ACE - LLM

Query any LLM from the terminal with one interface across API and CLI providers. ACE Logo

Gem Version Ruby License: MIT

Works with: Claude Code, Codex CLI, OpenCode, Gemini CLI, pi-agent, and more.

Getting Started | Usage Guide | Handbook - Skills, Agents, Templates

ace-llm demo

ace-llm gives developers and coding agents one command surface for querying any LLM provider. Address models by alias (gflash, sonnet), explicit provider:model notation, or with thinking levels (codex:gpt:high) and execution presets (cc@ro). Pass prompts and system instructions inline or as file paths, or start supported CLI providers in native interactive mode with --interactive. Fallback routing and retry behavior keep prompt workflows resilient.

Testing

Package-local verification contract:

ace-test ace-llm
ace-test ace-llm feat
ace-test ace-llm all
ace-test-e2e ace-llm

Deterministic coverage lives in test/fast/ and test/feat/. Scenario assets stay in test/e2e/.

How It Works

  1. Select a model — by alias, provider:model, with a thinking level suffix (:low/:medium/:high), or an @preset — and submit a prompt.
  2. The provider router resolves the target through ace-llm-providers-cli adapters, applying fallback and retry rules from the config cascade.
  3. The response is returned as text, markdown, or JSON with optional token usage metadata.

Use Cases

Switch providers with aliases - use short names like gflash, sonnet, opus instead of full provider:model notation. Aliases resolve through versioned YAML in .ace-defaults/.

Control reasoning depth - append a thinking level (codex:gpt:high, claude:sonnet:low) to tune reasoning budgets. Supported CLI providers: claude, codex (levels: low, medium, high, xhigh).

Run preset-driven prompts - apply execution profiles with @preset or --preset. Built-in presets for CLI providers: @ro (read-only), @rw (read-write), @yolo (full autonomy). Supported by: claude, codex, gemini, opencode, pi.

Launch real interactive agents - use --interactive for supported CLI providers so alias resolution, presets, and skill translation still flow through ace-llm, but the provider starts its native terminal UI instead of one-shot print mode.

Build resilient prompt workflows - configure fallback chains and retry behavior through the config cascade so transient provider issues do not block work.

Power LLM-enhanced flows in sibling packages - serve as the execution backend for ace-git-commit, ace-idea, ace-review, ace-sim, ace-prompt-prep, and more.

Getting Started | Usage Guide | Handbook - Skills, Agents, Templates | Part of ACE