{ "id": "dotnet", "title": "Redis agent memory with NRedisStack", "url": "https://redis.io/docs/latest/develop/use-cases/agent-memory/dotnet/", "summary": "Build a Redis-backed agent memory layer in C# with NRedisStack, ONNX Runtime, and standard Redis commands — working memory in a Hash, long-term semantic recall as JSON with a vector index, and an event log in a Stream.", "tags": [ "docs", "develop", "stack", "oss", "rs", "rc" ], "last_updated": "2026-06-11T16:10:09-04:00", "children": [], "page_type": "content", "content_hash": "31f6894a54d39cae964c9211e29559c3715f95fc592e66dff27a44398be74e70", "sections": [ { "id": "overview", "title": "Overview", "role": "overview", "text": "This guide shows you how to build a small Redis-backed agent memory layer in C# (.NET 8) with [NRedisStack](https://redis.io/docs/latest/develop/clients/dotnet) and the ONNX Runtime, using only standard Redis commands — no agent-memory SDK, no managed service. It includes a local web server built with the .NET [`HttpListener`](https://learn.microsoft.com/en-us/dotnet/api/system.net.httplistener) so you can send turns at the agent, watch working memory update in place, see semantically similar long-term memories recalled in real time, watch the write-time deduplication skip near-duplicates, and inspect the per-thread event log.\n\nThe embedder runs the ONNX-exported [`Xenova/all-MiniLM-L6-v2`](https://huggingface.co/Xenova/all-MiniLM-L6-v2) model — the same encoder the [Python](https://redis.io/docs/latest/develop/use-cases/agent-memory/redis-py) and [Node.js](https://redis.io/docs/latest/develop/use-cases/agent-memory/nodejs) examples use. .NET ONNX Runtime is the same C++ kernel that powers Python's `onnxruntime`, so the vectors produced here are numerically identical to the Python ones to within rounding noise. The distance bands the Python walkthrough quotes carry over to this demo without recalibration, and a memory written by one demo can be recalled by the other against the same Redis instance." }, { "id": "overview", "title": "Overview", "role": "overview", "text": "The memory layer splits across three Redis primitives, each handling one tier:\n\n* **Working memory** for the active session is a [Hash](https://redis.io/docs/latest/develop/data-types/hashes) at `agent:session:` holding the goal, scratchpad, a rolling window of recent turns (as a JSON list inside one field), and a few audit timestamps. One [`HGETALL`](https://redis.io/docs/latest/commands/hgetall) returns the whole session in a single round trip; every write refreshes the key's [`EXPIRE`](https://redis.io/docs/latest/commands/expire) so idle sessions decay on their own.\n* **Long-term memory** is a set of [JSON](https://redis.io/docs/latest/develop/data-types/json) documents at `agent:mem:`, each carrying the memory text, a 384-dimensional embedding vector, and tag fields for user, namespace, kind (episodic / semantic), and source thread. A single [Redis Search](https://redis.io/docs/latest/develop/ai/search-and-query) index covers the [HNSW vector field](https://redis.io/docs/latest/develop/ai/search-and-query/vectors) and every metadata field, so one [`FT.SEARCH`](https://redis.io/docs/latest/commands/ft.search) call performs the KNN with the metadata pre-filter in the same round trip. Write-time deduplication runs the same KNN at insert time and skips a new memory whose nearest existing entry is within a tighter threshold.\n* **Event log** for the agent's actions and observations is a [Stream](https://redis.io/docs/latest/develop/data-types/streams) at `agent:events:`, appended with [`XADD MAXLEN ~`](https://redis.io/docs/latest/commands/xadd) so retention stays bounded automatically, replayed with [`XREVRANGE`](https://redis.io/docs/latest/commands/xrevrange).\n\nThat gives you:\n\n* A single round trip per tier: one [`HGETALL`](https://redis.io/docs/latest/commands/hgetall) for the session, one [`FT.SEARCH`](https://redis.io/docs/latest/commands/ft.search) for recall, one [`XADD`](https://redis.io/docs/latest/commands/xadd) for the event log.\n* Sub-millisecond reads on every step of the agent loop, so the memory layer doesn't dominate per-step latency.\n* Per-tier decay: short TTLs on working memory, longer on episodic memories, no TTL on semantic memories. Combined with a database-level [eviction policy](https://redis.io/docs/latest/develop/reference/eviction) (LFU is the common choice), memory stays bounded under pressure.\n* Scoping enforced inside the query: a recall query for `user=alice` will never see `user=bob`'s memories, because the TAG filter goes into the same [`FT.SEARCH`](https://redis.io/docs/latest/commands/ft.search) call as the KNN." }, { "id": "how-it-works", "title": "How it works", "role": "content", "text": "Each turn through the agent loop touches all three tiers in one pass: append to working memory, recall similar long-term memories, write the turn back as a new memory (with deduplication), and append one event to the log." }, { "id": "per-turn-flow", "title": "Per-turn flow", "role": "content", "text": "1. The application calls `embedder.EncodeOne(text)` to turn the incoming turn into a 384-dimensional `float[]`.\n2. `session.AppendTurn(threadId, role, content, user, agentName)` reads the per-thread Hash with [`HGETALL`](https://redis.io/docs/latest/commands/hgetall), appends the new turn to the rolling window in application code, trims it back to the configured maximum, and writes the Hash back with [`HSET`](https://redis.io/docs/latest/commands/hset) + [`EXPIRE`](https://redis.io/docs/latest/commands/expire) inside a [`MULTI/EXEC`](https://redis.io/docs/latest/commands/multi). The session TTL refreshes on every write so an active thread stays alive.\n3. `memory.Recall(vec, user, @namespace, k: 5)` runs [`FT.SEARCH`](https://redis.io/docs/latest/commands/ft.search) with a TAG pre-filter and a `KNN 5` clause. Redis returns the closest matching memories together with their cosine distances; memories beyond the recall threshold are dropped before they reach the agent so an unrelated query doesn't surface confident-looking false positives.\n4. `memory.Remember(text, vec, user, @namespace, kind)` runs the same KNN with a tighter dedup threshold. If an existing memory is within the threshold, the new write is skipped and the existing memory's `hit_count` is incremented with [`JSON.NUMINCRBY`](https://redis.io/docs/latest/commands/json.numincrby); otherwise a fresh JSON document is written with [`JSON.SET`](https://redis.io/docs/latest/commands/json.set) and a per-kind [`EXPIRE`](https://redis.io/docs/latest/commands/expire) — `episodic` defaults to seven days, `semantic` has no TTL by default.\n5. `events.Record(threadId, action, detail)` appends one entry to the per-thread Stream with [`XADD MAXLEN ~`](https://redis.io/docs/latest/commands/xadd), bounding retention to roughly a thousand entries per thread without an explicit cleanup job.\n\nThe embedding is computed once and reused for steps 3 and 4 — there's no point encoding the same text twice. Recall runs before the write, so the agent doesn't see its own just-written turn echoed back as a recalled memory." }, { "id": "the-session-store", "title": "The session store", "role": "content", "text": "`AgentSession` wraps the working-memory Hash and the rolling turn window ([source](https://github.com/redis/docs/blob/main/content/develop/use-cases/agent-memory/dotnet/AgentSession.cs)):\n\n[code example]\n\nThe data model is one Hash per thread. The rolling turn window is stored as a JSON string in a single field so the whole session loads in one [`HGETALL`](https://redis.io/docs/latest/commands/hgetall) — the hash never grows in size or field count as the conversation goes on.\n\n[code example]\n\nEvery write — `Start`, `AppendTurn`, `SetGoal`, `SetScratchpad` — runs the [`HSET`](https://redis.io/docs/latest/commands/hset) and [`EXPIRE`](https://redis.io/docs/latest/commands/expire) inside a [`MULTI`](https://redis.io/docs/latest/commands/multi) / [`EXEC`](https://redis.io/docs/latest/commands/exec) (via NRedisStack's `CreateTransaction`) so a connection drop between the two writes can't leave the session without a TTL." }, { "id": "the-long-term-memory-store", "title": "The long-term memory store", "role": "content", "text": "`LongTermMemory` owns the JSON documents, the vector index, the recall query, and the write-time deduplication ([source](https://github.com/redis/docs/blob/main/content/develop/use-cases/agent-memory/dotnet/LongTermMemory.cs)):\n\n[code example]" }, { "id": "data-model", "title": "Data model", "role": "content", "text": "Each memory is a JSON document at `agent:mem:`. The embedding is stored as a JSON array of floats so the document is human-readable from `redis-cli`; [`FT.SEARCH`](https://redis.io/docs/latest/commands/ft.search) still expects the *query* vector as raw `float32` bytes (packed by `LocalEmbedder.ToBytes` with explicit little-endian writes), regardless of how the indexed document stores it.\n\n[code example]\n\nThe Redis Search index is declared on the JSON document type with alias names so the query syntax stays compact (`FieldName(\"$.user\", \"user\")` writes `$.user AS user` into `FT.CREATE`):\n\n[code example]" }, { "id": "the-query", "title": "The query", "role": "content", "text": "Both recall and dedup share the same hybrid query: a TAG pre-filter in parentheses followed by `=>[KNN k @embedding $vec]`. With `DIALECT 2`, Redis applies the filter first and KNN-ranks only the matching documents.\n\n[code example]\n\n`distance` is the cosine *distance* (0 means identical, 2 means opposite). Recall and dedup share the same query shape; only the threshold differs — strict at write time so the index doesn't fill with paraphrases of the same fact, looser at read time so the agent gets a wider net of relevant memories." }, { "id": "per-kind-ttls", "title": "Per-kind TTLs", "role": "content", "text": "`Remember` resolves the entry's TTL from the memory's `kind`:\n\n| Kind | Default TTL | When to use it |\n|-----------|-------------|-------------------------------------------------------------|\n| `episodic` | 7 days | Snapshots from a specific session that should decay. |\n| `semantic` | none | Distilled facts and preferences the agent carries forward. |\n\nYou can override per write with `ttlSeconds: ...` on `Remember`, or pass a different `ttlByKind: ...` map to the `LongTermMemory` constructor — for example, to give semantic memories a six-month TTL while leaving episodic memories at seven days." }, { "id": "the-event-log", "title": "The event log", "role": "content", "text": "`AgentEventLog` is a thin wrapper over a per-thread Redis Stream ([source](https://github.com/redis/docs/blob/main/content/develop/use-cases/agent-memory/dotnet/AgentEventLog.cs)):\n\n[code example]\n\n`Record` calls [`XADD`](https://redis.io/docs/latest/commands/xadd) with `MAXLEN ~ 1000` (StackExchange.Redis's `useApproximateMaxLength: true`). The tilde lets Redis trim in whole-node units instead of exactly-N units, which is much cheaper at the cost of overshooting the bound by up to a node's worth — the right tradeoff for an audit log where exact length doesn't matter.\n\nThe Stream is independent of the session Hash and the long-term JSON documents: it answers \"what just happened\" without competing with either of those for indexing or memory budget. Consumer groups (not used in this demo) would let downstream workers — summarisers, consolidators, audit pipelines — replay the log without losing position." }, { "id": "concurrency-caveats", "title": "Concurrency caveats", "role": "content", "text": "The three helpers above trade correctness under heavy concurrency for clarity. Each is fine on a single-process demo, but lifting the code into a real multi-worker agent surfaces three races worth knowing about:\n\n* **Working memory is read-modify-write.** `AgentSession.AppendTurn` calls [`HGETALL`](https://redis.io/docs/latest/commands/hgetall), mutates the `recent_turns` list in application code, and writes the Hash back with [`HSET`](https://redis.io/docs/latest/commands/hset). Two concurrent turns on the same thread can both read the same `recent_turns`, append different entries, and write back — last writer wins, the other turn is silently lost. The robust fix is either a [`WATCH`](https://redis.io/docs/latest/commands/watch) / [`MULTI`](https://redis.io/docs/latest/commands/multi) / [`EXEC`](https://redis.io/docs/latest/commands/exec) loop around the read-modify-write or a small [Lua script](https://redis.io/docs/latest/commands/eval) that does the append atomically server-side.\n\n* **Long-term dedup is not atomic.** `LongTermMemory.Remember` runs a [`FT.SEARCH`](https://redis.io/docs/latest/commands/ft.search) KNN lookup, decides whether the candidate is a duplicate, and (if not) calls [`JSON.SET`](https://redis.io/docs/latest/commands/json.set). Two workers seeing the same fact in flight can each fail to see the other's not-yet-committed write and both insert a new memory. The pragmatic fix is to accept that the index will occasionally hold near-duplicates and run a background consolidator that periodically scans for memory pairs within a tight distance and merges them, rather than trying to make the write itself atomic.\n\n* **The active thread is server state.** The demo server keeps a single `CurrentThreadId` that `/new_thread` and `/reset` mutate. `HandleTurn` reads it without coordination, so a turn racing with a thread rotation can apply to the previous thread. This is cosmetic for a one-user browser demo. A multi-user agent would carry the thread id on the request itself rather than as shared server state.\n\nThose caveats are deliberate. A more conservative implementation would obscure the Redis-shaped parts of the pattern; the demo prioritizes a small, readable code path that maps directly onto the commands in the prose above." }, { "id": "pre-seeding-long-term-memory", "title": "Pre-seeding long-term memory", "role": "content", "text": "In a real deployment the memory store fills up organically as the agent reasons over user turns: each turn produces zero or more memories that flow into the store, with deduplication catching repeats. For the demo, `SeedMemory.cs` pre-loads a small set of mixed semantic and episodic memories so the very first recall query returns something useful ([source](https://github.com/redis/docs/blob/main/content/develop/use-cases/agent-memory/dotnet/SeedMemory.cs)):\n\n[code example]\n\nThe seed list mixes long-lived facts and preferences (`semantic`) with snapshots of past sessions (`episodic`), so the **Kind to write** control in the demo has something to switch between when a new turn is being remembered." }, { "id": "the-interactive-demo", "title": "The interactive demo", "role": "content", "text": "`Program.cs` runs a .NET [`HttpListener`](https://learn.microsoft.com/en-us/dotnet/api/system.net.httplistener) on port 8093, dispatching to handlers on the thread pool. The HTML page exposes three live panels — working memory, recalled memories, event log — plus a memories table for admin actions. Endpoints:\n\n| Endpoint | What it does |\n|---------------------|---------------------------------------------------------------------------------|\n| `GET /state` | Index info, current session, in-scope long-term memories, and recent events. |\n| `POST /turn` | Embed the text, append to working memory, recall similar memories, optionally write a new memory (with dedup), append an event. |\n| `POST /new_thread` | Start a fresh thread; long-term memory and other threads are untouched. |\n| `POST /reset` | Drop every long-term memory and re-seed the sample set. |\n| `POST /drop_memory` | Delete a single long-term memory by id. |\n\nThe server holds one `LocalEmbedder`, one `AgentSession`, one `LongTermMemory`, and one `AgentEventLog` for the lifetime of the process. The \"current thread\" is a single property on the demo object that the **New thread** button rotates — every browser tab inherits the same thread until you explicitly start a new one." }, { "id": "run-the-demo-locally", "title": "Run the demo locally", "role": "content", "text": "1. Clone the [`redis/docs`](https://github.com/redis/docs) repository and change into the example\n directory:\n\n [code example]\n\n2. Restore and build the project. You'll need the [.NET 8 SDK](https://dotnet.microsoft.com/download)\n or later:\n\n [code example]\n\n3. Make sure a Redis instance with Redis Search and Redis JSON is running locally on\n port 6379. [Redis Stack](https://redis.io/docs/latest/operate/oss_and_stack/install/install-stack)\n ships both, or [Redis 8](https://redis.io/docs/latest/develop/ai/search-and-query) with the\n Search and JSON modules enabled.\n\n4. Start the demo. The first run downloads the\n [`Xenova/all-MiniLM-L6-v2`](https://huggingface.co/Xenova/all-MiniLM-L6-v2) ONNX\n weights (around 90 MB) and `vocab.txt` into a local `model_cache/` directory next\n to the binary:\n\n [code example]\n\n5. Open and try some turns:\n\n * **\"Remind me which theme I prefer in editors.\"** — paraphrase of a seeded\n semantic memory (\"The user dislikes dark mode and prefers a high-contrast\n light theme...\"). You should see that memory recalled with a cosine\n distance around 0.47, comfortably under the 0.55 default recall\n threshold.\n * **\"What did we discuss about the order-routing outage?\"** — paraphrase of\n a seeded episodic memory; the postmortem memory should recall around\n 0.44. Switch the **Kind to write** dropdown to `skip` so the question\n itself doesn't enter long-term memory.\n * **\"I prefer concise answers without filler phrases.\"** — paraphrase of\n a seeded *semantic* memory. Switch the **Kind to write** dropdown to\n `semantic` so the dedup KNN runs in the same kind as the seed (dedup\n is scoped per kind, on purpose, so an episodic write can't collapse\n onto a semantic memory). You should then see the write **deduped**\n onto the existing memory at a cosine distance around 0.15, with\n `hit_count` ticking up in the memories table.\n * **\"My favorite color is teal.\"** — unrelated to any seed; nothing\n recalls above the threshold (every seed lands above 0.8), and the new\n memory is written as `episodic` (or `semantic`, depending on the\n dropdown) under a fresh id.\n * Switch the **User** field to `bob` and re-ask any of the above — recall\n returns nothing because the seed memories live under `default`. That's\n the TAG pre-filter at work inside [`FT.SEARCH`](https://redis.io/docs/latest/commands/ft.search).\n * Slide the **Recall threshold** down to 0.30 to see borderline paraphrases\n drop out of the recall set, then back up to 0.70 to watch them return.\n\n The .NET ONNX Runtime is the same C++ kernel that powers Python's\n `onnxruntime`, so distances here match the Python demo to four decimal\n places. `Xenova/all-MiniLM-L6-v2` puts a faithful paraphrase in the\n 0.15 – 0.50 cosine-distance range, a loose paraphrase or related topic in\n the 0.50 – 0.80 range, and unrelated queries above 0.8 — which is what\n motivates the 0.55 default recall threshold and the 0.20 default dedup\n threshold. A stricter embedding model (or a domain-tuned one) would let\n you tighten both; a noisier one would push them up. The right thresholds\n are always a function of the model, the corpus, and how conservative the\n agent needs to be about accepting a memory as a match.\n\nThe server is read/write against your local Redis. The default memory index is `agentmem:idx`, JSON keys live under `agent:mem:`, session Hashes under `agent:session:`, and event Streams under `agent:events:`. Useful flags (pass them after `--`, for example `dotnet run -- --no-reset`):\n\n* `--no-reset` — keep the existing long-term memories across restarts instead of dropping and re-seeding.\n* `--session-ttl-seconds` — change the working-memory TTL (default 3600).\n* `--dedup-threshold` — change the cosine-distance cutoff for write-time deduplication.\n* `--recall-threshold` — change the default cosine-distance cutoff for recall." } ], "examples": [ { "id": "the-session-store-ex0", "language": "csharp", "code": "using StackExchange.Redis;\nusing AgentMemoryDemo;\n\nvar mux = ConnectionMultiplexer.Connect(\"localhost:6379\");\nvar db = mux.GetDatabase();\n\nvar session = new AgentSession(\n db,\n keyPrefix: \"agent:session:\",\n defaultTtlSeconds: 3600, // one hour\n maxTurns: 20); // rolling window per thread\n\nstring threadId = session.NewThreadId();\nsession.Start(threadId, user: \"alice\", agentName: \"demo-agent\",\n goal: \"Plan next week's meetings.\");\nsession.AppendTurn(threadId, role: \"user\",\n content: \"Schedule a budget review with finance.\",\n user: \"alice\", agentName: \"demo-agent\");\nSessionState? state = session.Load(threadId);\nConsole.WriteLine($\"{state?.TurnCount} {state?.RecentTurns.Count} {state?.TtlSeconds}\");", "section_id": "the-session-store" }, { "id": "the-session-store-ex1", "language": "text", "code": "agent:session:9f3d2a4b8c61\n thread_id=9f3d2a4b8c61\n user=alice\n agent=demo-agent\n goal=Plan next week's meetings.\n scratchpad=Need to confirm finance's availability.\n turn_count=4\n created_ts=1715990400.12\n last_active_ts=1715990650.83\n recent_turns=[{\"role\":\"user\",\"content\":\"...\",\"ts\":...}, ...]", "section_id": "the-session-store" }, { "id": "the-long-term-memory-store-ex0", "language": "csharp", "code": "using AgentMemoryDemo;\n\nvar memory = new LongTermMemory(\n db,\n indexName: \"agentmem:idx\",\n keyPrefix: \"agent:mem:\",\n dedupThreshold: 0.20, // cosine distance — tight at write time\n recallThreshold: 0.55); // looser at read time\nvar embedder = await LocalEmbedder.CreateAsync();\nmemory.CreateIndex(); // idempotent\n\n// Write a memory. The same KNN that powers recall also runs here at\n// a tighter threshold so paraphrases of the same fact collapse.\nfloat[] vec = embedder.EncodeOne(\"The user prefers light mode in editors.\");\nWriteResult result = memory.Remember(\n text: \"The user prefers light mode in editors.\",\n embedding: vec,\n user: \"alice\",\n @namespace: \"default\",\n kind: \"semantic\",\n sourceThread: \"9f3d2a4b8c61\");\nConsole.WriteLine($\"deduped={result.Deduped} id={result.Id} dist={result.ExistingDistance}\");\n\n// Recall against a later question.\nfloat[] q = embedder.EncodeOne(\"Which theme does this user like?\");\nvar hits = memory.Recall(\n queryEmbedding: q,\n user: \"alice\",\n @namespace: \"default\",\n k: 5);\nforeach (var h in hits)\n{\n Console.WriteLine($\"{h.Distance:F3} [{h.Kind}] {h.Text}\");\n}", "section_id": "the-long-term-memory-store" }, { "id": "data-model-ex0", "language": "json", "code": "agent:mem:7c3f8a1b9e02\n{\n \"id\": \"7c3f8a1b9e02\",\n \"user\": \"alice\",\n \"namespace\": \"default\",\n \"kind\": \"semantic\",\n \"source_thread\": \"9f3d2a4b8c61\",\n \"text\": \"The user prefers light mode in editors.\",\n \"embedding\": [0.013, -0.041, ...],\n \"created_ts\": 1715990400.12,\n \"hit_count\": 0\n}", "section_id": "data-model" }, { "id": "data-model-ex1", "language": "text", "code": "FT.CREATE agentmem:idx\n ON JSON PREFIX 1 agent:mem:\n SCHEMA\n $.text AS text TEXT\n $.user AS user TAG\n $.namespace AS namespace TAG\n $.kind AS kind TAG\n $.source_thread AS source_thread TAG\n $.created_ts AS created_ts NUMERIC SORTABLE\n $.hit_count AS hit_count NUMERIC SORTABLE\n $.embedding AS embedding VECTOR HNSW 6\n TYPE FLOAT32 DIM 384\n DISTANCE_METRIC COSINE", "section_id": "data-model" }, { "id": "the-query-ex0", "language": "text", "code": "FT.SEARCH agentmem:idx\n \"(@user:{alice} @namespace:{default} @kind:{semantic})\n =>[KNN 5 @embedding $vec AS distance]\"\n PARAMS 2 vec <384-float32-bytes>\n SORTBY distance\n RETURN 8 user namespace kind source_thread text created_ts hit_count distance\n DIALECT 2", "section_id": "the-query" }, { "id": "the-event-log-ex0", "language": "csharp", "code": "var events = new AgentEventLog(db, maxLen: 1000);\nevents.Record(threadId, \"turn_appended:user\",\n \"Schedule a budget review with finance.\");\nevents.Record(threadId, \"memory_written\",\n \"wrote 7c3f8a1b9e02 as semantic\");\n\nforeach (var e in events.Recent(threadId, count: 20))\n{\n Console.WriteLine($\"{e.Action} {e.Detail}\");\n}", "section_id": "the-event-log" }, { "id": "pre-seeding-long-term-memory-ex0", "language": "csharp", "code": "using AgentMemoryDemo;\n\nvar memory = new LongTermMemory(db);\nvar embedder = await LocalEmbedder.CreateAsync();\nmemory.CreateIndex();\nSeedMemory.Seed(memory, embedder, user: \"default\", @namespace: \"default\");", "section_id": "pre-seeding-long-term-memory" }, { "id": "run-the-demo-locally-ex0", "language": "bash", "code": "git clone https://github.com/redis/docs.git\n cd docs/content/develop/use-cases/agent-memory/dotnet", "section_id": "run-the-demo-locally" }, { "id": "run-the-demo-locally-ex1", "language": "bash", "code": "dotnet build", "section_id": "run-the-demo-locally" }, { "id": "run-the-demo-locally-ex2", "language": "bash", "code": "dotnet run", "section_id": "run-the-demo-locally" } ] }