The memory engine for AI that actually knows you.

pip install yantrikdbcargo add yantrikdb

---

The Problem

Every AI memory solution does the same thing:

Store everything. Embed. Retrieve top-k. Inject into context. Hope it helps.

That doesn’t model how memory works. It treats all memories as equal. Old memories never fade. Contradictions are never detected. Nothing is ever consolidated. The AI never proactively remembers anything.

YantrikDB fixes all of this.

Relevance-Conditioned Scoring

Relevance gates every other signal multiplicatively. A perfectly relevant old memory surfaces. An irrelevant high-importance memory doesn’t. This is the key insight — patented and proven.

Cognitive State Graph

Typed nodes (beliefs, goals, intents, preferences) with typed edges (supports, contradicts, causes, predicts). Your AI doesn’t just remember — it reasons about what it knows.

Autonomous Cognition

Consolidation merges related memories. Conflict detection flags contradictions. Pattern mining discovers recurring themes. All automatic via db.think().

Proactive Triggers

Decaying memories, unresolved conflicts, emerging patterns — YantrikDB tells your AI when to act, grounded in real data. Not engagement farming.

Five Unified Indexes

Vector (HNSW), graph, temporal, decay heap, and key-value — all in one embedded SQLite database. No server. No infrastructure. Just a file.

MCP Server

pip install yantrikdb-mcp — instant persistent memory for Claude Code, Cursor, Windsurf, and any MCP-compatible AI agent.

---

See It In Action

from yantrikdb import YantrikDB

db = YantrikDB("memory.db", embedding_dim=384)

# Remember — with importance and emotional valence
db.record("User prefers Python over JavaScript", importance=0.7)
db.record("User is stressed about Friday's deadline", importance=0.9, valence=-0.6)

# Recall — relevance-conditioned scoring, not just cosine similarity
results = db.recall("What's bothering the user?", top_k=5)
# → Returns the deadline stress memory (high relevance × high importance × recent)

# Relate — build the cognitive graph
db.relate("user", "deadline", "stressed_about", weight=0.9)

# Think — autonomous cognition loop
result = db.think()
# → Consolidates similar memories, detects contradictions, mines patterns
# → Returns proactive triggers: "User's deadline is approaching, stress is high"

---

Architecture

Index	What It Does	Example Query
Vector (HNSW)	Semantic similarity search	”What did the user say about work?”
Graph	Entity relationships & reasoning	”Who works at what company?”
Temporal	Time-aware retrieval	”What happened last Tuesday?”
Decay Heap	Importance with biological time decay	Memories fade like human memory
Key-Value	Instant fact lookup	”User’s timezone is CST”

All five indexes query the same data. A single recall() call blends signals from all of them into one relevance-conditioned score.

---

How It’s Different

	Vector DB	RAG Pipeline	YantrikDB
Storage	Flat embeddings	Chunked documents	Typed memories with metadata
Retrieval	Cosine top-k	Hybrid search	Relevance-conditioned scoring
Time	Ignored	Ignored	Temporal decay + recency
Contradictions	Undetected	Undetected	Automatic conflict detection
Consolidation	None	None	Autonomous merging
Proactive	Never	Never	Trigger-based notifications
Graph	Separate system	None	Built-in cognitive state graph

---

Patent

U.S. Patent Application No. 19/573,392 (filed March 2026) — covers relevance-conditioned scoring, the cognitive state graph, and the unified system architecture.

Open source under AGPL-3.0. The patent protects the methods, not the code. Use it freely. Read more →

---

Part of the Yantrik Ecosystem

Component	Description	License
YantrikDB	Cognitive memory engine	AGPL-3.0
YantrikDB MCP	MCP server for AI agents	MIT
Yantrik ML	Pluggable AI inference — LLM, embeddings, vision, TTS	AGPL-3.0
Yantrik Companion	AI agent with instincts, tools, and personality	AGPL-3.0
Yantrik OS	AI-native desktop operating system (Rust + Slint)	AGPL-3.0

Built by one person. All open source. Get started →