agentperf
No liveness check has reached it yet; it is registered on GitHub and PyPI and has been in the index since 13 Oct 2026. How this is checked
agentperf is an open-source command-line benchmark for measuring how well a computer supports AI coding agents. It reports performance results and explains the factors that affect agent workloads for developers.
Inferred · not functionally tested
Overview
5 featuresPurpose: Determining whether a computer can run AI coding agents effectively and identifying performance bottlenecks.
Inferred · not functionally tested
Audience: developers evaluating computers for AI coding workloads
Inferred · not functionally tested
Functions: analytics, monitoring
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.
agentperf sits in PulseGate's Testing & QA category. Inferred · not functionally tested: It focuses on determining whether a computer can run AI coding agents effectively and identifying performance bottlenecks. Inferred · not functionally tested: It is built as an open-source project for developers evaluating computers for AI coding workloads. Basis unknown · not verified: agentperf is open source under the MIT license. Basis unknown · not verified: It ships for the command line, and it can be self-hosted.
It is developed by SergeSerb2, and it first shipped in 2026. Development happens publicly on GitHub with 22 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are performance benchmarks, AI agent testing, and bottleneck analysis.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Performance benchmarks
- AI agent testing
- Bottleneck analysis
- Result explanations
- CLI reports
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit 94823eba8ebe · since Oct 2026
Trust & compliance
Indexing history
3What PulseGate has recorded for this listing
Frequently asked questions about agentperf
- What is agentperf?
- Inferred · not functionally tested: Agentperf focuses on determining whether a computer can run AI coding agents effectively and identifying performance bottlenecks. It is catalogued under Testing & QA on PulseGate.
- Who should use agentperf?
- Inferred · not functionally tested: agentperf is an open-source project built for developers evaluating computers for AI coding workloads.
- Does agentperf have a free plan?
- Basis unknown · not verified: Yes — agentperf is open source under the MIT license and free to use.
- What platforms does agentperf run on?
- Basis unknown · not verified: agentperf runs on the command line. It can also be self-hosted.
- Is agentperf still active?
- The GitHub repository shows 22 commits in the last 90 days.
- What are alternatives to agentperf?
- Similar projects tracked by PulseGate include agentloop-profiler, agent-evaluation-lab, and agentprof.agentloop-profileragent-evaluation-labagentprof
- Who makes agentperf?
- agentperf is developed by SergeSerb2.
- How long has agentperf been around?
- agentperf first shipped in 2026.
Similar projects
Closest matches by what these projects do