Siddhant-K-code
diff --git a/‎README.md‎
Lines changed: 81 additions & 7 deletions b/‎README.md‎
Lines changed: 81 additions & 7 deletions
diff --git a/‎cmd/api.go‎
Lines changed: 23 additions & 0 deletions b/‎cmd/api.go‎
Lines changed: 23 additions & 0 deletions
diff --git a/‎cmd/api_memory.go‎
Lines changed: 155 additions & 0 deletions b/‎cmd/api_memory.go‎
Lines changed: 155 additions & 0 deletions
@@ -10,7 +10,7 @@
 
 **Context intelligence layer for AI agents.**
 
-Deduplicates, compresses, and manages context across sessions - so your agents produce reliable, deterministic outputs. Today: a dedup pipeline with ~12ms overhead. Next: persistent context memory, code change impact graphs, and session-aware context windows.
+Deduplicates, compresses, and manages context across sessions - so your agents produce reliable, deterministic outputs. Includes a dedup pipeline with ~12ms overhead and persistent context memory with write-time dedup and hierarchical decay.
 
 Less redundant data. Lower costs. Faster responses. Deterministic results.
 
@@ -201,12 +201,82 @@ Add to Claude Desktop (`~/Library/Application Support/Claude/claude_desktop_conf
 
 See [mcp/README.md](mcp/README.md) for more configuration options.
 
+## Context Memory
+
+Persistent memory that accumulates knowledge across agent sessions. Memories are deduplicated on write, ranked by relevance + recency on recall, and compressed over time through hierarchical decay.
+
+Enable with the `--memory` flag on `api` or `mcp` commands.
+
+### CLI
+
+```bash
+# Store a memory
+distill memory store --text "Auth uses JWT with RS256 signing" --tags auth --source docs
+
+# Recall relevant memories
+distill memory recall --query "How does authentication work?" --max-results 5
+
+# Remove outdated memories
+distill memory forget --tags deprecated
+
+# View statistics
+distill memory stats
+```
+
+### API
+
+```bash
+# Start API with memory enabled
+distill api --port 8080 --memory
+
+# Store
+curl -X POST http://localhost:8080/v1/memory/store \
+  -H "Content-Type: application/json" \
+  -d '{
+    "session_id": "session-1",
+    "entries": [{"text": "Auth uses JWT with RS256", "tags": ["auth"], "source": "docs"}]
+  }'
+
+# Recall
+curl -X POST http://localhost:8080/v1/memory/recall \
+  -H "Content-Type: application/json" \
+  -d '{"query": "How does auth work?", "max_results": 5}'
+```
+
+### MCP
+
+Memory tools are available in Claude Desktop, Cursor, and other MCP clients when `--memory` is enabled:
+
+```bash
+distill mcp --memory
+```
+
+Tools exposed: `store_memory`, `recall_memory`, `forget_memory`, `memory_stats`.
+
+### How Decay Works
+
+Memories compress over time based on access patterns:
+
+```
+Full text → Summary (~20%) → Keywords (~5%) → Evicted
+  (24h)        (7 days)         (30 days)
+```
+
+Accessing a memory resets its decay clock. Configure ages via `distill.yaml`:
+
+```yaml
+memory:
+  db_path: distill-memory.db
+  dedup_threshold: 0.15
+```
+
 ## CLI Commands
 
 ```bash
 distill api       # Start standalone API server
 distill serve     # Start server with vector DB connection
 distill mcp       # Start MCP server for AI assistants
+distill memory    # Store, recall, and manage persistent context memories
 distill analyze   # Analyze a file for duplicates
 distill sync      # Upload vectors to Pinecone with dedup
 distill query     # Test a query from command line
@@ -220,6 +290,10 @@ distill config    # Manage configuration files
 | POST | `/v1/dedupe` | Deduplicate chunks |
 | POST | `/v1/dedupe/stream` | SSE streaming dedup with per-stage progress |
 | POST | `/v1/retrieve` | Query vector DB with dedup (requires backend) |
+| POST | `/v1/memory/store` | Store memories with write-time dedup (requires `--memory`) |
+| POST | `/v1/memory/recall` | Recall memories by relevance + recency (requires `--memory`) |
+| POST | `/v1/memory/forget` | Remove memories by ID, tag, or age (requires `--memory`) |
+| GET | `/v1/memory/stats` | Memory store statistics (requires `--memory`) |
 | GET | `/health` | Health check |
 | GET | `/metrics` | Prometheus metrics |
 
@@ -489,10 +563,10 @@ KV cache for repeated context patterns (system prompts, tool definitions, boiler
 │  └─────────┘  └─────────┘  └─────────┘  └──────────┘  └─────────┘  │
 │     <1ms          6ms         <1ms          2ms           3ms        │
 │                                                                      │
-│  Context Intelligence (planned)                                      │
+│  Context Intelligence                                                │
 │  ┌──────────────┐  ┌──────────────┐  ┌──────────────────────────┐   │
 │  │ Memory Store │  │ Impact Graph │  │ Session Context Windows  │   │
-│  │  (#29)       │  │  (#30)       │  │  (#31)                   │   │
+│  │  (shipped)   │  │  (#30)       │  │  (#31)                   │   │
 │  └──────────────┘  └──────────────┘  └──────────────────────────┘   │
 │                                                                      │
 │  ┌──────────────────────────────────────────────────────────────┐    │
@@ -527,10 +601,10 @@ Distill is evolving from a dedup utility into a context intelligence layer. Here
 
 ### Context Memory
 
-| Feature | Issue | Description |
-|---------|-------|-------------|
-| **Context Memory Store** | [#29](https://github.com/Siddhant-K-code/distill/issues/29) | Persistent, deduplicated memory across sessions. Write-time dedup, hierarchical decay (full text -> summary -> keywords -> evicted), token-budgeted recall. |
-| **Session Management** | [#31](https://github.com/Siddhant-K-code/distill/issues/31) | Stateful context windows for long-running agents. Push context incrementally, Distill keeps it deduplicated and within budget. |
+| Feature | Issue | Status | Description |
+|---------|-------|--------|-------------|
+| **Context Memory Store** | [#29](https://github.com/Siddhant-K-code/distill/issues/29) | Shipped | Persistent, deduplicated memory across sessions. Write-time dedup, hierarchical decay, token-budgeted recall. See [Context Memory](#context-memory). |
+| **Session Management** | [#31](https://github.com/Siddhant-K-code/distill/issues/31) | Planned | Stateful context windows for long-running agents. Push context incrementally, Distill keeps it deduplicated and within budget. |
 
 ### Code Intelligence
 
 
@@ -45,6 +45,7 @@ func init() {
 	apiCmd.Flags().String("openai-key", "", "OpenAI API key for embeddings (or use OPENAI_API_KEY)")
 	apiCmd.Flags().String("embedding-model", "text-embedding-3-small", "OpenAI embedding model")
 	apiCmd.Flags().String("api-keys", "", "Comma-separated list of valid API keys (or use DISTILL_API_KEYS)")
+	apiCmd.Flags().Bool("memory", false, "Enable persistent memory store")
 
 	// Bind to viper for config file support
 	_ = viper.BindPFlag("server.port", apiCmd.Flags().Lookup("port"))
@@ -177,6 +178,27 @@ func runAPI(cmd *cobra.Command, args []string) error {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/v1/dedupe", m.Middleware("/v1/dedupe", server.handleDedupe))
 	mux.HandleFunc("/v1/dedupe/stream", m.Middleware("/v1/dedupe/stream", server.handleDedupeStream))
+
+	// Setup memory store (opt-in)
+	enableMemory, _ := cmd.Flags().GetBool("memory")
+	if enableMemory {
+		memDBPath := viper.GetString("memory.db_path")
+		if memDBPath == "" {
+			memDBPath = "distill-memory.db"
+		}
+		memThreshold := viper.GetFloat64("memory.dedup_threshold")
+		if memThreshold == 0 {
+			memThreshold = 0.15
+		}
+		memStore, err := memoryStoreFromConfig(memDBPath, memThreshold)
+		if err != nil {
+			return fmt.Errorf("failed to create memory store: %w", err)
+		}
+		defer func() { _ = memStore.Close() }()
+
+		memAPI := &MemoryAPI{store: memStore, embedder: embedder}
+		memAPI.RegisterMemoryRoutes(mux, m.Middleware)
+	}
 	mux.HandleFunc("/health", server.handleHealth)
 	mux.HandleFunc("/metrics", func(w http.ResponseWriter, r *http.Request) {
 		m.Handler().ServeHTTP(w, r)
@@ -218,6 +240,7 @@ func runAPI(cmd *cobra.Command, args []string) error {
 	fmt.Printf("Distill API server starting on %s\n", addr)
 	fmt.Printf("  Embeddings: %v\n", embedder != nil)
 	fmt.Printf("  Auth: %v (%d keys)\n", server.hasAuth, len(validKeys))
+	fmt.Printf("  Memory: %v\n", enableMemory)
 	fmt.Println()
 	fmt.Println("Endpoints:")
 	fmt.Printf("  POST http://%s/v1/dedupe\n", addr)
 
@@ -0,0 +1,155 @@
+package cmd
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"time"
+
+	"github.com/Siddhant-K-code/distill/pkg/memory"
+	"github.com/Siddhant-K-code/distill/pkg/retriever"
+)
+
+// MemoryAPI handles memory-related HTTP endpoints.
+type MemoryAPI struct {
+	store    *memory.SQLiteStore
+	embedder retriever.EmbeddingProvider
+}
+
+// RegisterMemoryRoutes adds memory endpoints to the given mux.
+func (m *MemoryAPI) RegisterMemoryRoutes(mux *http.ServeMux, mw func(string, http.HandlerFunc) http.HandlerFunc) {
+	mux.HandleFunc("/v1/memory/store", mw("/v1/memory/store", m.handleStore))
+	mux.HandleFunc("/v1/memory/recall", mw("/v1/memory/recall", m.handleRecall))
+	mux.HandleFunc("/v1/memory/forget", mw("/v1/memory/forget", m.handleForget))
+	mux.HandleFunc("/v1/memory/stats", mw("/v1/memory/stats", m.handleStats))
+}
+
+func (m *MemoryAPI) handleStore(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	var req memory.StoreRequest
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		writeJSONError(w, "invalid request body", http.StatusBadRequest)
+		return
+	}
+
+	// Generate embeddings for entries that don't have them
+	if m.embedder != nil {
+		var textsToEmbed []string
+		var indices []int
+		for i, e := range req.Entries {
+			if len(e.Embedding) == 0 && e.Text != "" {
+				textsToEmbed = append(textsToEmbed, e.Text)
+				indices = append(indices, i)
+			}
+		}
+		if len(textsToEmbed) > 0 {
+			ctx, cancel := context.WithTimeout(r.Context(), 30*time.Second)
+			defer cancel()
+			embeddings, err := m.embedder.EmbedBatch(ctx, textsToEmbed)
+			if err != nil {
+				writeJSONError(w, fmt.Sprintf("embedding error: %v", err), http.StatusInternalServerError)
+				return
+			}
+			for i, idx := range indices {
+				req.Entries[idx].Embedding = embeddings[i]
+			}
+		}
+	}
+
+	result, err := m.store.Store(r.Context(), req)
+	if err != nil {
+		writeJSONError(w, err.Error(), http.StatusInternalServerError)
+		return
+	}
+
+	w.Header().Set("Content-Type", "application/json")
+	_ = json.NewEncoder(w).Encode(result)
+}
+
+func (m *MemoryAPI) handleRecall(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodPost {
+		http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	var req memory.RecallRequest
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		writeJSONError(w, "invalid request body", http.StatusBadRequest)
+		return
+	}
+
+	if req.Query == "" && len(req.QueryEmbedding) == 0 {
+		writeJSONError(w, "query or query_embedding is required", http.StatusBadRequest)
+		return
+	}
+
+	// Generate query embedding if not provided
+	if len(req.QueryEmbedding) == 0 && m.embedder != nil && req.Query != "" {
+		ctx, cancel := context.WithTimeout(r.Context(), 10*time.Second)
+		defer cancel()
+		emb, err := m.embedder.Embed(ctx, req.Query)
+		if err != nil {
+			writeJSONError(w, fmt.Sprintf("embedding error: %v", err), http.StatusInternalServerError)
+			return
+		}
+		req.QueryEmbedding = emb
+	}
+
+	result, err := m.store.Recall(r.Context(), req)
+	if err != nil {
+		writeJSONError(w, err.Error(), http.StatusInternalServerError)
+		return
+	}
+
+	w.Header().Set("Content-Type", "application/json")
+	_ = json.NewEncoder(w).Encode(result)
+}
+
+func (m *MemoryAPI) handleForget(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodDelete && r.Method != http.MethodPost {
+		http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	var req memory.ForgetRequest
+	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
+		writeJSONError(w, "invalid request body", http.StatusBadRequest)
+		return
+	}
+
+	result, err := m.store.Forget(r.Context(), req)
+	if err != nil {
+		writeJSONError(w, err.Error(), http.StatusInternalServerError)
+		return
+	}
+
+	w.Header().Set("Content-Type", "application/json")
+	_ = json.NewEncoder(w).Encode(result)
+}
+
+func (m *MemoryAPI) handleStats(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		http.Error(w, "method not allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	stats, err := m.store.Stats(r.Context())
+	if err != nil {
+		writeJSONError(w, err.Error(), http.StatusInternalServerError)
+		return
+	}
+
+	w.Header().Set("Content-Type", "application/json")
+	_ = json.NewEncoder(w).Encode(stats)
+}
+
+func writeJSONError(w http.ResponseWriter, msg string, code int) {
+	w.Header().Set("Content-Type", "application/json")
+	w.WriteHeader(code)
+	_ = json.NewEncoder(w).Encode(map[string]string{"error": msg})
+}