Skip to content
v0.2 · Pre-production

Multi-agent orchestration,
built for production.

Set one API key. Commander classifies the task, picks the right topology, and streams every agent decision to your terminal. No black boxes. 6700+ tests, no graph builders, no YAML.

Commander terminal streaming multi-agent execution
25
LLM providers
5
Canonical topologies
18
Built-in tools
6700+
Tests

See every decision

Deliberation, topology, tools, and quality gates stream live — not after the fact. Copy, set a key, and watch agents work.

git clone https://github.com/PStarH/Commander.git
cd Commander && pnpm install
export OPENAI_API_KEY=sk-...
npx tsx packages/core/src/cliEntry.ts run "audit this repo" --stream

What Commander does

Six core capabilities, each backed by production-grade infrastructure and audited in CI.

Why Commander

Built for engineers who want to see what their AI is actually doing.

You are the engineer, not a passenger

Other frameworks hide agent graphs behind YAML and hope. Commander streams every thought, tool call, and quality gate so you can debug and trust the run.

No graph builders. No YAML.

Describe the task in plain language. Deliberation classifies it, picks a topology, and scales agents 1–20. Simple tasks stay simple.

Production primitives, not demos

Circuit breakers, DLQ, saga compensation, SQLite WAL checkpoints, semantic cache, multi-tenancy — the same discipline as a distributed system.

One key, twenty-five providers

Set any API key. Auto-detect + failover across cloud and local models (Ollama, vLLM). Swap providers without rewriting your workflow.

Start where you are

Three paths into the same engine.

Ready to orchestrate?

One command, 25 providers, every decision visible. Set an API key and go.

MIT Licensed — Built for multi-agent orchestration.