parallel-memory

作者: parallel-web

在可能有用时,回忆过去的Parallel Task、Monitor和FindAll运行记录;在接到请求时,清除运行记录或清空记忆。

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

来自 parallel-web 的更多技能

parallel-monitor
parallel-web
持续按固定频率追踪网页变化。当用户要求“监控”、“追踪变化”、“关注”或“提醒我”某内容时使用…
migrate-to-parallel
parallel-web
将Exa、Tavily、Perplexity或Firecrawl的网页数据集成完全迁移到相应的Parallel产品,同时保持应用程序行为不变。使用…
parallel-data-enrichment
parallel-web
批量丰富公司、人员或产品数据,通过网页来源字段(如CEO姓名、融资信息、联系方式)进行补充。支持内联JSON数据或CSV文件输入,并将丰富后的结果输出为CSV。异步运行,通过监控URL和轮询命令跟踪进度。需要parallel-cli工具和互联网访问,可处理大型数据集并配置超时时间。通过自然语言意图描述(例如“CEO姓名和成立年份”)支持灵活的字段请求。
parallel-deep-research
parallel-web
针对复杂主题的详尽研究,支持可配置的深度、延迟与成本权衡。三个处理层级(pro-fast、ultra-fast、ultra)耗时从30秒到25分钟不等,成本按基准的1倍至3倍递增。异步执行与轮询机制:即时启动研究,通过URL监控进度,就绪后获取结果且不阻塞流程。输出格式化的Markdown报告与JSON元数据;执行摘要打印至标准输出以便快速概览。专为显式...
parallel-findall
parallel-web
发现与自然语言描述匹配的实体(公司、人物、产品等)。当用户要求“找出所有X”或“列出每个Y,这些Y……”时使用。
parallel-web-extract
parallel-web
从多个URL并行提取内容,高效利用令牌。通过单条命令处理网页、文章、PDF及JavaScript密集型网站。在分叉上下文中运行,相比内置WebFetch减少令牌开销。支持批量提取多个URL,可设置可选聚焦目标。需安装parallel-cli并完成认证;提取内容以Markdown格式输出至本地文件,便于后续查询。
parallel-web-search
parallel-web
快速网络搜索,用于获取当前信息、进行研究及事实核查。可执行单一目标查询或并行多个关键词搜索,返回最多10条结果,包含摘要和元数据。支持通过--after-date进行时效性过滤,以及使用--include-domains进行特定域名搜索。输出结构化JSON,包含标题、URL、发布日期和摘要,便于解析和后续查询。要求每条声明使用Markdown格式的内联引用...
setup
parallel-web
设置 Parallel 插件(安装 CLI)