Skip to content
Back to the index

memory-arena

PyPIInfrastructure

PulseGate's liveness check found it on 14 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 1 Jul 2026. How this is checked

memory-arena is an open-source CLI tool for benchmarking and evaluating up to 20 agent-memory strategies for LLMs. It provides a unified evaluator and supports advanced retrievers, helping AI researchers and developers compare memory systems effectively.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI
1star
5features
2026since

Overview

5 features

Purpose: Comparing and benchmarking different agent-memory strategies for LLMs.

Inferred · not functionally tested

Audience: AI researchers and developers

Inferred · not functionally tested

Functions: analytics

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

In the Agent evaluation & testing space, memory-arena takes a focused approach. Inferred · not functionally tested: It focuses on comparing and benchmarking different agent-memory strategies for LLMs. Inferred · not functionally tested: memory-arena is an open-source project aimed at AI researchers and developers. Basis unknown · not verified: memory-arena is open source under the MIT license. Basis unknown · not verified: memory-arena is available on the command line, and it can be self-hosted.

Behind memory-arena is xmpuspus, and it first shipped in 2026. Development happens publicly on GitHub with 9 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are agent-memory benchmarking, multiple strategy support, and unified evaluator.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Agent-memory benchmarking
  • Multiple strategy support
  • Unified evaluator
  • Pure Python
  • MIT license

Topics: Inferred · not functionally tested

Tags
agent-memoryllm-benchmarkrag-evaluationmemory-strategiespython-tool
AI capabilities
Code
Weights: Open

JSON profile · Text profile · Access guide

Built with & integrations

Framework
FastAPI
AI providers
anthropicopenai
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHub · ★ 1Active maintenance

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about memory-arena

What does memory-arena do?
Inferred · not functionally tested: Memory-arena focuses on comparing and benchmarking different agent-memory strategies for LLMs. It is catalogued under Agent evaluation & testing on PulseGate.
Who should use memory-arena?
Inferred · not functionally tested: memory-arena is an open-source project built for AI researchers and developers.
Does memory-arena have a free plan?
Basis unknown · not verified: Yes — memory-arena is open source under the MIT license and free to use.
What platforms does memory-arena run on?
Basis unknown · not verified: memory-arena runs on the command line. It can also be self-hosted.
Is memory-arena still active?
PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 9 commits in the last 90 days.
What are alternatives to memory-arena?
Similar projects tracked by PulseGate include calera-agent-memory, ai-dememory, and aml-memory.calera-agent-memoryai-dememoryaml-memory
Who makes memory-arena?
memory-arena is developed by xmpuspus.
When did memory-arena launch?
memory-arena first shipped in 2026.

Similar projects

Closest matches by what these projects do