Ax is a TypeScript-first programming framework for building applications with large language models through typed generation, agents, workflows, and optimization tools. It is intended for developers who want one model for LLM programs across TypeScript, Python, Java, C++, Go, Rust, and other runtimes.
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.
npx skills add ax-llm/ax --skill ax-python-gepagit clone --depth 1 https://github.com/ax-llm/axWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ax-llm/ax/ax-python-gepa)<a href="https://agentmods.dev/skills/ax-llm/ax/ax-python-gepa"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-python-gepa/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ax-llm/ax/ax-python-gepa"><img src="https://agentmods.dev/badge/skills/ax-llm/ax/ax-python-gepa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00037 | $0.00418 |
| Opus 5.5 | $0.00015 | $0.00167 |
| Sonnet 5.5 | $0.00007 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
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 yesterday.
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.
This is a copy
66% identical to ax-cpp-playbook — 29 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.
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.mdandaxir-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-apiexamples only when the user explicitly has provider credentials available. - Use
no-keyexamples 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.
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.
- yesterday Changed 3ebfe211fb84
- 2d ago Changed 092825aeda3d
- 4d ago Changed 5f1acf3b39ea
- 6d ago Changed c342abdb5fca
- 8d ago Changed b576341054eb
- 11d ago Changed fa80846aec2b
- 12d ago Changed 8b0c719ed090
- 13d ago Changed 4dcecc824017
- 19d ago Changed a3b03df10783
- 22d ago First seen · 46 lines · 37 tokens per session scan A bc4e3d7f3229
ax-python-gepa is a skill published in the GitHub repository ax-llm/ax (2,967 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 418 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 66% identical to ax-cpp-playbook, differing in 29 lines, and is treated as a copy.
Other skills, from other repositories
claude-api
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
migrating-llm-gateway-callers
Migrates an LLM caller from services/llm-gateway to PostHog/ai-gateway. Use when adding a gateway caller, converting an existing Python gateway integration, adopting shared Go-capable client builders, changing gateway URLs or headers for a caller, or removing a Python fallback. Inventories the caller's contract…
migrate-from-ai-sdk
Use when porting an app from the Vercel AI SDK (ai, @ai-sdk/) to @deuz-sdk/core. Triggers include "migrate from the AI SDK", "replace ai with @deuz-sdk/core", "we use streamText/generateText/useChat and want to switch", removing @ai-sdk/openai or @ai-sdk/anthropic, porting a toUIMessageStreamResponse route, converting…
model-context
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
build-mcp-server
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.