Skip to content
Back to the index

agentprof

PyPIInfrastructure

No liveness check has reached it yet; it is registered on GitHub and PyPI and has been in the index since 9 Oct 2026. How this is checked

agentprof is an open-source command-line tool for analyzing AI coding agent sessions. It provides call trees, timing data, token usage, cost analysis, and waste detection for developers working with coding agents.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Understanding the execution, token usage, cost, and inefficiencies of AI coding agent sessions.

Inferred · not functionally tested

Audience: developers and AI engineering teams

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.

In the LLM & agent tracing space, agentprof takes a focused approach. Inferred · not functionally tested: It focuses on understanding the execution, token usage, cost, and inefficiencies of AI coding agent sessions. Inferred · not functionally tested: agentprof is an open-source project aimed at developers and AI engineering teams. Basis unknown · not verified: agentprof is open source under the MIT license. Basis unknown · not verified: It ships for the command line, and it can be self-hosted.

Behind agentprof is epicodic, 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 6 catalogued features are call trees, timing analysis, and token tracking.

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

Tasks: Inferred · not functionally tested

  • Call trees
  • Timing analysis
  • Token tracking
  • Cost analysis
  • Waste detection
  • Session profiling

Topics: Inferred · not functionally tested

Tags
ai-agent-observabilitycoding-agent-profilingtoken-cost-analysisllm-call-tracing
AI capabilities
TextCodeStructured

JSON profile · Text profile · Access guide

Built with & integrations

Written with
Claude Code
Runs on
CLISelf-hosted
Written with — evidence
Claude Code
commit 6f2d0af8f94e · since Oct 2026

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceGitHubActive maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed8 Oct · 23:06 UTC
    agentprof seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about agentprof

What does agentprof do?
Inferred · not functionally tested: Agentprof focuses on understanding the execution, token usage, cost, and inefficiencies of AI coding agent sessions. It is catalogued under LLM & agent tracing on PulseGate.
Who should use agentprof?
Inferred · not functionally tested: agentprof is an open-source project built for developers and AI engineering teams.
Does agentprof have a free plan?
Basis unknown · not verified: Yes — agentprof is open source under the MIT license and free to use.
What platforms does agentprof run on?
Basis unknown · not verified: agentprof runs on the command line. It can also be self-hosted.
Is agentprof still active?
The GitHub repository shows 9 commits in the last 90 days.
What are alternatives to agentprof?
Similar projects tracked by PulseGate include agentloop-profiler, agentcost-cli, and coding-agent-cost.agentloop-profileragentcost-clicoding-agent-cost
Who develops agentprof?
agentprof is developed by epicodic.
When did agentprof launch?
agentprof first shipped in 2026.

Similar projects

Closest matches by what these projects do