parallel-memory

Recall past Parallel Task, Monitor, and FindAll runs when they may help; evict runs or clear memory when asked.

npx skills add https://github.com/parallel-web/parallel-agent-skills --skill parallel-memory

Parallel Memory

Action: $ARGUMENTS

Requires parallel-cli >=0.8.1. If the installed version is older, or parallel-cli memory --help fails with no such command or similar, tell the user to update parallel-cli, then retry.

When to use

  • Inspect memory only when prior Parallel work may help fulfill the request or the user asks to retrieve, evict, or clear it.
  • Memory results are excerpts from past runs; fetch the source run for full records, and launch a fresh run when current information is required.

Choose the operation

User intentOperation
Recall prior work about a topicRetrieve with a concise query
Show recent past runsRetrieve without query
Remove one saved Task, Monitor, or FindAll sourceEvict by exact kind and id
Permanently remove all entries from your personal MemoryClear memory
Turn memory offDirect the user to account settings; do not clear as a substitute

Use the CLI

Use parallel-cli memory for retrieve, evict, and clear operations.

  • If memory is not eligible, report the returned reason; it distinguishes rollout, organization settings, account opt-in, and key eligibility.
  • On a key-eligibility error, tell the user to reauthenticate.

Retrieve memory

Form a short semantic query that describes the prior work to find. Apply filters when they help. Empty results is a successful retrieval with no matches, not an error.

  • Set kind to task, monitor, or findall when it clearly narrows the retrieval.
  • Set since for an explicit timestamp boundary (RFC 3339, e.g. 2026-08-01T00:00:00Z).
  • Omit query when retrieving recent memories rather than a topic.

Retrieve by query:

parallel-cli memory retrieve \
  --query "serverless inference vendors"

For recent memories:

parallel-cli memory retrieve \
  --limit 5

Use results

Available fields vary by kind:

  • task: use id, updated_at, input_excerpt, and output_excerpt.

  • monitor: use the monitor id, status, query excerpt, and matching event IDs, timestamps, and excerpts.

  • findall: use id, updated_at, objective excerpt, and matched_count.

  • Fetch the original Task result, Monitor events, or FindAll result when exact output, entities, citations, or provenance matter.

  • Summarize the useful findings and unresolved questions.

  • Lead with what the prior work established, then list the contributing saved runs with kind, ID, and timestamp.

  • Distinguish recalled information from any fresh verification.

  • Parallel runs do not consult Memory. If recalled information may be useful, include the relevant details in the new run's input.

Expect ingestion to be asynchronous. Do not promise that a newly completed run will be immediately retrievable.

Evict or clear memory

Evict a single run from your personal Memory, or clear it entirely. These do not delete the underlying Parallel runs. Ask for confirmation before clearing unless the user already asked for it.

parallel-cli memory evict \
  --kind task \
  --id "trun_example"
parallel-cli memory clear \
  --confirm-clear

More skills from parallel-web

parallel-monitor
parallel-web
Continuously track the web for changes on a recurring cadence. Use when the user asks to 'monitor', 'track changes to', 'watch', or 'alert me when' something…
migrate-to-parallel
parallel-web
Migrate Exa, Tavily, Perplexity, or Firecrawl web-data integrations completely to the appropriate Parallel products while preserving application behavior. Use…
parallel-data-enrichment
parallel-web
Bulk enrichment of company, people, or product data with web-sourced fields like CEO names, funding, and contact info. Accepts inline JSON data or CSV files; outputs enriched results to CSV Runs asynchronously with progress tracking via monitoring URL and polling commands Requires parallel-cli tool and internet access; handles large datasets with configurable timeouts Supports flexible field requests through natural language intent descriptions (e.g., "CEO name and founding year")
parallel-deep-research
parallel-web
Exhaustive research with configurable depth, latency, and cost trade-offs for complex topics. Three processor tiers (pro-fast, ultra-fast, ultra) ranging from 30 seconds to 25 minutes, with cost scaling from 1x to 3x baseline Asynchronous execution with polling: kick off research instantly, monitor progress via URL, retrieve results when ready without blocking Outputs formatted markdown report and JSON metadata; executive summary printed to stdout for quick overview Designed for explicit...
parallel-findall
parallel-web
Discover entities (companies, people, products, etc.) matching a natural-language description. Use when the user asks to 'find all X' or 'list every Y that…' —…
parallel-web-extract
parallel-web
Extract content from multiple URLs in parallel, token-efficiently. Handles webpages, articles, PDFs, and JavaScript-heavy sites with a single command Runs in a forked context to minimize token overhead compared to built-in WebFetch Supports batch extraction of multiple URLs with optional focus objectives Requires parallel-cli installation and authentication; outputs extracted content as markdown to a local file for follow-up queries
parallel-web-search
parallel-web
Fast web search for current information, research, and fact-finding across the internet. Executes single objective-based queries or multiple keyword searches in parallel, returning up to 10 results with excerpts and metadata Supports time-sensitive filtering via --after-date and domain-specific searches with --include-domains Outputs structured JSON with titles, URLs, publish dates, and excerpts for easy parsing and follow-up queries Requires inline citations for every claim using markdown...
setup
parallel-web
Set up the Parallel plugin (install CLI)