 12 | Do not treat those messages as normal conversation. They are explicit operator commands. |
| 13 | |
| 14 | ## Commands |
| 15 | |
| 16 | - `ov dream` |
| 17 | Manual sync. Read OpenClaw's `sessions.json`, sync eligible chat transcripts to OpenViking, then commit each session when new messages exist. |
| 18 | |
| 19 | - `ov recall <query>` |
| 20 | Manual recall. Search OpenViking under the default user root URI, `viking://user/default`. |
| 21 | |
| 22 | ## Sync Behavior |
| 23 | |
| 24 | Trigger when the user message is exactly `ov dream`. |
| 25 | |
| 26 | Execution flow: |
| 27 | |
| 28 | 1. Run: |
| 29 | |
| 30 | ```bash |
| 31 | python3 scripts/dream.py dream |
| 32 | ``` |
| 33 | |
| 34 | 2. Return the sync summary. |
| 35 | |
| 36 | The sync command reads OpenClaw session metadata from `~/.openclaw/agents/main/sessions/sessions.json` when available. It syncs chat-like session keys such as `agent:main:main`, `:direct:`, `:channel:`, `:group:`, and `:room:`. |
| 37 | |
| 38 | It must not sync explicitly non-chat sessions, including keys containing `:cron:`, `:heartbeat`, `:subagent:`, `:acp:`, or `:hook:`. |
| 39 | |
| 40 | Each source session keeps an independent sync cursor in `~/.openclaw/memory/ov_dream_sync.json`. |
| 41 | |
| 42 | ## Recall Behavior |
| 43 | |
| 44 | Trigger when the user message starts with `ov recall `. |
| 45 | |
| 46 | This is a hard routing rule for this skill: |
| 47 | |
| 48 | - If the user says `ov recall <query>`, do not answer from general reasoning. |
| 49 | - Do not summarize what recall would do. |
| 50 | - Do not ask whether recall should be run. |
| 51 | - Immediately execute the local recall command. |
| 52 | |
| 53 | Execution flow: |
| 54 | |
| 55 | 1. Extract everything after `ov recall` as the recall query. |
| 56 | 2. Run: |
| 57 | |
| 58 | ```bash |
| 59 | python3 scripts/dream.py recall "<query>" |
| 60 | ``` |
| 61 | |
| 62 | 3. Return the relevant memory rows to the user. |
| 63 | 4. If no memories are found, return `No memories found.` |
| 64 | |
| 65 | Rules: |
| 66 | |
| 67 | - Treat `ov recall ...` as a manual recall request, not a normal conversation turn. |
| 68 | - Treat the command text after `ov recall` as the exact recall query. |
| 69 | - Run the recall command from the skill directory so `scripts/dream.py` resolves correctly. |
| 70 | - Do not auto-inject retrieved memories into prompt context. |
| 71 | - Do not trigger `ov dream` unless the user separately asks for sync. |
| 72 | - If the query is empty, ask the user for the recall query instead of guessing. |
| 73 | |
| 74 | ## Notes |
| 75 | |
| 76 | - This skill is manual-only in the first version. |
| 77 | - It does not auto-inject recall into prompts. |
| 78 | - It does not replace the OpenViking context-engine plugin. |
| 79 | - Disk-based sync is for recently recorded chat transcripts. It is not a precise "currently running sessions" detector. |
| 80 | - For OpenViking serverless, configure `OPENVIKING_BASE_URL`, `OPENVIKING_API_KEY`, and optionally `OPENVIKING_AUTH_MODE=serverless`. The CLI will use Bearer auth and the serverless session message format automatically. |
People who liked this also viewed
6 picksType
- azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026
- just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026
- firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 2026
- firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 2026
- firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 2026
- firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 2026
