zavora-ai

zavora-ai/adk-rust

Skill Claude CodeCodex

Design and implement ADK-Rust agent workflow patterns including LLM, sequential, parallel, loop, and multi-agent orchestration. Use when building or refactoring agent topology.

zavora-ai/adk-rust

Skill Claude CodeCodex

Bootstrap new ADK-Rust applications with correct crate/features, provider setup, and verification steps. Use when starting a new agent app or converting an existing Rust app to ADK-Rust.

zavora-ai/adk-rust

Skill Claude CodeCodex

Add evaluation, telemetry, and guardrails to ADK-Rust systems as one quality loop. Use when hardening agent behavior before production release.

zavora-ai/adk-rust

Skill Claude CodeCodex

Build and debug ADK graph workflows with checkpoints, routing, interrupts, and state reducers. Use when implementing graph-based orchestration in adk-graph.

zavora-ai/adk-rust

Skill Claude CodeCodex

Select and configure ADK-Rust model providers and feature flags with environment validation. Use when choosing Gemini/OpenAI/Anthropic/DeepSeek/Groq/Ollama/mistralrs for a project.

zavora-ai/adk-rust

Skill Claude CodeCodex

Implement realtime voice agents with ADK-Rust, including audio formats, event handling, and streaming reliability. Use when building or debugging voice interactions in adk-realtime.

zavora-ai/adk-rust

Skill Claude CodeCodex

Use ADK Studio code generation and perform release-readiness checks for ADK-Rust changes. Use when validating generated projects, examples, and release quality gates.

zavora-ai/adk-rust

Skill Claude CodeCodex

Add ADK-Rust tools, MCP integrations, and ADK UI protocol outputs safely. Use when building function tools, MCP toolsets, browser tools, or UI render tools.

zavora-ai/adk-rust

Skill Claude CodeCodex

Run full ADK-Rust workspace verification and produce a findings-first review. Use when validating build/test/lint health, triaging regressions, or preparing merge/release quality reports.

zavora-ai/adk-rust

Skill Claude CodeCodex

Build, debug, and validate ADK Studio projects and generated Rust workflows. Use when working on adk-studio schemas, action nodes, code generation, graph runner behavior, or studio deployment readiness.

zavora-ai/adk-rust

Instructions file CodexOpenCode

AGENTS.md instructions for zavora-ai/adk-rust, covering adk-rust, dev environment, first-time setup, linux / macos — add to /.bashrc or /.zshrc and windows — persist for the current user.

zavora-ai/adk-rust

Agent

A trigger handler is required. The supported path is withinvoker, which takes anything implementing adkcore::AgentInvoker — Runner does.

zavora-ai/adk-rust

Agent

CodeActAgent is a peer to LlmAgent that acts by writing and running code instead of emitting one tool call at a time. Each turn the model produces a single script; tools are exposed as callable functions the script can compose; and the script communicates its result by returning a tagged value.

zavora-ai/adk-rust

Agent

The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.

zavora-ai/adk-rust

Agent

Write agent workflows as normal async Rust functions with automatic checkpointing, typed state reducers, and interrupt/resume support.

zavora-ai/adk-rust

Agent

Build complex, stateful workflows using LangGraph-style orchestration with native ADK-Rust integration.

zavora-ai/adk-rust

Agent

The LlmAgent is the core agent type in ADK-Rust that uses a Large Language Model for reasoning and decision-making.

zavora-ai/adk-rust

Agent

Build sophisticated applications by composing specialized agents into teams.

zavora-ai/adk-rust

Agent

Realtime agents enable voice-based interactions with AI assistants using bidirectional audio streaming. The adk-realtime crate provides a unified interface for building voice-enabled agents that work with OpenAI's Realtime API and Google's Gemini Live API.

zavora-ai/adk-rust

Agent

Workflow agents orchestrate multiple agents in predictable patterns—sequential pipelines, parallel execution, or iterative loops. Unlike LlmAgent which uses AI reasoning, workflow agents follow deterministic execution paths.

zavora-ai/computer-use-mcp

Instructions file CodexOpenCode

Instructions for zavora-ai/computer-use-mcp, covering using computer-use-mcp with ai agents, tool priority guidance, quick setup for any agent, codex and claude (anthropic).

zavora-ai/computer-use-mcp

Skill Claude CodeCodex

Fill desktop form fields using accessibility tools (fillform, setvalue) instead of click+type loops.

zavora-ai/computer-use-mcp

Skill Claude CodeCodex

Recover from FocusFailure and wrong-window input when using computer-use-mcp.

zavora-ai/computer-use-mcp

Skill Claude CodeCodex

Prefer AppleScript/JXA (macOS) or PowerShell (Windows) via runscript before GUI automation.