Practical notes: 8 Best Free Vector Databases for AI Agents in 2026

This walkthrough rebuilds the path from raw materials to a working system for: 8 Best Free Vector Databases for AI Agents in 2026. The focus is operable steps, explicit checks, and code that you can drop into a repo without guessing intent. For the Overview stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.

TL;DR

When working through the TL DR stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

How We Evaluated These Databases

When working through the How We Evaluated These stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

The 8 Best Free Vector Databases for AI Agents

When working through the The 8 Best Free stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

1. VectorAI DB Community Edition

When working through the 1 VectorAI DB Community stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

# VectorAI DB -- basic similarity search.

from actian_vectorai import VectorAIClient, VectorParams, Distance

with VectorAIClient("localhost:6574") as client:
    client.collections.create(
        "agent_memory",
        vectors_config=VectorParams(size=768, distance=Distance.Cosine),
    )

    client.points.upsert(
        "agent_memory",
        points=[{"id": 1, "vector": [0.1] * 768, "payload": {"text": "example memory"}}],
    )

    results = client.points.search(
        "agent_memory",
        query_vector=[0.1] * 768,
        limit=5,
    )

2. Qdrant

When working through the 2 Qdrant stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

# Qdrant -- basic similarity search.
from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance, PointStruct

client = QdrantClient(url="http://localhost:6333")

client.create_collection(
    collection_name="agent_memory",
    vectors_config=VectorParams(size=768, distance=Distance.COSINE),
)

client.upsert(
    collection_name="agent_memory",
    points=[PointStruct(id=1, vector=[0.1] * 768, payload={"text": "example memory"})],
)

results = client.query_points(
    collection_name="agent_memory",
    query=[0.1] * 768,
    limit=5,
)

3. Weaviate

When working through the 3 Weaviate stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

# Weaviate -- basic similarity search.
import weaviate
from weaviate.classes.config import Configure
from weaviate.classes.query import MetadataQuery

client = weaviate.connect_to_local()

memories = client.collections.create(
    name="AgentMemory",
    vector_config=Configure.Vectors.self_provided(),
)

memories.data.insert(
    properties={"text": "example memory"},
    vector=[0.1] * 768,
)

response = memories.query.near_vector(
    near_vector=[0.1] * 768,
    limit=5,
    return_metadata=MetadataQuery(distance=True),
)

client.close()

4. Milvus

When working through the 4 Milvus stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

# Milvus -- basic similarity search.
from pymilvus import MilvusClient

client = MilvusClient(uri="http://localhost:19530", token="root:Milvus")

client.create_collection(collection_name="agent_memory", dimension=768)

client.insert(
    collection_name="agent_memory",
    data={"id": 1, "vector": [0.1] * 768, "text": "example memory"},
)

results = client.search(
    collection_name="agent_memory",
    data=[[0.1] * 768],
    limit=5,
)

5. ChromaDB

When working through the 5 ChromaDB stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node. When working through the 5 ChromaDB stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.

# ChromaDB -- basic similarity search.
import chromadb

client = chromadb.PersistentClient(path="./agent_memory")
collection = client.get_or_create_collection(name="agent_memory")

collection.add(
    ids=["1"],
    embeddings=[[0.1] * 768],
    documents=["example memory"],
)

results = collection.query(
    query_embeddings=[[0.1] * 768],
    n_results=5,
)

6. LanceDB

The 6 LanceDB stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

# LanceDB -- basic similarity search.
import lancedb

db = lancedb.connect("./agent_memory")

table = db.create_table(
    "agent_memory",
    data=[{"id": 1, "vector": [0.1] * 768, "text": "example memory"}],
)

results = table.search([0.1] * 768).limit(5).to_list()

7. pgvector

The 7 pgvector stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

# pgvector -- basic similarity search.
import psycopg
from pgvector.psycopg import register_vector

conn = psycopg.connect("dbname=agent_memory")
register_vector(conn)

conn.execute("CREATE EXTENSION IF NOT EXISTS vector")
conn.execute(
    "CREATE TABLE IF NOT EXISTS memories (id bigserial PRIMARY KEY, "
    "text text, embedding vector(768))"
)
conn.execute(
    "INSERT INTO memories (text, embedding) VALUES (%s, %s)",
    ("example memory", [0.1] * 768),
)

results = conn.execute(
    "SELECT text FROM memories ORDER BY embedding <-> %s LIMIT 5",
    ([0.1] * 768,),
).fetchall()

8. Pinecone

The 8 Pinecone stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts. The 8 Pinecone stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.

# Pinecone -- basic similarity search.
from pinecone import Pinecone, ServerlessSpec
import os

pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])

pc.create_index(
    name="agent-memory",
    dimension=768,
    metric="cosine",
    spec=ServerlessSpec(cloud="aws", region="us-east-1"),
)

while not pc.describe_index("agent-memory").status["ready"]:
    pass

index = pc.Index("agent-memory")
index.upsert(vectors=[("1", [0.1] * 768, {"text": "example memory"})])

results = index.query(vector=[0.1] * 768, top_k=5)

How to Choose

For the How to Choose stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish. Put human approval on edges that spend money or change production data. Compile-time wiring does not equal business completeness.

Operational checklist

The Operational checklist stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope.

Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

Add a smoke test that exercises the critical path in CI with fixtures, not live paid APIs, whenever budgets allow.

Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.

Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

Before promoting the stack, freeze versions, capture a golden transcript for the critical path, and confirm rollback steps. Shared environments need rate limits, tenancy checks, and a clear owner for secret rotation. Prefer boring reliability over clever one-off demos.

Batch note for 470145f5d4e7: keep provider keys out of the repo, set a per-session token ceiling, and store transcripts next to the eval fixtures so later model swaps stay comparable.

When working through the hardening note 0 stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

Hardening detail 0/772: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

The hardening note 1 stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish.

Hardening detail 1/772: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

For the hardening note 2 stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion.

Hardening detail 2/772: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

When working through the hardening note 3 stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph.

Hardening detail 3/772: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

The hardening note 4 stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.

Hardening detail 4/772: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

The hardening note 0 stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline.

Hardening detail 0/791: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.

For the hardening note 1 stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

Hardening detail 1/791: measure wall time, error class, and token spend for this note, then decide whether to keep the change based on a fixed question set rather than anecdote.