{"id":50884,"date":"2026-03-12T20:00:00","date_gmt":"2026-03-12T13:00:00","guid":{"rendered":"https:\/\/thaipropertynews.com\/feeds\/?p=50884"},"modified":"2026-03-12T20:00:00","modified_gmt":"2026-03-12T13:00:00","slug":"zilliz-open-sources-memsearch-giving-ai-agents-persistent-human-readable-memory","status":"publish","type":"post","link":"https:\/\/thaipropertynews.com\/feeds\/?p=50884","title":{"rendered":"Zilliz Open-Sources Memsearch, Giving AI Agents Persistent, Human-Readable Memory"},"content":{"rendered":"<table border=\"0\" cellspacing=\"10\" cellpadding=\"5\" align=\"right\">\n<tbody>\n<tr>\n<td><img decoding=\"async\" src=\"https:\/\/mma.prnasia.com\/media2\/2713871\/zilliz_milvus_Logo.jpg?p=medium600\" border=\"0\" alt=\"\" title=\"logo\" hspace=\"0\" vspace=\"0\" width=\"118\"\/><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><i>New open-source library lets developers give any AI agent long-term memory that humans can read, edit, and trust\u2014extracted from OpenClaw&#8217;s viral memory system and powered by the Milvus vector database.<\/i><\/p>\n<p><span class=\"legendSpanClass\"><span class=\"xn-location\">REDWOOD CITY, Calif.<\/span><\/span>, <span class=\"legendSpanClass\"><span class=\"xn-chron\">March 12, 2026<\/span><\/span> \/PRNewswire\/ &#8212;\u00a0<a href=\"https:\/\/zilliz.com\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Zilliz<\/a>, the company behind <a href=\"https:\/\/milvus.io\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Milvus<\/a>, the world&#8217;s most widely adopted open-source <a href=\"https:\/\/zilliz.com\/learn\/what-is-vector-database?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">vector database<\/a>, today announced the open-source release of <a href=\"https:\/\/github.com\/zilliztech\/memsearch?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">memsearch<\/a>, a lightweight library that gives AI agents persistent, long-term memory across conversations. Available today under the <span class=\"xn-org\">MIT<\/span> license, memsearch was engineered by Zilliz&#8217;s team by extracting and rebuilding the memory subsystem originally developed for <a href=\"https:\/\/milvus.io\/blog\/openclaw-formerly-clawdbot-moltbot-explained-a-complete-guide-to-the-autonomous-ai-agent.md\" target=\"_blank\" rel=\"nofollow\">OpenClaw<\/a>\u2014the autonomous AI agent that captured 189,000+ GitHub stars in under two weeks\u2014turning it into a reusable, standalone tool any developer can adopt today.<\/p>\n<div class=\"PRN_ImbeddedAssetReference\">\n<\/div>\n<p>The AI agent ecosystem has a memory problem. When a conversation ends, most agents forget everything\u2014context, preferences, prior decisions\u2014forcing users to repeat themselves session after session. Existing solutions that attempt to address this typically store information in opaque, proprietary formats that only the AI can access, leaving developers unable to inspect, correct, or migrate what their agent has learned.<\/p>\n<p>Memsearch takes a fundamentally different approach. Rather than abstracting memory behind an inaccessible black box, it stores all agent memories as plain-text files\u2014readable, editable, and version-controllable by any developer. Milvus then automatically indexes those files, enabling fast, accurate semantic retrieval at scale.<\/p>\n<p><i>&#8220;Memory is the missing layer in the AI agent stack. Developers deserve to know what their agents remember, fix it when it&#8217;s wrong, and carry it forward without lock-in. memsearch is our answer to that\u2014transparent, portable, and built on the open-source foundation the community already trusts.&#8221;<\/i> <b>\u2014 <span class=\"xn-person\">Jiang Chen<\/span>, Head of Developer Relations, Zilliz<\/b><\/p>\n<p><b>Why\u00a0Memsearch \u2014 Key Benefits for Developers<\/b><\/p>\n<ul type=\"disc\">\n<li><b>Full transparency:<\/b> Every memory is a human-readable text file. Developers can see exactly what their AI agent knows\u2014no special tools, no proprietary dashboards required.<\/li>\n<li><b>Easy correction:<\/b> Fix a bad memory by editing a file. memsearch detects the change automatically\u2014no retraining, no data pipelines, no manual re-ingestion.<\/li>\n<li><b>Team collaboration:<\/b> Because memory lives in standard files, teams can apply familiar version-control workflows\u2014Git commits, pull request reviews, rollbacks\u2014to what their agent remembers.<\/li>\n<li><b>True portability:<\/b> Switching machines, AI models, or cloud providers requires nothing more than copying files. There is no proprietary export step, no migration script, no vendor permission.<\/li>\n<li><b>Plug-and-play integration:<\/b> memsearch works with any AI agent framework. A single command installs it; no infrastructure changes are required.<\/li>\n<\/ul>\n<p><b>Dedicated Plugin for <span class=\"xn-person\">Claude Code<\/span><\/b><\/p>\n<p>Alongside memsearch, Zilliz is releasing the <a href=\"https:\/\/zilliztech.github.io\/memsearch\/claude-plugin\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">memsearch ccplugin<\/a>\u2014a purpose-built persistent memory plugin for <span class=\"xn-person\">Claude Code<\/span>, Anthropic&#8217;s AI-powered coding assistant.<\/p>\n<p>AI-assisted coding sessions accumulate significant context over time: architectural decisions, debugging history, project conventions, and team preferences. Today, that context evaporates when a session ends. The memsearch ccplugin automatically captures session summaries and injects relevant prior context at the start of every new session\u2014so <span class=\"xn-person\">Claude Code<\/span> arrives informed, not amnesiac.<\/p>\n<p><b>Installation takes a single command.<\/b><\/p>\n<p>For full technical detail on the <a href=\"https:\/\/milvus.io\/blog\/we-extracted-openclaws-memory-system-and-opensourced-it-memsearch.md?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">memsearch architecture<\/a> and the <a href=\"https:\/\/milvus.io\/blog\/adding-persistent-memory-to-claude-code-with-the-lightweight-memsearch-plugin.md?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\"><span class=\"xn-person\">Claude Code<\/span> plugin<\/a>, see the Zilliz engineering blog.<\/p>\n<p><b>Availability<\/b><\/p>\n<p>memsearch is free and open source (<span class=\"xn-org\">MIT<\/span> license) and is available immediately.<\/p>\n<ul type=\"disc\">\n<li>GitHub: github.com\/zilliztech\/memsearch<\/li>\n<li>Documentation: zilliztech.github.io\/memsearch<\/li>\n<li><span class=\"xn-person\">Claude Code Plugin<\/span>: zilliztech.github.io\/memsearch\/claude-plugin<\/li>\n<\/ul>\n<p><b>About\u00a0Zilliz<\/b><\/p>\n<p>Zilliz is the company behind <a href=\"https:\/\/milvus.io\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Milvus<\/a>, the world&#8217;s most widely adopted open-source vector database. <a href=\"https:\/\/zilliz.com\/cloud?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Zilliz Cloud<\/a> brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.<\/p>\n<p>Zilliz is built to make AI not just possible\u2014but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.<\/p>\n<p>Headquartered in Redwood Shores, <span class=\"xn-location\">California<\/span>, Zilliz is backed by leading investors, including Aramco&#8217;s Prosperity 7 Ventures, Temasek&#8217;s Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at\u00a0 <a href=\"https:\/\/zilliz.com\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Zilliz.com<\/a>.<\/p>","protected":false},"excerpt":{"rendered":"<p><!-- wp:html --><\/p>\n<table border=\"0\" cellspacing=\"10\" cellpadding=\"5\" align=\"right\">\n<tbody>\n<tr>\n<td><img decoding=\"async\" src=\"https:\/\/mma.prnasia.com\/media2\/2713871\/zilliz_milvus_Logo.jpg?p=medium600\" border=\"0\" alt=\"\" title=\"logo\" hspace=\"0\" vspace=\"0\" width=\"118\"\/><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><i>New open-source library lets developers give any AI agent long-term memory that humans can read, edit, and trust\u2014extracted from OpenClaw&#8217;s viral memory system and powered by the Milvus vector database.<\/i><\/p>\n<p><span class=\"legendSpanClass\"><span class=\"xn-location\">REDWOOD CITY, Calif.<\/span><\/span>, <span class=\"legendSpanClass\"><span class=\"xn-chron\">March 12, 2026<\/span><\/span> \/PRNewswire\/ &#8212;\u00a0<a href=\"https:\/\/zilliz.com\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Zilliz<\/a>, the company behind <a href=\"https:\/\/milvus.io\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Milvus<\/a>, the world&#8217;s most widely adopted open-source <a href=\"https:\/\/zilliz.com\/learn\/what-is-vector-database?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">vector database<\/a>, today announced the open-source release of <a href=\"https:\/\/github.com\/zilliztech\/memsearch?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">memsearch<\/a>, a lightweight library that gives AI agents persistent, long-term memory across conversations. Available today under the <span class=\"xn-org\">MIT<\/span> license, memsearch was engineered by Zilliz&#8217;s team by extracting and rebuilding the memory subsystem originally developed for <a href=\"https:\/\/milvus.io\/blog\/openclaw-formerly-clawdbot-moltbot-explained-a-complete-guide-to-the-autonomous-ai-agent.md\" target=\"_blank\" rel=\"nofollow\">OpenClaw<\/a>\u2014the autonomous AI agent that captured 189,000+ GitHub stars in under two weeks\u2014turning it into a reusable, standalone tool any developer can adopt today.<\/p>\n<div class=\"PRN_ImbeddedAssetReference\">\n<\/div>\n<p>The AI agent ecosystem has a memory problem. When a conversation ends, most agents forget everything\u2014context, preferences, prior decisions\u2014forcing users to repeat themselves session after session. Existing solutions that attempt to address this typically store information in opaque, proprietary formats that only the AI can access, leaving developers unable to inspect, correct, or migrate what their agent has learned.<\/p>\n<p>Memsearch takes a fundamentally different approach. Rather than abstracting memory behind an inaccessible black box, it stores all agent memories as plain-text files\u2014readable, editable, and version-controllable by any developer. Milvus then automatically indexes those files, enabling fast, accurate semantic retrieval at scale.<\/p>\n<p><i>&#8220;Memory is the missing layer in the AI agent stack. Developers deserve to know what their agents remember, fix it when it&#8217;s wrong, and carry it forward without lock-in. memsearch is our answer to that\u2014transparent, portable, and built on the open-source foundation the community already trusts.&#8221;<\/i> <b>\u2014 <span class=\"xn-person\">Jiang Chen<\/span>, Head of Developer Relations, Zilliz<\/b><\/p>\n<p><b>Why\u00a0Memsearch \u2014 Key Benefits for Developers<\/b><\/p>\n<ul type=\"disc\">\n<li><b>Full transparency:<\/b> Every memory is a human-readable text file. Developers can see exactly what their AI agent knows\u2014no special tools, no proprietary dashboards required.<\/li>\n<li><b>Easy correction:<\/b> Fix a bad memory by editing a file. memsearch detects the change automatically\u2014no retraining, no data pipelines, no manual re-ingestion.<\/li>\n<li><b>Team collaboration:<\/b> Because memory lives in standard files, teams can apply familiar version-control workflows\u2014Git commits, pull request reviews, rollbacks\u2014to what their agent remembers.<\/li>\n<li><b>True portability:<\/b> Switching machines, AI models, or cloud providers requires nothing more than copying files. There is no proprietary export step, no migration script, no vendor permission.<\/li>\n<li><b>Plug-and-play integration:<\/b> memsearch works with any AI agent framework. A single command installs it; no infrastructure changes are required.<\/li>\n<\/ul>\n<p><b>Dedicated Plugin for <span class=\"xn-person\">Claude Code<\/span><\/b><\/p>\n<p>Alongside memsearch, Zilliz is releasing the <a href=\"https:\/\/zilliztech.github.io\/memsearch\/claude-plugin\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">memsearch ccplugin<\/a>\u2014a purpose-built persistent memory plugin for <span class=\"xn-person\">Claude Code<\/span>, Anthropic&#8217;s AI-powered coding assistant.<\/p>\n<p>AI-assisted coding sessions accumulate significant context over time: architectural decisions, debugging history, project conventions, and team preferences. Today, that context evaporates when a session ends. The memsearch ccplugin automatically captures session summaries and injects relevant prior context at the start of every new session\u2014so <span class=\"xn-person\">Claude Code<\/span> arrives informed, not amnesiac.<\/p>\n<p><b>Installation takes a single command.<\/b><\/p>\n<p>For full technical detail on the <a href=\"https:\/\/milvus.io\/blog\/we-extracted-openclaws-memory-system-and-opensourced-it-memsearch.md?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">memsearch architecture<\/a> and the <a href=\"https:\/\/milvus.io\/blog\/adding-persistent-memory-to-claude-code-with-the-lightweight-memsearch-plugin.md?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\"><span class=\"xn-person\">Claude Code<\/span> plugin<\/a>, see the Zilliz engineering blog.<\/p>\n<p><b>Availability<\/b><\/p>\n<p>memsearch is free and open source (<span class=\"xn-org\">MIT<\/span> license) and is available immediately.<\/p>\n<ul type=\"disc\">\n<li>GitHub: github.com\/zilliztech\/memsearch<\/li>\n<li>Documentation: zilliztech.github.io\/memsearch<\/li>\n<li><span class=\"xn-person\">Claude Code Plugin<\/span>: zilliztech.github.io\/memsearch\/claude-plugin<\/li>\n<\/ul>\n<p><b>About\u00a0Zilliz<\/b><\/p>\n<p>Zilliz is the company behind <a href=\"https:\/\/milvus.io\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Milvus<\/a>, the world&#8217;s most widely adopted open-source vector database. <a href=\"https:\/\/zilliz.com\/cloud?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Zilliz Cloud<\/a> brings that performance to production with a fully managed, cloud-native platform built for scalable, low-latency vector search and hybrid retrieval. It supports billion-scale workloads with sub-10ms latency, auto-scaling, and optimized indexes for GenAI use cases like semantic search and RAG.<\/p>\n<p>Zilliz is built to make AI not just possible\u2014but practical. With a focus on performance and cost-efficiency, it helps engineering teams move from prototype to production without overprovisioning or complex infrastructure. Over 10,000 organizations worldwide rely on Zilliz to build intelligent applications at scale.<\/p>\n<p>Headquartered in Redwood Shores, <span class=\"xn-location\">California<\/span>, Zilliz is backed by leading investors, including Aramco&#8217;s Prosperity 7 Ventures, Temasek&#8217;s Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, Trustbridge Partners, and others. Learn more at\u00a0 <a href=\"https:\/\/zilliz.com\/?utm_source=vendor&amp;utm_medium=referral&amp;utm_campaign=seonews-Memsearch-Plugin\" target=\"_blank\" rel=\"nofollow\">Zilliz.com<\/a>.<\/p>\n<p><!-- \/wp:html --><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"rop_custom_images_group":[],"rop_custom_messages_group":[],"rop_publish_now":"initial","rop_publish_now_accounts":[],"rop_publish_now_history":[],"rop_publish_now_status":"pending","footnotes":""},"categories":[1],"tags":[],"class_list":["post-50884","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts\/50884","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=50884"}],"version-history":[{"count":0,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=\/wp\/v2\/posts\/50884\/revisions"}],"wp:attachment":[{"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=50884"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=50884"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/thaipropertynews.com\/feeds\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=50884"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}