MemState - Transactional Memory for AI Agents

Agents hallucinate because their memory drifts. SQL says one thing, the Vector DB says another. MemState keeps them in sync, always.

Mental Model: MemState extends database transactions to your Vector DB.
One unit. One commit. One rollback.

Documentation: https://scream4ik.github.io/MemState/

Source Code: https://github.com/scream4ik/MemState

Quick Start

pip install memstate[chromadb]

from pydantic import BaseModel
from memstate import MemoryStore, SQLiteStorage, HookError
from memstate.integrations.chroma import ChromaSyncHook
import chromadb

# 1. Define Data Schema
class UserPref(BaseModel):
    content: str
    role: str

# 2. Setup Storage (Local)
sqlite = SQLiteStorage("agent_memory.db")
chroma = chromadb.Client()

# 3. Initialize with Sync Hook
mem = MemoryStore(sqlite)
mem.add_hook(ChromaSyncHook(chroma, "agent_memory", text_field="content", metadata_fields=["role"]))
mem.register_schema("preference", UserPref)

# 4. Atomic Commit
# Validates Pydantic model -> Writes SQL -> Upserts Vector
try:
    mem.commit_model(model=UserPref(content="User prefers vegetarian", role="preference"))
except HookError as e:
    print("Commit failed, SQL rolled back automatically:", e)

# 5. Undo (if needed)
# mem.rollback(1)

👉 See full Documentation & Examples

The Problem

AI agents usually store memory in two places: SQL (structured facts) and Vector DB (semantic search).

These two stores drift easily. If a network request to the Vector DB fails, or the agent crashes mid-operation, you end up with "Split-Brain" memory:

• SQL: "User lives in London"
• Vector DB: "User lives in New York" (Stale embedding)

Result: The agent retrieves wrong context and hallucinates.

Key Features

MemState acts as a Consistency Layer between your agent and its storage.

• Atomic Commits: SQL and Vector DB stay in sync. If one fails, both rollback.
• Async & Fast: Full asyncio support for high-performance FastAPI/LangGraph apps.
• Type Safety: Pydantic validation prevents LLMs from corrupting your JSON schema.
• Hybrid Search: Search by meaning (Vector), filter by facts (SQL).
• Time Travel: Undo N steps with rollback(n). Great for user corrections.

Proof: Benchmark under failure

1000 memory updates with 10% random vector DB failures:

Why 900 instead of 1000? MemState refuses partial writes.
If vector sync fails, SQL is rolled back automatically.

Manual sync produces silent drift.
Drift compounds over time, stale embeddings keep being retrieved forever.

Full benchmark script: benchmarks/

Ecosystem

LangGraph Integration

from memstate.integrations.langgraph import MemStateCheckpointer

checkpointer = MemStateCheckpointer(memory=mem)
app = workflow.compile(checkpointer=checkpointer)

Status

Beta. The API is stable. Suitable for production agents that require high reliability.

Read the Docs | Report an Issue

License

Apache 2.0 - see LICENSE

Contributing

Issues and PRs welcome. See CONTRIBUTING.md for details.