Memory Management Python Packages

circular-dict

CircularDict is a high-performance Python data structure that blends the functionality of dictionaries and circular buffers. Inheriting the usage of traditional dictionaries, it allows you to define constraints on size and memory usage. Ideal for caching large data structures while maintaining control over memory footprint.

librmm-cu12

NVIDIA RMM is a library for allocating and managing GPU memory in C++ and Python.

rmm-cu12

NVIDIA RMM is a library for allocating and managing GPU memory in C++ and Python.

cognee

Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free

librmm-cu13

NVIDIA RMM is a library for allocating and managing GPU memory in C++ and Python.

rmm-cu13

NVIDIA RMM is a library for allocating and managing GPU memory in C++ and Python.

everos

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

skills-tree

The universal, platform-agnostic skills and capability registry for AI agents — mapping capabilities, skills, implementations, dependencies, evidence, and platform adapters across agent ecosystems.

memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

stress-injector

Python script, to inject memory, CPU and URL stress

anneal-memory

Living memory for AI agents with an immune system. Episodes compress into identity. Zero dependencies, works with any client.

memtether

Cross-client AI memory hub — one physical SQLite, many clients. File-level pointers, REST API, Web Dashboard, MCP. Zero cloud. Dual-timeline governance. PyPI: memtether

compressed-lists

Memory-efficient container for list-like objects

memanto

Memory that AI Agents Love!

memoryos

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

agent-memguard

Local-first MCP memory governance for coding agents — Codex, Claude Code, Cursor, Grok, and Trae. Shared rules, deduplication, token insights, audit, and rollback.

memnos

Persistent memory for AI coding agents — MCP server, REST API & Python SDK. Works with Claude Code, Cursor, Windsurf and any LLM agent.

memnos-sdk

Persistent memory for AI coding agents — MCP server, REST API & Python SDK. Works with Claude Code, Cursor, Windsurf and any LLM agent.

pointers-py

Bringing the hell of pointers to Python.

loci-rag

A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.

mnemo-db

On-prem, MCP-native memory for AI agents in regulated settings: every write lands in a SHA-256 hash-chained log an auditor can verify offline, without trusting the store or the vendor. Rust, embedded, Apache-2.0.

mnemolink

Curated, injectable personas and artificial memories for AI agents.

memmachine-client

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

stormlog

GPU memory profiler for PyTorch, JAX & TensorFlow — real-time monitoring, leak detection, OOM flight recording, distributed analysis, and interactive TUI.