mentedb 0.17.0

The mind database for AI agents

MenteDB Python SDK

Python bindings for MenteDB, the mind database for AI agents. Built with PyO3 and maturin for native Rust performance from Python.

Installation

From source (development)

cd sdks/python
pip install maturin
maturin develop

From PyPI (once published)

pip install mentedb

On Debian and Ubuntu systems pip refuses system wide installs (PEP 668). Use a virtual environment or pipx:

python3 -m venv .venv && .venv/bin/pip install mentedb
# or: pipx install mentedb

Quick start

from mentedb import MenteDB

with MenteDB("./agent-memory") as db:
    # process_turn — the primary API, one call does everything
    result = db.process_turn(
        user_message="The deployment failed because the config was missing",
        assistant_response="I'll check the config setup.",
        turn_id=0,
    )
    # result.context — relevant memories for your prompt
    # result.facts_extracted — what was learned this turn
    # result.contradiction_count — conflicting beliefs detected
    # Optional kwargs: project_context, agent_id, session_id (tags stored
    # turns so injection recall can exclude the requesting session)

    # Sleeptime enrichment runs automatically after process_turn:
    # - Extracts semantic facts from conversations
    # - Links and deduplicates entities
    # - Builds community summaries and user profile
    # Requires LLM config: MENTEDB_OPENAI_API_KEY or MENTEDB_ANTHROPIC_API_KEY

    # Or use low-level APIs directly:

    # Store a memory
    mid = db.store(
        "The deployment failed because the config was missing",
        memory_type=MemoryType.EPISODIC,
        tags=["deployment", "config"],
    )

    # Recall memories with MQL
    result = db.recall("RECALL tag:deployment LIMIT 5")
    print(result.text)

    # Vector similarity search
    hits = db.search(embedding=[0.1] * 384, k=5)
    for hit in hits:
        print(f"{hit.id}: {hit.score:.4f}")

    # Relate memories
    mid2 = db.store("Always validate config before deploy", memory_type=MemoryType.PROCEDURAL)
    db.relate(mid, mid2, edge_type=EdgeType.CAUSED)

    # Forget a memory
    db.forget(mid)

MenteDB Cloud (hosted)

Prefer a managed API with no engine to run? Use MenteDBClient with an mdb_ key from app.mentedb.com. The verbs mirror the embedded client, so only the constructor changes.

from mentedb import MenteDBClient

client = MenteDBClient(api_key="mdb_...")

# Turn 0: tell it something.
client.process_turn("I switched from Postgres to SQLite for side projects", "Noted.", 0)

# Turn 1: it remembers.
result = client.process_turn("what database am I using for side projects?", "", 1)
for memory in result.context:
    print(memory.content)

# Also available: client.search(...), client.store(...),
# client.store_multimodal(data, media_type=...), client.forget(memory_id)

MenteDBClient is pure standard library (no extra dependencies) and talks to https://api.mentedb.com. process_turn uses the REST endpoint, while store, search, store_multimodal, and forget use the hosted MCP tools.

Cognitive features

The SDK also exposes MenteDB cognitive subsystems for real time stream monitoring, conversation trajectory tracking, and pain signal management.

Sleeptime Enrichment

MenteDB automatically enriches memories in the background after process_turn. The pipeline extracts semantic facts, links and deduplicates entities, groups them into communities with summaries, and builds a user profile — all feeding back into future process_turn context retrieval.

Requires an LLM provider: set MENTEDB_OPENAI_API_KEY or MENTEDB_ANTHROPIC_API_KEY. Without one, the engine works normally — enrichment just doesn't run.

Cognitive subsystems

from mentedb._mentedb_python import CognitionStream, TrajectoryTracker, PainRegistry

# Stream monitoring
stream = CognitionStream(buffer_size=500)
stream.feed_token("The")
stream.feed_token(" sky")
alerts = stream.check_alerts([("some-uuid", "the sky is blue")])

# Trajectory tracking
tracker = TrajectoryTracker(max_turns=50)
tracker.record_turn("deployment", "investigating", ["which env?"])
context = tracker.get_resume_context()

# Pain registry
pain = PainRegistry(max_warnings=3)
pain.record_pain("some-uuid", 0.8, ["timeout", "deploy"], "deploy timed out")
warnings = pain.check_triggers(["deploy"])

API reference

MenteDB

Method	Description
process_turn(user_message, assistant_response, turn_id, project_context, agent_id)	Primary API. Process a conversation turn through the full cognitive pipeline
store(content, memory_type, embedding, agent_id, tags)	Store a memory, returns its UUID
recall(query)	Recall memories using MQL
search(embedding, k)	Vector similarity search
relate(source, target, edge_type, weight)	Add a relationship
forget(memory_id)	Remove a memory
close()	Flush and close the database

Types

MemoryType: episodic, semantic, procedural, anti_pattern, reasoning, correction

EdgeType: caused, before, related, contradicts, supports, supersedes, derived, part_of

License

Apache 2.0. See the repository root LICENSE file for details.