comanda
View on GitHubThe CLI-native orchestrator for AI agent workflows. Run Claude Code, Codex, Gemini CLI & Kimi Code from declarative YAML. Because the terminal is where real work happens.
Go CLI that turns English goals into inspectable YAML agent workflows, coordinating Claude Code, Codex, Gemini CLI, Kimi Code and API/local models. Adds stateful agentic loops, quality gates, codebase indexes/knowledge graphs, semantic memory, and an MCP server.
Use Cases
Run Claude Code, Codex, Gemini CLI and Kimi Code from declarative YAML workflowsOrchestrate multi-agent parallel review with distinct rolesDurable self-improving agentic loops with automated quality gatesGenerate and iteratively improve workflows from English descriptionsExpose checked-in workflows as MCP tools and skills as MCP promptsCapture codebase indexes and traverse a knowledge graphBounded project-local semantic memory recall for promptsRun git-diff pipelines through agent workflows in CIServe workflows as HTTP or OpenAI-compatible endpointsIsolate parallel agent implementations using git worktrees
Built With
- Language
- Go
- Frameworks
- MCP Go SDK · Cobra · Bubbletea · go-openai · Google Generative AI Go · AWS Bedrock Runtime · Ollama · vLLM · llama.cpp · PostgreSQL/SQLite FTS5
Tags
cli · yaml · workflow-orchestration · multi-agent · coding-agents · agentic-loops · quality-gates · mcp · semantic-memory · knowledge-graph · codebase-index · git-worktrees · terminal · automation · stateful-checkpoints · go