Back to packageRELEASE DETAILS

0.1.0

PyPI

agentmem-core

A proactive memory layer for long-horizon coding agents, it knows when to remind.

Published14 Jul 2026

Direct dependencies9

Transitive dependenciesNot calculated

README

Version 0.1.0 documentation

agentmem-core

The core of AgentMem: a proactive memory layer for long-horizon coding agents. It maintains a structured memory bank and decides when to remind your agent, instead of dumping everything or retrieving on similarity.

pip install agentmem-core

Published as agentmem-core (the name agentmem was already taken on PyPI by an unrelated project); everything you import and run is still agentmem.

from agentmem import MemorySession, triggers

mem = MemorySession(task="Fix the auth tests without changing the public API")
while not done:
    reminder = mem.pending_context()          # str | None
    reply = call_your_agent(messages, memory_context=reminder)
    mem.observe(reply.new_messages)

Full docs, integrations, and the design rationale live in the main repository.

Licensed under Apache-2.0.

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Declared dependencies 9

Native requirements

9 direct targetsNot calculated transitive count

Package / target	Requirement	Relationship
anthropic Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`anthropic>=0.40`	runtime
pydantic-settings Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pydantic-settings>=2.3`	runtime
pydantic Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pydantic>=2.7`	runtime
claude-agent-sdk Environment { "extras": "", "marker": "extra == \"agent-sdk\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`claude-agent-sdk>=0.2; extra == "agent-sdk"`	runtime
aider-chat Environment { "extras": "", "marker": "extra == \"aider\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`aider-chat<0.87,>=0.86; extra == "aider"`	runtime
agentmem-daemon Environment { "extras": "", "marker": "extra == \"daemon\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`agentmem-daemon; extra == "daemon"`	runtime
litellm Environment { "extras": "", "marker": "extra == \"litellm\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`litellm>=1.40; extra == "litellm"`	runtime
mcp Environment { "extras": "", "marker": "extra == \"mcp\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`mcp<2,>=1.28; extra == "mcp"`	runtime
openai-agents Environment { "extras": "", "marker": "extra == \"openai-agents\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`openai-agents<0.19,>=0.18; extra == "openai-agents"`	runtime