agent-framework-memorysync

MemorySync for the Microsoft Agent Framework: agents that remember users across sessions — without ever stalling a run.

pip install agent-framework-memorysync

Quick start

from agent_framework import Agent
from agent_framework_memorysync import MemorySyncContextProvider

provider = MemorySyncContextProvider(
    api_key="ms_...",          # or MEMORYSYNC_API_KEY
    user_id="customer-42",     # required — who these memories belong to
    session_id="support",      # scopes the transcript
)

agent = Agent(client=..., context_providers=[provider])
result = await agent.run("which seat should I book?")

Every run recalls relevant memories into the instructions layer under a hard budget, and both sides of the exchange persist automatically after the run — no extra code per turn.

Why this one

Semantics worth knowing

• Turns store verbatim under the agent-framework::<session> transcript scope — separate history, same shared user memories as every other MemorySync surface.
• The resolved run identity is pinned in the provider's session-state slice, so recall and capture can never diverge within a run — and the slice stays JSON-native, so AgentSession serialization keeps working.
• expose_search_tool=True adds search_memory + save_memory tools via context.extend_tools.
• Free-tier quota exhaustion is silent by design (adds accepted-without- storing, reads empty); evaluation keys surface strict 429s.

Configuration

Development

pip install -e . agent-framework-core pytest pytest-asyncio
python -m pytest tests -q     # 21 tests incl. a REAL Agent run (stub chat client)

License

MIT