fenic
v0.13.0 open-sourceSemantic DataFrames for humans and agents
Summary
fenic is an open-source semantic DataFrame engine that turns AI-assisted exploration of structured and unstructured data into reusable, inspectable DataFrame pipelines, and it uses a permissive license. Developers run it as a Python library via pip install. It is designed for data processing workflows, placing it in the ai-infrastructure category. Its documentation describes it as being for creating durable artifacts from varied data sources like logs and documents, and it has seen active development with recent usage noted in the README.
Semantic DataFrames for humans and agents
What fenic answers
What kinds of data sources does fenic incorporate?
documents, transcripts, logs, eval traces, tickets, tables, and APIs
Does it offer tools for making the pipelines usable by both humans and autonomous agents?
both humans and agents author, inspect, and reuse the resulting pipelines
How does fenic manage the execution of the model calls within a workflow?
it compiles and runs the pipeline on a query engine built for inference, handling automatic batching, rate limiting, retries, and response caching
What methods are available for ensuring that code written by AI coding agents is structured correctly?
a mechanism to install necessary skills and a tool to lint the resulting code
When building a pipeline, how is the underlying query execution engine configured?
developers configure models once on a Session object
Examples
Command line
No option matches that search.
| option | found in | since | description |
|---|
No option matches that search.
Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.
Release history
- v0.13.0
fenic v0.13.0 adds Gemini 3.7 Flash support, drops Claude Opus 4.1, and extends Python compatibility to 3.13 and 3.14.
└──▷ GET THIS VERSION$ git clone --branch v0.13.0 https://github.com/typedef-ai/fenic.git # already have the repo? check out this version: $ git checkout v0.13.0
- ›Adds support for Gemini 3.7 Flash as a new language model backend.
- ›Extends Python version support to include Python 3.13 and 3.14.
- ›Removes retired Claude Opus 4.1 from the list of supported models.
└──▷ BREAKING ON UPGRADE- !Claude Opus 4.1 has been removed; pipelines configured to use it will break on upgrade.
- v0.12.0
fenic v0.12.0 adds Claude Opus 5, Gemini 3.6 Flash and 3.5 Flash-Lite model support, and MCP documentation service migration.
└──▷ GET THIS VERSION$ git clone --branch v0.12.0 https://github.com/typedef-ai/fenic.git # already have the repo? check out this version: $ git checkout v0.12.0
- ›Adds support for Anthropic Claude Opus 5 as a configurable language model.
- ›Adds support for Google Gemini 3.6 Flash and 3.5 Flash-Lite as configurable language models.
- ›Migrates the Fenic documentation service to MCP.