[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-redis-redis-semantic-cache":3,"mdc--2qypk2-key":38,"related-repo-redis-redis-semantic-cache":586,"related-org-redis-redis-semantic-cache":702},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":33,"sourceUrl":36,"mdContent":37},"redis-semantic-cache","implement semantic caching with Redis","Redis LangCache guidance for semantic caching of LLM responses on Redis Cloud — calling search\u002Fset via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom attributes. Use when caching LLM completions or RAG answers to cut API cost and latency, building a cache-aside layer in front of OpenAI \u002F Anthropic \u002F etc., tuning hit rate vs precision, or splitting one app's LLM workloads into multiple LangCache caches.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"redis","Redis","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fredis.png",[12,16,19,20,23],{"name":13,"slug":14,"type":15},"LLM","llm","tag",{"name":17,"slug":18,"type":15},"Search","search",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"AI Infrastructure","ai-infrastructure",{"name":24,"slug":25,"type":15},"Caching","caching",92,"https:\u002F\u002Fgithub.com\u002Fredis\u002Fagent-skills","2026-05-27T07:19:43.897283","MIT",21,[32,8],"agent-skills",{"repoUrl":27,"stars":26,"forks":30,"topics":34,"description":35},[32,8],"Redis' official collection of agent skills","https:\u002F\u002Fgithub.com\u002Fredis\u002Fagent-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fredis-semantic-cache","---\nname: redis-semantic-cache\ndescription: Redis LangCache guidance for semantic caching of LLM responses on Redis Cloud — calling search\u002Fset via the SDK or REST API, tuning the similarity threshold, separating caches per task type, and filtering with custom attributes. Use when caching LLM completions or RAG answers to cut API cost and latency, building a cache-aside layer in front of OpenAI \u002F Anthropic \u002F etc., tuning hit rate vs precision, or splitting one app's LLM workloads into multiple LangCache caches.\nlicense: MIT\nmetadata:\n  author: Redis, Inc.\n  version: \"0.1.0\"\n---\n\n# Redis Semantic Cache\n\nSemantic caching for LLM responses with Redis Cloud's LangCache service. Stores prompts as embeddings; subsequent semantically-similar prompts return the cached response without re-calling the model.\n\n> LangCache is currently in **preview** on Redis Cloud. Features and behavior may change.\n\n## When to apply\n\n- Wrapping an LLM call (OpenAI, Anthropic, etc.) with a cache layer to cut cost and latency.\n- Caching RAG answers, classification outputs, or any deterministic LLM workload.\n- Tuning the precision\u002Fhit-rate trade-off for a semantic cache.\n- Splitting one application's LLM workloads across multiple cache instances.\n\n## 1. The cache-aside flow\n\nLangCache fits in front of any LLM call as a standard cache-aside pattern:\n\n1. Send the user's prompt to LangCache's `search`.\n2. **Cache hit** — return the stored response directly.\n3. **Cache miss** — call the LLM, then `set` the response so future similar prompts hit.\n\n```python\nfrom langcache import LangCache\nimport os\n\nlang_cache = LangCache(\n    server_url=f\"https:\u002F\u002F{os.getenv('HOST')}\",\n    cache_id=os.getenv(\"CACHE_ID\"),\n    api_key=os.getenv(\"API_KEY\"),\n)\n\nresult = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.9)\nif result:\n    response = result[0][\"response\"]\nelse:\n    response = llm.generate(\"What is Redis?\")\n    lang_cache.set(prompt=\"What is Redis?\", response=response)\n```\n\nThe same operations are available via REST (`POST \u002Fv1\u002Fcaches\u002F{cacheId}\u002Fentries\u002Fsearch` and `POST \u002Fv1\u002Fcaches\u002F{cacheId}\u002Fentries`) when an SDK isn't an option.\n\nSee [references\u002Flangcache-usage.md](references\u002Flangcache-usage.md) for full SDK + REST samples and attribute-based storage.\n\n## 2. Tune the similarity threshold\n\nThe threshold controls how close (in embedding cosine distance) a new prompt must be to a cached one to count as a hit. Higher = stricter match, fewer false positives. Lower = more hits, more risk of returning an off-topic answer.\n\n| Threshold | Behavior | Use when |\n|---|---|---|\n| 0.95+ | Near-exact match required | Customer-facing answers where wrong responses are costly |\n| 0.9 | Balanced default | Most workloads — start here |\n| 0.8 | Loose semantic match | Internal tools, exploratory queries, FAQ deduplication |\n\n```python\n# Stricter — fewer false positives\nresult = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.95)\n\n# Looser — higher hit rate\nresult = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.8)\n```\n\nAdjust by watching the actual cache-hit rate and spot-checking that returned answers are still relevant.\n\nSee [references\u002Fbest-practices.md](references\u002Fbest-practices.md).\n\n## 3. Separate caches per task type\n\nDifferent LLM workloads should not share one cache — a \"code question\" prompt is semantically close to other code questions but has nothing to do with a password-reset support query, and crossing them returns garbage.\n\n```python\nsupport_cache = LangCache(server_url=..., cache_id=\"support-cache-id\", api_key=...)\ncode_cache    = LangCache(server_url=..., cache_id=\"code-cache-id\",    api_key=...)\n```\n\nCreate distinct cache IDs in Redis Cloud per task, and route each call to the right one. As a finer-grained alternative, store and search with **custom attributes** (e.g. `{\"category\": \"database\"}`) to keep tasks in the same cache but isolated by attribute filter — useful when the same prompt format spans subtopics.\n\n## References\n\n- [LangCache documentation](https:\u002F\u002Fredis.io\u002Fdocs\u002Flatest\u002Fdevelop\u002Fai\u002Flangcache\u002F)\n",{"data":39,"body":43},{"name":4,"description":6,"license":29,"metadata":40},{"author":41,"version":42},"Redis, Inc.","0.1.0",{"type":44,"children":45},"root",[46,54,60,77,84,109,115,120,165,313,334,347,353,358,445,491,496,506,512,517,540,560,566,580],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","Redis Semantic Cache",{"type":47,"tag":55,"props":56,"children":57},"p",{},[58],{"type":52,"value":59},"Semantic caching for LLM responses with Redis Cloud's LangCache service. Stores prompts as embeddings; subsequent semantically-similar prompts return the cached response without re-calling the model.",{"type":47,"tag":61,"props":62,"children":63},"blockquote",{},[64],{"type":47,"tag":55,"props":65,"children":66},{},[67,69,75],{"type":52,"value":68},"LangCache is currently in ",{"type":47,"tag":70,"props":71,"children":72},"strong",{},[73],{"type":52,"value":74},"preview",{"type":52,"value":76}," on Redis Cloud. Features and behavior may change.",{"type":47,"tag":78,"props":79,"children":81},"h2",{"id":80},"when-to-apply",[82],{"type":52,"value":83},"When to apply",{"type":47,"tag":85,"props":86,"children":87},"ul",{},[88,94,99,104],{"type":47,"tag":89,"props":90,"children":91},"li",{},[92],{"type":52,"value":93},"Wrapping an LLM call (OpenAI, Anthropic, etc.) with a cache layer to cut cost and latency.",{"type":47,"tag":89,"props":95,"children":96},{},[97],{"type":52,"value":98},"Caching RAG answers, classification outputs, or any deterministic LLM workload.",{"type":47,"tag":89,"props":100,"children":101},{},[102],{"type":52,"value":103},"Tuning the precision\u002Fhit-rate trade-off for a semantic cache.",{"type":47,"tag":89,"props":105,"children":106},{},[107],{"type":52,"value":108},"Splitting one application's LLM workloads across multiple cache instances.",{"type":47,"tag":78,"props":110,"children":112},{"id":111},"_1-the-cache-aside-flow",[113],{"type":52,"value":114},"1. The cache-aside flow",{"type":47,"tag":55,"props":116,"children":117},{},[118],{"type":52,"value":119},"LangCache fits in front of any LLM call as a standard cache-aside pattern:",{"type":47,"tag":121,"props":122,"children":123},"ol",{},[124,137,147],{"type":47,"tag":89,"props":125,"children":126},{},[127,129,135],{"type":52,"value":128},"Send the user's prompt to LangCache's ",{"type":47,"tag":130,"props":131,"children":133},"code",{"className":132},[],[134],{"type":52,"value":18},{"type":52,"value":136},".",{"type":47,"tag":89,"props":138,"children":139},{},[140,145],{"type":47,"tag":70,"props":141,"children":142},{},[143],{"type":52,"value":144},"Cache hit",{"type":52,"value":146}," — return the stored response directly.",{"type":47,"tag":89,"props":148,"children":149},{},[150,155,157,163],{"type":47,"tag":70,"props":151,"children":152},{},[153],{"type":52,"value":154},"Cache miss",{"type":52,"value":156}," — call the LLM, then ",{"type":47,"tag":130,"props":158,"children":160},{"className":159},[],[161],{"type":52,"value":162},"set",{"type":52,"value":164}," the response so future similar prompts hit.",{"type":47,"tag":166,"props":167,"children":172},"pre",{"className":168,"code":169,"language":170,"meta":171,"style":171},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from langcache import LangCache\nimport os\n\nlang_cache = LangCache(\n    server_url=f\"https:\u002F\u002F{os.getenv('HOST')}\",\n    cache_id=os.getenv(\"CACHE_ID\"),\n    api_key=os.getenv(\"API_KEY\"),\n)\n\nresult = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.9)\nif result:\n    response = result[0][\"response\"]\nelse:\n    response = llm.generate(\"What is Redis?\")\n    lang_cache.set(prompt=\"What is Redis?\", response=response)\n","python","",[173],{"type":47,"tag":130,"props":174,"children":175},{"__ignoreMap":171},[176,187,196,206,215,224,233,242,251,259,268,277,286,295,304],{"type":47,"tag":177,"props":178,"children":181},"span",{"class":179,"line":180},"line",1,[182],{"type":47,"tag":177,"props":183,"children":184},{},[185],{"type":52,"value":186},"from langcache import LangCache\n",{"type":47,"tag":177,"props":188,"children":190},{"class":179,"line":189},2,[191],{"type":47,"tag":177,"props":192,"children":193},{},[194],{"type":52,"value":195},"import os\n",{"type":47,"tag":177,"props":197,"children":199},{"class":179,"line":198},3,[200],{"type":47,"tag":177,"props":201,"children":203},{"emptyLinePlaceholder":202},true,[204],{"type":52,"value":205},"\n",{"type":47,"tag":177,"props":207,"children":209},{"class":179,"line":208},4,[210],{"type":47,"tag":177,"props":211,"children":212},{},[213],{"type":52,"value":214},"lang_cache = LangCache(\n",{"type":47,"tag":177,"props":216,"children":218},{"class":179,"line":217},5,[219],{"type":47,"tag":177,"props":220,"children":221},{},[222],{"type":52,"value":223},"    server_url=f\"https:\u002F\u002F{os.getenv('HOST')}\",\n",{"type":47,"tag":177,"props":225,"children":227},{"class":179,"line":226},6,[228],{"type":47,"tag":177,"props":229,"children":230},{},[231],{"type":52,"value":232},"    cache_id=os.getenv(\"CACHE_ID\"),\n",{"type":47,"tag":177,"props":234,"children":236},{"class":179,"line":235},7,[237],{"type":47,"tag":177,"props":238,"children":239},{},[240],{"type":52,"value":241},"    api_key=os.getenv(\"API_KEY\"),\n",{"type":47,"tag":177,"props":243,"children":245},{"class":179,"line":244},8,[246],{"type":47,"tag":177,"props":247,"children":248},{},[249],{"type":52,"value":250},")\n",{"type":47,"tag":177,"props":252,"children":254},{"class":179,"line":253},9,[255],{"type":47,"tag":177,"props":256,"children":257},{"emptyLinePlaceholder":202},[258],{"type":52,"value":205},{"type":47,"tag":177,"props":260,"children":262},{"class":179,"line":261},10,[263],{"type":47,"tag":177,"props":264,"children":265},{},[266],{"type":52,"value":267},"result = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.9)\n",{"type":47,"tag":177,"props":269,"children":271},{"class":179,"line":270},11,[272],{"type":47,"tag":177,"props":273,"children":274},{},[275],{"type":52,"value":276},"if result:\n",{"type":47,"tag":177,"props":278,"children":280},{"class":179,"line":279},12,[281],{"type":47,"tag":177,"props":282,"children":283},{},[284],{"type":52,"value":285},"    response = result[0][\"response\"]\n",{"type":47,"tag":177,"props":287,"children":289},{"class":179,"line":288},13,[290],{"type":47,"tag":177,"props":291,"children":292},{},[293],{"type":52,"value":294},"else:\n",{"type":47,"tag":177,"props":296,"children":298},{"class":179,"line":297},14,[299],{"type":47,"tag":177,"props":300,"children":301},{},[302],{"type":52,"value":303},"    response = llm.generate(\"What is Redis?\")\n",{"type":47,"tag":177,"props":305,"children":307},{"class":179,"line":306},15,[308],{"type":47,"tag":177,"props":309,"children":310},{},[311],{"type":52,"value":312},"    lang_cache.set(prompt=\"What is Redis?\", response=response)\n",{"type":47,"tag":55,"props":314,"children":315},{},[316,318,324,326,332],{"type":52,"value":317},"The same operations are available via REST (",{"type":47,"tag":130,"props":319,"children":321},{"className":320},[],[322],{"type":52,"value":323},"POST \u002Fv1\u002Fcaches\u002F{cacheId}\u002Fentries\u002Fsearch",{"type":52,"value":325}," and ",{"type":47,"tag":130,"props":327,"children":329},{"className":328},[],[330],{"type":52,"value":331},"POST \u002Fv1\u002Fcaches\u002F{cacheId}\u002Fentries",{"type":52,"value":333},") when an SDK isn't an option.",{"type":47,"tag":55,"props":335,"children":336},{},[337,339,345],{"type":52,"value":338},"See ",{"type":47,"tag":340,"props":341,"children":343},"a",{"href":342},"references\u002Flangcache-usage.md",[344],{"type":52,"value":342},{"type":52,"value":346}," for full SDK + REST samples and attribute-based storage.",{"type":47,"tag":78,"props":348,"children":350},{"id":349},"_2-tune-the-similarity-threshold",[351],{"type":52,"value":352},"2. Tune the similarity threshold",{"type":47,"tag":55,"props":354,"children":355},{},[356],{"type":52,"value":357},"The threshold controls how close (in embedding cosine distance) a new prompt must be to a cached one to count as a hit. Higher = stricter match, fewer false positives. Lower = more hits, more risk of returning an off-topic answer.",{"type":47,"tag":359,"props":360,"children":361},"table",{},[362,386],{"type":47,"tag":363,"props":364,"children":365},"thead",{},[366],{"type":47,"tag":367,"props":368,"children":369},"tr",{},[370,376,381],{"type":47,"tag":371,"props":372,"children":373},"th",{},[374],{"type":52,"value":375},"Threshold",{"type":47,"tag":371,"props":377,"children":378},{},[379],{"type":52,"value":380},"Behavior",{"type":47,"tag":371,"props":382,"children":383},{},[384],{"type":52,"value":385},"Use when",{"type":47,"tag":387,"props":388,"children":389},"tbody",{},[390,409,427],{"type":47,"tag":367,"props":391,"children":392},{},[393,399,404],{"type":47,"tag":394,"props":395,"children":396},"td",{},[397],{"type":52,"value":398},"0.95+",{"type":47,"tag":394,"props":400,"children":401},{},[402],{"type":52,"value":403},"Near-exact match required",{"type":47,"tag":394,"props":405,"children":406},{},[407],{"type":52,"value":408},"Customer-facing answers where wrong responses are costly",{"type":47,"tag":367,"props":410,"children":411},{},[412,417,422],{"type":47,"tag":394,"props":413,"children":414},{},[415],{"type":52,"value":416},"0.9",{"type":47,"tag":394,"props":418,"children":419},{},[420],{"type":52,"value":421},"Balanced default",{"type":47,"tag":394,"props":423,"children":424},{},[425],{"type":52,"value":426},"Most workloads — start here",{"type":47,"tag":367,"props":428,"children":429},{},[430,435,440],{"type":47,"tag":394,"props":431,"children":432},{},[433],{"type":52,"value":434},"0.8",{"type":47,"tag":394,"props":436,"children":437},{},[438],{"type":52,"value":439},"Loose semantic match",{"type":47,"tag":394,"props":441,"children":442},{},[443],{"type":52,"value":444},"Internal tools, exploratory queries, FAQ deduplication",{"type":47,"tag":166,"props":446,"children":448},{"className":168,"code":447,"language":170,"meta":171,"style":171},"# Stricter — fewer false positives\nresult = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.95)\n\n# Looser — higher hit rate\nresult = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.8)\n",[449],{"type":47,"tag":130,"props":450,"children":451},{"__ignoreMap":171},[452,460,468,475,483],{"type":47,"tag":177,"props":453,"children":454},{"class":179,"line":180},[455],{"type":47,"tag":177,"props":456,"children":457},{},[458],{"type":52,"value":459},"# Stricter — fewer false positives\n",{"type":47,"tag":177,"props":461,"children":462},{"class":179,"line":189},[463],{"type":47,"tag":177,"props":464,"children":465},{},[466],{"type":52,"value":467},"result = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.95)\n",{"type":47,"tag":177,"props":469,"children":470},{"class":179,"line":198},[471],{"type":47,"tag":177,"props":472,"children":473},{"emptyLinePlaceholder":202},[474],{"type":52,"value":205},{"type":47,"tag":177,"props":476,"children":477},{"class":179,"line":208},[478],{"type":47,"tag":177,"props":479,"children":480},{},[481],{"type":52,"value":482},"# Looser — higher hit rate\n",{"type":47,"tag":177,"props":484,"children":485},{"class":179,"line":217},[486],{"type":47,"tag":177,"props":487,"children":488},{},[489],{"type":52,"value":490},"result = lang_cache.search(prompt=\"What is Redis?\", similarity_threshold=0.8)\n",{"type":47,"tag":55,"props":492,"children":493},{},[494],{"type":52,"value":495},"Adjust by watching the actual cache-hit rate and spot-checking that returned answers are still relevant.",{"type":47,"tag":55,"props":497,"children":498},{},[499,500,505],{"type":52,"value":338},{"type":47,"tag":340,"props":501,"children":503},{"href":502},"references\u002Fbest-practices.md",[504],{"type":52,"value":502},{"type":52,"value":136},{"type":47,"tag":78,"props":507,"children":509},{"id":508},"_3-separate-caches-per-task-type",[510],{"type":52,"value":511},"3. Separate caches per task type",{"type":47,"tag":55,"props":513,"children":514},{},[515],{"type":52,"value":516},"Different LLM workloads should not share one cache — a \"code question\" prompt is semantically close to other code questions but has nothing to do with a password-reset support query, and crossing them returns garbage.",{"type":47,"tag":166,"props":518,"children":520},{"className":168,"code":519,"language":170,"meta":171,"style":171},"support_cache = LangCache(server_url=..., cache_id=\"support-cache-id\", api_key=...)\ncode_cache    = LangCache(server_url=..., cache_id=\"code-cache-id\",    api_key=...)\n",[521],{"type":47,"tag":130,"props":522,"children":523},{"__ignoreMap":171},[524,532],{"type":47,"tag":177,"props":525,"children":526},{"class":179,"line":180},[527],{"type":47,"tag":177,"props":528,"children":529},{},[530],{"type":52,"value":531},"support_cache = LangCache(server_url=..., cache_id=\"support-cache-id\", api_key=...)\n",{"type":47,"tag":177,"props":533,"children":534},{"class":179,"line":189},[535],{"type":47,"tag":177,"props":536,"children":537},{},[538],{"type":52,"value":539},"code_cache    = LangCache(server_url=..., cache_id=\"code-cache-id\",    api_key=...)\n",{"type":47,"tag":55,"props":541,"children":542},{},[543,545,550,552,558],{"type":52,"value":544},"Create distinct cache IDs in Redis Cloud per task, and route each call to the right one. As a finer-grained alternative, store and search with ",{"type":47,"tag":70,"props":546,"children":547},{},[548],{"type":52,"value":549},"custom attributes",{"type":52,"value":551}," (e.g. ",{"type":47,"tag":130,"props":553,"children":555},{"className":554},[],[556],{"type":52,"value":557},"{\"category\": \"database\"}",{"type":52,"value":559},") to keep tasks in the same cache but isolated by attribute filter — useful when the same prompt format spans subtopics.",{"type":47,"tag":78,"props":561,"children":563},{"id":562},"references",[564],{"type":52,"value":565},"References",{"type":47,"tag":85,"props":567,"children":568},{},[569],{"type":47,"tag":89,"props":570,"children":571},{},[572],{"type":47,"tag":340,"props":573,"children":577},{"href":574,"rel":575},"https:\u002F\u002Fredis.io\u002Fdocs\u002Flatest\u002Fdevelop\u002Fai\u002Flangcache\u002F",[576],"nofollow",[578],{"type":52,"value":579},"LangCache documentation",{"type":47,"tag":581,"props":582,"children":583},"style",{},[584],{"type":52,"value":585},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":587,"total":244},[588,606,626,637,650,668,682],{"slug":589,"name":589,"fn":590,"description":591,"org":592,"tags":593,"stars":26,"repoUrl":27,"updatedAt":605},"iris-development","integrate with Redis Iris AI products","Iris is Redis's umbrella for AI-focused products. Use this skill when integrating with the Iris Redis Agent Memory (RAM) data plane on Redis Cloud — recording session events for an AI agent, creating or searching long-term memories, configuring a memory store, or tuning background memory promotion. Code examples use the official `redis-agent-memory` (Python) and `@redis-iris\u002Fagent-memory` (TypeScript) SDKs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[594,597,598,601,604],{"name":595,"slug":596,"type":15},"Agents","agents",{"name":21,"slug":22,"type":15},{"name":599,"slug":600,"type":15},"Backend","backend",{"name":602,"slug":603,"type":15},"Memory","memory",{"name":9,"slug":8,"type":15},"2026-05-27T07:19:45.213725",{"slug":607,"name":607,"fn":608,"description":609,"org":610,"tags":611,"stars":26,"repoUrl":27,"updatedAt":625},"redis-clustering","configure Redis clustering and replication","Redis Cluster and replication guidance covering hash tags for multi-key operations, avoiding CROSSSLOT errors, and reading from replicas to scale read-heavy workloads. Use when designing keys for a sharded Redis Cluster, debugging CROSSSLOT errors on MGET \u002F SDIFF \u002F pipelines, configuring a multi-key transaction in a cluster, or routing reads to replicas for caches, analytics, or dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[612,615,618,621,624],{"name":613,"slug":614,"type":15},"Architecture","architecture",{"name":616,"slug":617,"type":15},"Database","database",{"name":619,"slug":620,"type":15},"Infrastructure","infrastructure",{"name":622,"slug":623,"type":15},"Performance","performance",{"name":9,"slug":8,"type":15},"2026-05-27T07:19:38.757599",{"slug":627,"name":627,"fn":628,"description":629,"org":630,"tags":631,"stars":26,"repoUrl":27,"updatedAt":636},"redis-connections","optimize Redis client connections","Redis client and connection guidance covering connection pooling, multiplexing, pipelining, client-side caching with RESP3, avoiding slow commands (KEYS, SMEMBERS, HGETALL), and tuning socket timeouts. Use when configuring a Redis client (redis-py, Jedis, Lettuce, NRedisStack), batching commands for throughput, eliminating per-request connection creation, iterating large keyspaces with SCAN, enabling client-side caching for read-heavy workloads, or setting connect and read timeouts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[632,633,634,635],{"name":599,"slug":600,"type":15},{"name":24,"slug":25,"type":15},{"name":622,"slug":623,"type":15},{"name":9,"slug":8,"type":15},"2026-05-27T07:19:42.616757",{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":26,"repoUrl":27,"updatedAt":649},"redis-core","model data with Redis structures","Core Redis modeling guidance — choose the right data structure (String, Hash, List, Set, Sorted Set, JSON, Stream, Vector Set) and use consistent colon-separated key names. Use when designing a Redis data model, caching objects, deciding between Hash and JSON, building counters, leaderboards, membership sets, or session stores, or when reviewing\u002Fcleaning up Redis key naming.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[643,644,647,648],{"name":613,"slug":614,"type":15},{"name":645,"slug":646,"type":15},"Data Modeling","data-modeling",{"name":616,"slug":617,"type":15},{"name":9,"slug":8,"type":15},"2026-05-27T07:19:41.317954",{"slug":651,"name":651,"fn":652,"description":653,"org":654,"tags":655,"stars":26,"repoUrl":27,"updatedAt":667},"redis-observability","monitor and triage Redis performance","Redis observability guidance — which metrics to monitor (memory, connections, hit ratio, ops\u002Fsec, rejected connections), which built-in commands to reach for during incident triage (SLOWLOG, INFO, MEMORY DOCTOR, CLIENT LIST, FT.PROFILE), and when to use the Redis Insight GUI. Use when setting up monitoring or alerts for a Redis instance, diagnosing a performance regression, profiling a slow FT.SEARCH query, or wiring Redis metrics into Prometheus, Datadog, or similar.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[656,659,662,665,666],{"name":657,"slug":658,"type":15},"Debugging","debugging",{"name":660,"slug":661,"type":15},"Monitoring","monitoring",{"name":663,"slug":664,"type":15},"Observability","observability",{"name":622,"slug":623,"type":15},{"name":9,"slug":8,"type":15},"2026-05-27T07:19:47.780873",{"slug":669,"name":669,"fn":670,"description":671,"org":672,"tags":673,"stars":26,"repoUrl":27,"updatedAt":681},"redis-search","implement Redis Search indexing and queries","Redis Search guidance covering FT.CREATE schema design, field type selection (TEXT, TAG, NUMERIC, GEO, GEOSHAPE, VECTOR, JSON path), DIALECT 2 query syntax, FT.SEARCH \u002F FT.AGGREGATE \u002F FT.HYBRID command selection, vector similarity with HNSW or FLAT, hybrid retrieval combining lexical and vector ranking, RAG pipelines, zero-downtime index updates via aliases, and debugging with FT.PROFILE and FT.EXPLAIN. Use when defining a search index on Hash or JSON documents, writing FT.SEARCH queries with filters, sorting, aggregation, or vector KNN, tuning HNSW parameters, building a RAG retrieval pipeline, or troubleshooting slow or empty search results.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[674,675,676,679,680],{"name":613,"slug":614,"type":15},{"name":616,"slug":617,"type":15},{"name":677,"slug":678,"type":15},"Engineering","engineering",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-06-24T07:39:43.089819",{"slug":683,"name":683,"fn":684,"description":685,"org":686,"tags":687,"stars":26,"repoUrl":27,"updatedAt":701},"redis-security","secure Redis instances and clusters","Redis security guidance covering authentication (requirepass and ACL users), TLS, ACL-based least-privilege access control, restricting network exposure via bind and protected-mode, firewall rules, and disabling dangerous commands. Use when deploying Redis to production, defining ACL users for an application, configuring TLS connections, locking down a Redis instance behind a firewall, or auditing a Redis deployment for security hardening.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[688,691,694,697,698],{"name":689,"slug":690,"type":15},"Access Control","access-control",{"name":692,"slug":693,"type":15},"Authentication","authentication",{"name":695,"slug":696,"type":15},"Compliance","compliance",{"name":9,"slug":8,"type":15},{"name":699,"slug":700,"type":15},"Security","security","2026-05-27T07:19:40.030241",{"items":703,"total":825},[704,712,720,727,734,742,750,758,766,781,796,812],{"slug":589,"name":589,"fn":590,"description":591,"org":705,"tags":706,"stars":26,"repoUrl":27,"updatedAt":605},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[707,708,709,710,711],{"name":595,"slug":596,"type":15},{"name":21,"slug":22,"type":15},{"name":599,"slug":600,"type":15},{"name":602,"slug":603,"type":15},{"name":9,"slug":8,"type":15},{"slug":607,"name":607,"fn":608,"description":609,"org":713,"tags":714,"stars":26,"repoUrl":27,"updatedAt":625},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[715,716,717,718,719],{"name":613,"slug":614,"type":15},{"name":616,"slug":617,"type":15},{"name":619,"slug":620,"type":15},{"name":622,"slug":623,"type":15},{"name":9,"slug":8,"type":15},{"slug":627,"name":627,"fn":628,"description":629,"org":721,"tags":722,"stars":26,"repoUrl":27,"updatedAt":636},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[723,724,725,726],{"name":599,"slug":600,"type":15},{"name":24,"slug":25,"type":15},{"name":622,"slug":623,"type":15},{"name":9,"slug":8,"type":15},{"slug":638,"name":638,"fn":639,"description":640,"org":728,"tags":729,"stars":26,"repoUrl":27,"updatedAt":649},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[730,731,732,733],{"name":613,"slug":614,"type":15},{"name":645,"slug":646,"type":15},{"name":616,"slug":617,"type":15},{"name":9,"slug":8,"type":15},{"slug":651,"name":651,"fn":652,"description":653,"org":735,"tags":736,"stars":26,"repoUrl":27,"updatedAt":667},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[737,738,739,740,741],{"name":657,"slug":658,"type":15},{"name":660,"slug":661,"type":15},{"name":663,"slug":664,"type":15},{"name":622,"slug":623,"type":15},{"name":9,"slug":8,"type":15},{"slug":669,"name":669,"fn":670,"description":671,"org":743,"tags":744,"stars":26,"repoUrl":27,"updatedAt":681},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[745,746,747,748,749],{"name":613,"slug":614,"type":15},{"name":616,"slug":617,"type":15},{"name":677,"slug":678,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"slug":683,"name":683,"fn":684,"description":685,"org":751,"tags":752,"stars":26,"repoUrl":27,"updatedAt":701},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[753,754,755,756,757],{"name":689,"slug":690,"type":15},{"name":692,"slug":693,"type":15},{"name":695,"slug":696,"type":15},{"name":9,"slug":8,"type":15},{"name":699,"slug":700,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":759,"tags":760,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[761,762,763,764,765],{"name":21,"slug":22,"type":15},{"name":24,"slug":25,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"slug":767,"name":767,"fn":768,"description":769,"org":770,"tags":771,"stars":778,"repoUrl":779,"updatedAt":780},"agent-filesystem","manage persistent storage in Redis","Use when agents need persistent shared storage, when saving or restoring workspace state, or when coordinating file access across multiple agents and machines. Creates Redis-backed workspaces, checkpoints and restores agent state, mounts shared filesystems locally, searches workspace contents, and forks workspaces for parallel work.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[772,773,776,777],{"name":595,"slug":596,"type":15},{"name":774,"slug":775,"type":15},"File Storage","file-storage",{"name":602,"slug":603,"type":15},{"name":9,"slug":8,"type":15},22,"https:\u002F\u002Fgithub.com\u002Fredis\u002Fagent-filesystem","2026-04-10T04:51:05.904489",{"slug":782,"name":782,"fn":783,"description":784,"org":785,"tags":786,"stars":778,"repoUrl":779,"updatedAt":795},"codex-settings-sync","sync Codex settings across computers","Use when the user wants to migrate Codex state in ~\u002F.codex into Agent Filesystem and mount the same shared Codex memory\u002Fsettings across multiple computers. Recommends a .afsignore before migration and defaults to excluding worktrees, caches, logs, and temporary files.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[787,790,791,794],{"name":788,"slug":789,"type":15},"Codex","codex",{"name":602,"slug":603,"type":15},{"name":792,"slug":793,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-04-10T04:51:07.268248",{"slug":797,"name":797,"fn":798,"description":799,"org":800,"tags":801,"stars":306,"repoUrl":810,"updatedAt":811},"cloud-database-provisioning","provision Redis Cloud databases","Provision a Redis Cloud database end-to-end — Essentials (fixed plan) or Pro (custom) — using Redis Cloud MCP tools",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[802,805,806,809],{"name":803,"slug":804,"type":15},"Cloud","cloud",{"name":616,"slug":617,"type":15},{"name":807,"slug":808,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"https:\u002F\u002Fgithub.com\u002Fredis\u002Fredisctl","2026-06-03T07:53:00.906753",{"slug":813,"name":813,"fn":814,"description":815,"org":816,"tags":817,"stars":306,"repoUrl":810,"updatedAt":824},"compare-approaches","prototype Redis data model alternatives","Prototype and compare 2-3 Redis data model alternatives for the same workload",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[818,819,820,823],{"name":645,"slug":646,"type":15},{"name":616,"slug":617,"type":15},{"name":821,"slug":822,"type":15},"Prototyping","prototyping",{"name":9,"slug":8,"type":15},"2026-05-27T07:19:55.591944",27]