Skip to content
Back to the index

evidenceflow

PyPIInfrastructure

PulseGate's liveness check found it on 5 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 4 Sep 2026. How this is checked

evidenceflow is an open-source Python package for analyzing how retrieved and tool-generated evidence propagates through AI-agent execution traces. It supports evaluation and observability workflows involving retrieval, tool calling, provenance, and information flow.

Inferred · not functionally tested

Open SourceMPL-2.0CLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Tracing how retrieved and tool-generated evidence flows through AI-agent executions.

Inferred · not functionally tested

Audience: AI-agent developers and ML observability engineers

Inferred · not functionally tested

Functions: monitoring, 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: MPL-2.0 · 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.

evidenceflow is a LLM & agent tracing project. Inferred · not functionally tested: It focuses on tracing how retrieved and tool-generated evidence flows through AI-agent executions. Inferred · not functionally tested: evidenceflow is an open-source project aimed at AI-agent developers and ML observability engineers. Basis unknown · not verified: evidenceflow is open source under the MPL-2.0 license. Basis unknown · not verified: evidenceflow is available on the command line, and it can be self-hosted.

It is developed by Eduj Barrios, and it first shipped in 2026. Development happens publicly on GitHub with 11 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include evidence tracing, agent execution analysis, and tool-call tracking.

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

Tasks: Inferred · not functionally tested

  • Evidence tracing
  • Agent execution analysis
  • Tool-call tracking
  • Retrieval analysis
  • Provenance tracking
  • Information-flow analysis

Topics: Inferred · not functionally tested

Tags
agent-tracingevidence-provenancerag-observabilitytool-callinginformation-flow
AI capabilities
TextStructured
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
CLISelf-hosted

Trust & compliance

License
MPL-2.0
Public signals
HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed4 Sep · 13:01 UTC
    evidenceflow seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about evidenceflow

What is evidenceflow?
Inferred · not functionally tested: Evidenceflow focuses on tracing how retrieved and tool-generated evidence flows through AI-agent executions. It is catalogued under LLM & agent tracing on PulseGate.
Who is evidenceflow for?
Inferred · not functionally tested: evidenceflow is an open-source project built for AI-agent developers and ML observability engineers.
Does evidenceflow have a free plan?
Basis unknown · not verified: Yes — evidenceflow is open source under the MPL-2.0 license and free to use.
What platforms does evidenceflow run on?
Basis unknown · not verified: evidenceflow runs on the command line. It can also be self-hosted.
Is evidenceflow still active?
PulseGate's liveness check found it on 5 Oct 2026. Its GitHub repository shows 11 commits in the last 90 days.
Who develops evidenceflow?
evidenceflow is developed by Eduj Barrios.
How long has evidenceflow been around?
evidenceflow first shipped in 2026.
Is evidenceflow open source?
Basis unknown · not verified: Yes — evidenceflow is open source under the MPL-2.0 license, developed on GitHub.

Similar projects

Closest matches by what these projects do