Registry / ai-ml / cafitac-agent-memory

cafitac-agent-memory

JSON →
library0.1.162pypypiunverified

Reusable memory runtime for AI agents. Current version 0.1.162, rapid development with frequent releases. Designed to provide persistent, structured memory for agentic workflows.

pip install cafitac-agent-memory
INSTALL
IMPORT
SIG · CAFITAC-AGENT-MEMO
C
cafitac-agent-memory
ai-mlpythonv0.1.162
harness data pending
Install & Compatibility
Where this runs

No compatibility data collected yet for this library.

Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

InMemoryMemory
from agent_memory import InMemoryMemory
from cafitac_agent_memory.memory import InMemoryMemory

Initialize in-memory memory, save and load agent memory by user ID.

import os from cafitac_agent_memory.memory import InMemoryMemory memory = InMemoryMemory() memory.save('user_id', {'key': 'value'}) print(memory.load('user_id'))
Debug
Known issues
breakingVersion 0.1.0 renamed the main class from 'Memory' to 'InMemoryMemory' and changed the import path from 'cafitac.agent_memory' to 'cafitac_agent_memory'.
fix
Update imports: from cafitac_agent_memory.memory import InMemoryMemory
affects: <0.1.0
gotchaPersistentMemory requires a configured database backend (e.g., SQLite path). Using default may silently fail if not set up.
fix
Initialize PersistentMemory with a valid database URL: PersistentMemory(url='sqlite:///agent_memory.db')
affects: >=0.1.0
deprecatedThe 'save' method signature changed in 0.1.50: parameter 'namespace' was removed in favor of separate 'memory_context'.
fix
Use memory.save(user_id, data, memory_context='default') instead of namespace parameter.
affects: >=0.1.50
Upgrade
Version history
0.1.162latest on PyPI · released May 15, 2026
Audit
Dependencies

No dependency data recorded yet.

Agent activity
26 hits · last 30 days
node
22
Resources
cafitac-agent-memory — pip install cafitac-agent-memory · libregistry