What is ax-python-gepa?

A Python workflow for using AxLLM's GEPA optimizer, which improves generated results through reflection, evaluation metrics, and competing candidate versions.

Use it to run GEPA, seed it with example demonstrations through BootstrapFewShot, track optimizer state and reflection calls, and inspect optimization artifacts.

It helps manage the repeated evaluation and refinement needed when generated output must improve within a limited budget.

ax-python-gepa — Skill by ax-llm

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/ax-llm/ax/ax-python-gepa

Any agent

npx skills add ax-llm/ax --skill ax-python-gepa

Clone the repo

git clone --depth 1 https://github.com/ax-llm/ax

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 418 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin 86% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00037	$0.00418
Opus 5	$0.00018	$0.00209
Sonnet 5	$0.00007	$0.00084
Haiku 4.5	$0.00004	$0.00042

Measured today against content hash 718b486a3bfb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ax-python-gepa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

86% identical to ax-java-gepa — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

packages/python/skills/ax-python-gepa/SKILL.md · 46 lines

What it actually says

Ax GEPA For Python

This skill helps an agent write Python code with the generated Ax package axllm. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package.

When To Use

Run the generated GEPA optimizer or inspect a GEPA artifact.
Use BootstrapFewShot before GEPA when demonstrations should seed optimization.
Track metric budgets, reflection calls, candidate state, and Pareto fronts.

Package Facts

Language: Python.
Package: axllm.
Package API docs: API.md and axir-api.json.
Capability manifest: axir-capabilities.json.
Runnable examples: examples/.
Real network support: yes.
Scripted no-key transport support: yes.
Runtime profiles: javascript-quickjs, python-pyodide.

Core Pattern

from axllm import AxGEPA

engine = AxGEPA(reflection_client)
result = engine.optimize(request, evaluator)

Relevant API Surface

Optimizers: optimize, playbook, AxPlaybook, AxBootstrapFewShot, AxGEPA, OptimizerEngine, OptimizerEvaluator

Guardrails

Start from package examples for exact native syntax before inventing a new call shape.
Use provider-api examples only when the user explicitly has provider credentials available.
Use no-key examples for deterministic local checks and provider request mapping.
Treat AxIR as the source of generated package truth: if package docs disagree with source code, update the compiler and regenerate packages.
Do not copy repo-maintainer skills from tools/*/skills/ into user packages.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed 718b486a3bfb
3d ago First seen · 46 lines · 37 tokens per session scan A f5020afcaf96

Subscribe to this mod's changes

ax-python-gepa is a skill published in the GitHub repository ax-llm/ax (2,890 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 418 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to ax-java-gepa, differing in 22 lines, and is treated as a copy.

Data and AI LLM Languages Python ai cohere javascript openai

python-sdk

Python SDK patterns for Opik. Use when working in sdks/python, on SDK APIs, integrations, or message processing.

comet-ml/opik · 28 tokens

dali-dynamic-mode

DALI imperative dynamic mode (nvidia.dali.experimental.dynamic, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.

NVIDIA/skills · 38 tokens

datachain-core

Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.

datachain-ai/datachain · 54 tokens

ax-python-gepa