Perplexity 推出 pplx:單一二進位 CLI,將搜尋 API 帶入終端機,專為程式碼代理設計
重點摘要
Perplexity 發布了 pplx,這是其搜尋 API 的官方命令列客戶端。該工具會回傳有基礎依據的搜尋結果與萃取後的頁面文字,全部以 JSON 格式呈現。根據官方文件,它同時面向人類與程式碼代理,但並非聊天客戶端:沒有對話模式、沒有模型選擇,也不提供合成答案。pplx 僅提供兩個操作介面:pplx search web 執行即時網路搜尋,pplx content fetch 則擷取 URL 並回傳清理後的頁面文字。其輸出合約定義明確:成功時退出碼為 0,並在標準輸出中輸出單一 JSON 物件;失敗時退出碼為 1,標準輸出則為空。
Perplexity has released pplx, an official command line client for its Search API.The tool returns grounded search results and extracted page text, all as JSON.According to its docs, it targets humans and coding agents equally.It is not a chat client.
There is no conversational mode, no model selection and no synthesized answer.Two surfaces, one output contract The tool exposes exactly two working surfaces.pplx search web runs a live web search.pplx content fetch pulls a URL and returns cleaned page text.
The contract around them is the interesting part.Per the official pplx-cli Agent Skill, success means exit code 0 and exactly one JSON object on stdout.Search returns {hits: [{url, title, domain, snippet, ...}], total, saved_to?}.Every failure exits 1 with an empty stdout.
One JSON error object goes to stderr, shaped {"error":{"code","message","command","hint"?}}.Documented codes include AUTHENTICATION, UNKNOWN_ARGUMENT, ARGUMENT_ERROR and BAD_REQUEST.The skill notes that list is not exhaustive, so callers should branch on error.code.(function(){ var f=document.
getElementById("mtpPplxExplainerFrame"); window.addEventListener("message",function(e){ if(!e.data||e.data.pplxEmbed!=="pplx-explainer")return; var h=parseInt(e.data.height,10); if(h>0)f.style.
height=h+"px"; }); })(); #mtp-pplx-explainer hr,#mtp-pplx-explainer p:empty,#mtp-pplx-explainer del,#mtp-pplx-explainer s{display:none!
important} Install path and platform support Installation is a single shell command that pipes a script into sh: Copy CodeCopiedUse a different Browsercurl -fsSL https://github.com/perplexityai/perplexity-cli/releases/latest/download/install.sh | sh Reading install.sh shows what it actually does.
It downloads manifest.json from the latest release and extracts the tag and version.It then pins every remaining download to that tag, explicitly to avoid racing a concurrent publish.It fetches SHA256SUMS and the platform binary, verifies the checksum, and installs to ~/.local/bin/pplx.
No sudo is required.A receipt is written to ~/.config/pplx/pplx-receipt.json, but only after the installed binary runs successfully.Platform coverage is limited to three targets: macOS on Apple Silicon, Linux x86_64 and Linux arm64.Anything else exits with an error.
There is no Windows build and no Intel macOS build.Context-window economics are a first-class design concern The most agent-specific feature is token budgeting.--output-dir writes the full result set to a JSON file.--stdout-preview[=<CHARS>] truncates long string fields in stdout, adding ...
<truncated> markers.The skill is blunt about the trap: --stdout-preview is a no-op without a save directory.It truncates only when the result is also saved via --output-dir or $PPLX_OUTPUT_DIR.Used alone it returns full-size output, and hits can be multiple KB each.
Saved search results land at {dir}/web/{rand}.json and fetches at {dir}/fetch/{rand}.json.Files are written only after a successful request.PPLX_OUTPUT_DIR sets a workspace default so the flag need not be repeated.For content fetch, the skill adds a correctness check rather than a cost one.
Verify error and is_paywall in the output before trusting content.--html adds a raw_html field fetched live via crawler, and --no-cache forces a live fetch.(function(){ var f=document.getElementById("mtpPplxDeployFrame"); window.addEventListener("message",function(e){ if(!e.data||e.data.pplxEmbed!
=="pplx-deploy")return; var h=parseInt(e.data.height,10); if(h>0)f.style.height=h+"px"; }); })(); #mtp-pplx-deploy hr,#mtp-pplx-deploy p:empty,#mtp-pplx-deploy del,#mtp-pplx-deploy s{display:none!
important} Key Takeaways pplx is a single verified binary exposing two commands: pplx search web and pplx content fetch.Success is exit 0 plus one JSON object on stdout; failures put one JSON error object on stderr.pplx auth login is TTY-only, so agents and CI must export PERPLEXITY_API_KEY.
--stdout-preview only truncates when paired with --output-dir or $PPLX_OUTPUT_DIR.Search API billing is $5.00 per 1,000 requests, capped at 50 QPS on every usage tier.Sources: perplexityai/perplexity-cli, pplx-cli SKILL.
md, api-platform-developers, Perplexity API pricing, Rate limits and usage tiers, and Search API quickstart The post Perplexity Releases pplx, a Single-Binary CLI That Puts Its Search API in the Terminal for Coding Agents appeared first on MarkTechPost.
Related
相關文章

當 human in the loop 變成“閉著眼睛點確認”,企業Agent 安全還能靠誰?
專家指出,AI Agent 從內容安全轉向行為安全,提示詞注入、工具濫用與過度授權成為主要風險。企業應建立可視、可管、可追溯的安全基線,並對工具權限進行最小化與臨時化管理,避免 human in the loop 淪為形式。安全防護需從靜態入口轉向動態行為約束,以因應 Agent 自主執行帶來的全新挑戰。

開源Agent框架刷爆ARC-AGI-3,「自我改進」的RLM harness引爭議
一套開源Agent框架在ARC-AGI-3基準測試中創下超過85%的正確率,大幅領先其他解決方案,其核心是名為「RLM harness」的自我改進機制。然而,該方法引發學術爭議,部分研究者批評它透過反覆試錯「鑽漏洞」,不符合ARC-AGI評測一次性推理的精神。這場討論促使AI社群重新審視評測標準,並可能影響未來ARC-AGI版本的設計方向。

騰訊是在“賽馬”,還是在打造 “Agent工廠”?
騰訊內部正在探討其發展策略究竟是「賽馬」機制還是打造「Agent工廠」。相關討論聚焦於公司如何平衡內部競爭與統一平台建設。目前站內已移除相關混雜文字,保留原始主題供讀者參考。
ChinaJoy 2026 AI遊戲規模化落地,邊緣雲與API安全重構產業底層邏輯
2026年ChinaJoy展館,“與AI同遊”的主題隨處可見。行業調查顯示,僅有21%的企業擁有完整的API資產清單,大量後臺AI接口仍在無人監控的狀態下裸奔。合規與安全也同步下沉。算力下沉還不夠,API安全必須同步前移邊緣雲解決了體驗問題,但AI交互入口的安全,同樣需要前置到邊緣。算力與安全,缺一不可Akamai的判斷很明確:遊戲AI轉型不能割裂算力與安全。這也是遊戲廠商規模化落地AI智能體、構建AI原生遊戲的標準化底層方案。

openJiuwen發佈業界首個企業級分佈式蜂群架構,聯合郵儲成功落地金融生產環境
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.

螞蟻集團開源Avernet,讓人與智能體像組織一樣高效協作
**螞蟻集團開源Avernet:打造人與智能體高效協作的“組織級”基礎設施** **來源:量子位** **2026-08-07 11:08:51** 近日,螞蟻集團正式宣佈開源多智能體協作基礎設施Avernet,其社區版本已同步上線。作為業界首個聚焦於“組織級協作”的智能體基礎設施,Avernet的首個版本重點開放了智能體協作網絡能力,旨在支持不同智能體之間的發現、共識達成、跨團隊協作與治理,為人工智能從“單點智能”走向“系統智能”提供關鍵支撐。