EPISODIC MEMORY  ·  VECTOR + KEYWORD  ·  AES-256

Persistent memory for
every AI agent.

CHRONICLE stores, retrieves, and evolves agent memory across sessions. Hybrid search. Encrypted. Self-hostable. Drop-in compatible with LangChain, CrewAI, and OpenAI.

Memory depth
< 50ms
Retrieval speed
AES-256
Encrypted at rest
Docker
Self-hostable

Store. Search. Evolve.

Three operations. Infinite possibilities. CHRONICLE handles the entire memory lifecycle so your agents don’t have to.

Step 01

Store

Agents write memories as structured events — decisions, observations, user context, outcomes. CHRONICLE timestamps, tags, and encrypts every entry automatically.

Step 02

Search

Hybrid vector + keyword retrieval returns the most relevant memories in under 50ms. Semantic similarity finds context even when exact terms differ.

Step 03

Evolve

Memories consolidate over time. Frequently accessed and emotionally salient entries strengthen. Stale memories decay gracefully, keeping context sharp.

Four layers of cognition.

CHRONICLE models human-inspired memory architecture so agents think and recall like intelligent systems, not SQL queries.

EPISODIC

What happened

Ordered sequences of events with timestamps, actors, and outcomes. Gives agents autobiographical recall — every session, decision, and interaction persisted with full context.

Timestamp + causality + actor chain
SEMANTIC

What it knows

Facts, relationships, and concepts organized in a queryable knowledge graph. Agents accumulate durable beliefs about users, domains, and the world — surviving session boundaries.

Entity + relation + confidence score
PROCEDURAL

How to do things

Skill memories encoding successful action sequences, tool-use patterns, and step-by-step workflows. Agents learn from what worked and refine their capabilities over time.

Action sequence + success rate + context
WORKING

Right now

Active context window management for in-progress reasoning. CHRONICLE tracks which memories are in active use, ensuring agents never lose their current thread across tool calls.

Attention weights + recency decay

Drop-in for any
framework.

One pip install. Works with every major AI framework out of the box — LangChain, CrewAI, OpenAI Assistants, and raw HTTP for custom stacks.

LangChain CrewAI OpenAI REST API
pip install chronicle-client
from chronicle import ChronicleMemory # Initialize with your agent's identity memory = ChronicleMemory( api_key="chron_sk_...", agent_id="agent-prod-1", ) # Store a memory (async-safe) memory.store( "User prefers concise responses", type="semantic", tags=["preferences", "style"], ) # Hybrid search — vector + keyword results = memory.search( "user communication style", limit=5, types=["semantic", "episodic"], )
Response
{
  "memories": [
    {
      "id": "mem_8f3a2d1c",
      "content": "User prefers concise responses",
      "type": "semantic",
      "score": 0.97
    }
  ],
  "relevance_scores": [0.97, 0.84, 0.71],
  "total": 3
}
Retrieved in 23ms

Built for production agents.

Every feature your AI memory layer needs — without the complexity of rolling your own.

Hybrid vector + keyword search

Combines dense vector embeddings with BM25 keyword matching. Get the best of semantic similarity and exact-term recall in a single ranked result set.

AES-256 encryption

Every memory is encrypted at rest using AES-256-GCM and in transit with TLS 1.3. Your agent's context never leaves your control unencrypted.

Cross-session persistence

Memories survive restarts, redeploys, and crashes. Agents resume exactly where they left off — no cold-start amnesia, no lost context.

Agent isolation

Each agent operates in a private, cryptographically separated memory namespace. No cross-contamination between agents, tenants, or environments.

Memory consolidation

Important and frequently accessed memories strengthen over time. CHRONICLE's consolidation engine ensures the most relevant context always surfaces first.

Self-hostable Docker container

Full data sovereignty with a single Docker image. Run on your own infrastructure — cloud, on-prem, or air-gapped. No vendor lock-in, no egress fees.

Simple, transparent pricing.

All plans include AES-256 encryption, hybrid search, and drop-in framework adapters. No seat fees. No surprises.

Free
$0 /mo

Start persisting memory today, no credit card required.

  • 50,000 memories
  • 1 agent
  • Basic search
  • API access
Get Started →
Professional
$199 /mo

For high-throughput agent systems.

  • 5M memories
  • 100 agents
  • All features
  • Analytics dashboard
  • Priority support
Get Started →
Enterprise
$999 /mo

For regulated and large-scale deployments.

  • Unlimited memories
  • Unlimited agents
  • SLA guarantee
  • Dedicated support
  • Custom data residency
Contact Sales →

Give your agents
perfect memory.

Deploy in minutes. Self-host on your own infrastructure or use our managed cloud. No configuration required.

docker pull garmolabs/chronicle && docker run -p 8080:8080 garmolabs/chronicle