v0.1.0 — Now Open Source

Memory Engine
for AI Agents

Hybrid vector + BM25 search, knowledge graphs, deterministic analytics, and fact supersession in a single Rust binary. Self-host or deploy on our platform with one click.

Get Started Free Sign In Book a Demo

tellodb serve --port 5001

● ENGINE: tellodbdb_core v0.1.0 [Active]ONLINE

Retrieval p994.2ms

Memory Blocks142,850

Memory Substrates Loaded

✓HNSW Vector Index

✓BM25F Full-Text Search

✓Knowledge Graph Engine

✓Temporal Truth Decay

✓Metric Vault (Math)

✓Air-Gapped Proxy Gateway

$ tellodb query "user preferences"
> Ingesting fact... "prefer jasmine tea over coffee"
> Fact supersession resolved. Invalidation complete.

Learn how the engine works →

Interactive Demo

Live Memory Simulation.

Experience Tellodb's real-time ingestion and recall loop. Store a fact, then retrieve it across model contexts.

STEP 1

Ingestion Layer

Write Pipeline

Demo Memory Session Key

Memories are stored and queried using this unique key. It isolates your demo session and persists across reloads.

Raw Memory Input string

Ingest Latency (Engine)

---

Ingest Latency (Network RTT)

---

STEP 2

Truth Retrieval

Read Substrate

Memory Query (Semantic Search)

Query Latency (Engine)

---

Query Latency (Network RTT)

---

Retrieved Memory Hits

No memories retrieved yet. Ingest a fact first.

The Cognition Problem

Standard RAG is amnesiac.

Vector databases are giant warehouses of static text. They find words, but they do not understand life. They lose context, ignore the passage of time, and drown in their own noise.

Standard Vector DB

Amnesiac & Static
Retrieves conflicting data from 2 years ago exactly like data from 2 minutes ago. No concept of evolving truth.
Fails at Counting
Cannot accurately aggregate or count facts (e.g. 'How many cars do I own?'). Relies entirely on the LLM to do math.
Bloated Storage
Stores every single conversational 'uh' and 'um' instead of maintaining a clean, structured user profile.

Tellodb Memory Engine

Fact Supersession (Temporal Truth)
When life changes (e.g. moving from NYC to SF), Tellodb marks the old fact as stale, ensuring the LLM always gets the latest truth.
Deterministic Aggregation
Built-in execution layer accurately computes numeric and temporal queries before hitting the LLM, fixing benchmark failures.
Predict-Calibrate Profile
Distills thousands of words into compact, continuous user profiles. We track the deltas, you save on context windows.

Recall Precision Benchmarks

LongMemEval-S Suite

100%75%50%25%0%

68%

Standard RAG

95%+

Tellodb

Tellodb resolves standard vector search failures. In memory tasks with high fact-density, the local hybrid architecture ensures precise recall.

Temporal Fact Evolution

Supersession State

2025 (STALE)"Living in NYC"

Today (ACTIVE)"Moving to SF"

Fact Invalidation Complete

When newer truths supersede older context, the engine automatically tags prior states as stale, filtering them out from active agent context.

The Distillation Loop

We do not store text.
We extract truth.

Raw chat logs are noise. Tellodb acts as a cognitive filter, distilling human rambling into a clean, queryable lattice of facts.

Time-Awareness

I used to love coffee, but now I only drink tea. Tellodb does not hallucinate your old preferences. It updates your profile in real time.

Fact Distillation

Our engine automatically discards greetings and filler, keeping only the high-value semantic facts that actually matter for personalization.

User: "Hey! I just bought a white Mercedes!"

Raw Chat

Distillation Kernel

Rust Semantic Filter v0.1.0

Fact: User owns Mercedes (White)

Committed to memory lattice

The Human Touch

One brain,
infinite applications.

Our White Mercedes engine ensures your user's identity is not locked inside a single chat window.

The First Spark (May 12)

Hey! I just bought a white Mercedes! What should I do first?

GPT-4o detects: User Ownership → Vehicle: Mercedes (White)

Tellodb Ingests

Fact Integration

Fact: Owns Mercedes

Context: Initial Purchase

3 Months Later (Aug 20)

What was that maintenance tip for my car?

Claude 3.5 recalls: "For your white Mercedes, I recommend..."

Core Capabilities

Engineered for AI Scale.

Tellodb replaces complex, slow orchestration chains with a unified, high-performance cognitive database engine.

Rust Performance Core

Engineered in Rust with sub-100ms p99 query latencies, zero GC pauses, and compiled as a single air-gapped binary.

Fact Supersession

Time-aware rankings and TTL decay policies automatically tag older context as stale when new conflicting facts arrive.

Deterministic Analytics

Built-in arithmetic and count aggregation calculated directly on the database B-Tree indexes before LLM delivery.

Multi-Model Continuity

Switch cognitive backends (GPT-4, Claude 3.5, Llama 3) without losing memory state or query syntax history.

OpenAI Proxy Path (Coming Soon)

Drop-in proxy gateway that automatically injects relevant context into OpenAI-compatible system instructions. In development.

Graph Knowledge Base

Self-organizing RDF typed graph representations mapping relationships between user sessions and profile history.

Recall Engine Latency

<100ms

Average p99 Recall

Built natively in Rust. Delivers sub-100ms queries under heavy semantic and full-text loads.

Runtime Configuration

engine: Tellodb
routes: /ingest /query/semantic /query/temporal /memory
indexes: hnsw + bm25 + graph lineage
policy: ttl + decay + supersession
sdk: python + javascript

ProductionLocal-FirstModel-Agnostic

The Architecture of Truth

Sentient Memory Pipeline.

Tellodb is not just storage; it is a multi-stage cognitive processor that transforms raw noise into reliable agentic state.

IngestRaw Events

Distill & StoreCognitive Controller

HNSWBM25GRAPH

Final TruthGrounded Context

Intent-Aware Filtering

Automatically detects if the user is asking for numbers, preferences, or narrative history.

Neural Reranking

Applies a secondary precision pass to ensure the top-k candidates are semantically perfect.

Deterministic Compute

Computes aggregates (sums, counts) before delivery, preventing LLM arithmetic errors.

Interactive Graph

Sentient Memory Lattice.

Experience how Tellodb organizes memories. Drag nodes to interact with the underlying graph logic where new facts supersede the old.

Active Truth

Superseded Memory

Nodes represent discrete semantic facts, preferences, and entities stored within the Rust engine.

Red nodes indicate **superseded memories**—stale data that has been automatically invalidated by more recent truths.

Delivery Path

From prototype to
production memory.

The product has a clear progression: ingest fidelity, retrieval intelligence, and operational reliability.

Phase 01

Ingest and Distill

Raw events are normalized, deduplicated, and expanded into durable memories with lineage.

Companion memories
Dedup table
Graph relationships

Phase 02

Retrieve and Rerank

Semantic and lexical candidates are fused, reranked, then filtered by temporal policy before response.

HNSW + BM25
Cross-rerank
RRF + policy filters

Phase 03

Ship and Operate

Teams deploy one memory engine surface from local bench runs to hosted multi-tenant workloads.

SDK parity
Benchmarked quality
Operational playbooks

Book A Session

Schedule a 30-minute walkthrough.

Discuss database architecture, memory integration, and private deployment setups for your agentic applications.

Open Calendly Email Instead

Build Agents That
Actually Remember.

One binary, five memory substrates, zero lock-in. Start building persistent, self-improving agents today.

Get Started Free Book a Demo

Two Ways to Remember

Engine and Platform

Tellodb Core

Open Source Engine

The Rust-powered temporal memory engine that runs anywhere. Hybrid vector + BM25 search, knowledge graph traversal, deterministic analytics, and fact supersession — all in a single binary. No vendor lock-in.

▸Single binary — download and run locally
▸4 HNSW indexes + BM25F + redb KV + typed graph
▸Candle / ONNX embeddings, CPU or GPU targets
▸Embed directly in your custom agent architecture

Read the Docs Contact Us

Tellodb Platform

Managed Cloud Service

A full SaaS experience on top of the core engine. Deploy clusters in one click, manage your team, track usage with analytics, explore knowledge graphs visually, and never worry about infrastructure.

▸One-click cluster provisioning — no config files
▸Stripe integration — pay-as-you-go or flat-rates
▸Team management with invites and RBAC roles
▸Graph explorer, telemetry, and visual playground

Get Started Free Explore Platform Documentation

The Tellodb Ecosystem

Integrate Memory Anywhere.

We provide the tooling to make persistent memory a first-class citizen in your development workflow, from local testing to global scale.

Memory Enginefor AI Agents