RESOURCES · DOCS · AGENT STUDIO · QUICKSTART

From install to a signed replay in sixty seconds.

Install the desktop app or open the browser edition. Connect to a sample MCP server. Record a tool call. Replay it. Export the regression artifact.

INSTRUMENT READOUT · FIRST SESSION
STEP 01 · INSTALL AND OPEN

Local-first by default.

Desktop gets stdio MCP, the local OTLP receiver, OS keychain storage, sandbox mode, and signed update wiring from the shared Open Studio Platform shell.

The browser edition is intentionally smaller: remote SSE and HTTP MCP, A2A card testing, IndexedDB trace storage, and BYO provider keys protected by a passphrase.

↳ COMMANDS
brew install auraoneai/open/agent-studio-open
agentstudio sample filesystem --open
agentstudio connect --stdio "npx -y @modelcontextprotocol/server-filesystem ./sample-data"
STEP 02 · FIRST REPLAY

Record, replay, and keep it.

Use Compose to call a tool. Press Record before sending. The session appears in Trace Browser with tool calls, model messages, latency, cost estimates, and risk annotations.

Replay with the same model to verify determinism. Export a GitHub Action or a JUnit report when the sequence should become release coverage.

01

Connect to a sample MCP server

Pick filesystem, fetch, or sqlite from the sample drawer. The connection panel shows transport, latency, and the manifest counts.

↳ CHECK
02

Confirm Manifest Inspector renders

Tools, Resources, Prompts, and JSON tabs all populate. Risk findings show up in the side rail.

↳ CHECK
03

Send a schema-backed tool call

Use Compose to call a tool with the form view, then switch to JSON to confirm the wire-level payload.

↳ CHECK
04

Replay and export a trace card

Replay the session against the same model to verify determinism, then export a trace card or a GitHub Action.

↳ CHECK
STEP 03 · EXPORT THE ARTIFACT

One command becomes a release gate.

The exported .ast trace is portable. Drop it into a GitHub Action, a JUnit pipeline, a PR comment, or an AuraOne intake packet. The next release has to clear it.

↳ EXPORT
agentstudio record --session refund-path
agentstudio replay refund-path.ast --compare anthropic,openai
agentstudio export refund-path.ast --github-action --out .github/workflows/agentstudio.yml
agentstudio export refund-path.ast --junit --out reports/agentstudio.xml
QUICKSTART

Next time, it's already a replay.

You shipped one trace. Repeat the loop on the path that actually broke. That is the regression bank.

60-second quickstart | Agent Studio Open Docs