Skip to content
Back to the index

peekai

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

peekai is an open-source CLI tool for local-first observability and debugging of Python-based AI agents. It offers agent tracing, replay, and debugging features to help developers understand and improve their AI workflows. Ideal for AI researchers and developers working with LLM agents.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI
7stars
1fork
5features
2026since

Overview

5 features

Purpose: Enabling developers to debug and observe Python AI agents locally without relying on cloud services.

Inferred · not functionally tested

Audience: AI developers and researchers

Inferred · not functionally tested

Functions: 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, peekai takes a focused approach. Inferred · not functionally tested: Enabling developers to debug and observe Python AI agents locally without relying on cloud services. Inferred · not functionally tested: peekai is an open-source project aimed at AI developers and researchers. Basis unknown · not verified: peekai is open source under the MIT license. Basis unknown · not verified: peekai is available on the command line, and it can be self-hosted.

Oussama KH builds and maintains peekai, and it first shipped in 2026. Development happens publicly on GitHub with 32 commits in the last 90 days. Inferred · not functionally tested: Among its 5 catalogued features are agent tracing, debugging tools, and replay sessions.

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

Tasks: Inferred · not functionally tested

  • Agent tracing
  • Debugging tools
  • Replay sessions
  • Local observability
  • Python integration

Topics: Inferred · not functionally tested

Tags
agent-observabilitypython-debugginglocal-ai-tools
AI capabilities
Code
Weights: Open

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
anthropicopenai
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tierGitHub · ★ 7Active maintenance

Indexing history

What PulseGate has recorded for this listing

Nothing recorded for this listing in this window.

Frequently asked questions about peekai

What does peekai do?
Inferred · not functionally tested: Enabling developers to debug and observe Python AI agents locally without relying on cloud services. It is catalogued under LLM & agent tracing on PulseGate.
Who is peekai for?
Inferred · not functionally tested: peekai is an open-source project built for AI developers and researchers.
Does peekai have a free plan?
Basis unknown · not verified: Yes — peekai is open source under the MIT license and free to use.
What platforms does peekai run on?
Basis unknown · not verified: peekai runs on the command line. It can also be self-hosted.
Is peekai still active?
PulseGate's liveness check found it on 14 Sep 2026. Its GitHub repository shows 32 commits in the last 90 days.
Who makes peekai?
peekai is developed by Oussama KH.
When did peekai launch?
peekai first shipped in 2026.
Is peekai open source?
Basis unknown · not verified: Yes — peekai is open source under the MIT license, developed on GitHub.

Similar projects

Closest matches by what these projects do