meta-agents-db 0.2.5

Agent-native database with causal memory, composite-scored recall, and storage-layer policy enforcement

meta-agents-db

Agent-native database with causal memory, composite-scored recall, and storage-layer policy enforcement.

The first database designed for autonomous AI agents.

Install

pip install meta-agents-db

Quick start

from meta_agents_db import MetaAgentsDB

db = MetaAgentsDB("./data")
event_id = db.write(content="SPY broke below 200-day MA", tags=["signal", "SPY"])
results = db.recall("SPY bearish signals", top_k=10)
chain = db.trace_cause(event_id, direction="backward", max_depth=5)

Features

• Causal DAG — every memory links to its causes; trace full decision chains
• 5-signal composite recall — vector similarity + recency + causal proximity + importance + tag overlap
• Storage-layer policy — risk caps, budget caps, rate limits enforced at write time
• HNSW vector index — sub-millisecond approximate nearest neighbor search
• Session caching — deduplicates repeated recalls within a pipeline cycle
• MVCC — snapshot isolation for concurrent readers/writers
• WAL + SSTables — crash-safe append-only log with background compaction

License

Apache-2.0