Skip to content
Back to the index

maf-cachebench

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 7 Aug 2026. How this is checked

maf-cachebench is an open-source benchmark for Microsoft Agent Framework compaction strategies. It measures prompt-cache impact and information loss using replayed conversations or live agents, helping developers compare agent context-management approaches.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Measuring how agent conversation compaction strategies affect prompt-cache hits and retained information.

Inferred · not functionally tested

Audience: developers building with Microsoft Agent Framework

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.

maf-cachebench sits in PulseGate's Agent evaluation & testing category. Inferred · not functionally tested: It focuses on measuring how agent conversation compaction strategies affect prompt-cache hits and retained information. Inferred · not functionally tested: It is built as an open-source project for developers building with Microsoft Agent Framework. Basis unknown · not verified: maf-cachebench is open source under the MIT license. Basis unknown · not verified: maf-cachebench is available on the command line, and it can be self-hosted.

sokolaidev builds and maintains maf-cachebench, and it first shipped in 2026. The project is developed in the open on GitHub with 9 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are compaction benchmarking, prompt-cache analysis, and conversation replay.

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

Tasks: Inferred · not functionally tested

  • Compaction benchmarking
  • Prompt-cache analysis
  • Conversation replay
  • Live-agent testing
  • Information-loss measurement
  • Strategy comparison

Topics: Inferred · not functionally tested

Tags
prompt-cache-benchmarkingconversation-compactionagent-frameworkreplay-testing
AI capabilities
Text

JSON profile · Text profile · Access guide

Built with & integrations

Written with
Claude Code
Runs on
CLISelf-hosted
Written with — evidence
Claude Code
commit 6d9dfbb6ba55 · since Oct 2026

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

10

What PulseGate has recorded for this listing

  1. Indexed7 Oct · 09:17 UTC
    maf-cachebench seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open
  2. Indexed6 Oct · 17:25 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  3. Indexed4 Oct · 14:20 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  4. Indexed28 Sep · 19:50 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  5. Indexed26 Sep · 14:32 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  6. Indexed24 Sep · 19:19 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  7. Indexed23 Sep · 07:41 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  8. Indexed22 Sep · 19:21 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  9. Indexed21 Sep · 14:09 UTC
    maf-sandbox-bicep seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  10. Indexed7 Aug · 22:57 UTC
    maf-sandbox-bicep seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about maf-cachebench

What is maf-cachebench?
Inferred · not functionally tested: Maf-cachebench focuses on measuring how agent conversation compaction strategies affect prompt-cache hits and retained information. It is catalogued under Agent evaluation & testing on PulseGate.
Who is maf-cachebench for?
Inferred · not functionally tested: maf-cachebench is an open-source project built for developers building with Microsoft Agent Framework.
Does maf-cachebench have a free plan?
Basis unknown · not verified: Yes — maf-cachebench is open source under the MIT license and free to use.
What platforms does maf-cachebench run on?
Basis unknown · not verified: maf-cachebench runs on the command line. It can also be self-hosted.
Is maf-cachebench still maintained?
PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 9 commits in the last 90 days.
Who makes maf-cachebench?
maf-cachebench is developed by sokolaidev.
How long has maf-cachebench been around?
maf-cachebench first shipped in 2026.
Is maf-cachebench open source?
Basis unknown · not verified: Yes — maf-cachebench is open source under the MIT license, developed on GitHub.

Similar projects

Closest matches by what these projects do