AxAI Providers For Go

Use when writing Go code with github.com/ax-llm/ax/packages/go for provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

Install

Install only this skill for Go:

npx skills add https://ax-llm.github.io/ax/go/ --skill 'ax-go-ai'

Published skill file: ax-go-ai/SKILL.md.

Source

• Source: packages/go/skills/ax-go-ai/SKILL.md
• Version: 23.0.4

Skill Instructions

This skill helps an agent write Go code with the generated Ax package github.com/ax-llm/ax/packages/go. Use the generated package API, examples, and manifests; do not import TypeScript-only APIs unless you are editing the TypeScript package.

When To Use

• Create provider clients or normalize provider options.
• Choose between model-list routing, ordered failover, and adaptive operational routing.
• Use scripted transports for deterministic no-key examples.
• Use provider-api examples only when explicit provider credentials are available.

Package Facts

• Language: Go.
• Package: github.com/ax-llm/ax/packages/go.
• 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-goja.

Core Pattern

import ax "github.com/ax-llm/ax/packages/go"

llm := ax.NewAI("openai", map[string]ax.Value{"apiKey": os.Getenv("OPENAI_API_KEY")})

Routing And Balancing

• Use the multi-service router when a logical model key selects a configured service or concrete model. It combines model lists; it does not learn from outcomes.
• Use the default AxBalancer for deterministic ordered/metric failover with its existing retry policy.
• Opt into AxBalancerAdaptiveStrategy only for operational routing among application-approved equivalent aliases. It learns transient reliability and successful latency, combines them with estimated cost and a deadline, and explores with Thompson sampling.
• Put centralized decision state in an AxBalancerStatsStore. The routing-event callback is best-effort analytics and observability, not a state replication mechanism.
• Shared stores require non-empty, unique, stable route keys. Use slices to isolate workflows, tenants, or traffic classes without putting prompts, responses, raw errors, or sensitive identifiers in keys or events.
• Adaptive balancing does not measure answer quality or semantically choose a model. Only group routes that the application already accepts as substitutes.
• Generated streaming APIs are buffered: a provider error can fail over before the completed result is returned, and success latency is recorded after completion.
• Start with examples/adaptive_balancer_no_key for store/reducer syntax, then use the cataloged provider-backed adaptive-balancer example for a complete two-route setup.

Relevant API Surface

• AxAI: axllm.NewAI, axllm.OpenAICompatibleClient, axllm.OpenAIResponsesClient, axllm.GoogleGeminiClient, axllm.AnthropicClient, axllm.AxUsageContext, axllm.AxUsageEvent, axllm.AxUsageObserver, axllm.SetUsageObserver, axllm.AxBalancer, axllm.AxBalancerAdaptiveStrategy, axllm.AxBalancerStatsStore, axllm.AxInMemoryBalancerStatsStore, axllm.CreateBalancerRouteStats, axllm.UpdateBalancerRouteStats, axllm.SampleBalancerRouteHealth, axllm.MultiServiceRouter, axllm.ProviderRouter

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.