Agent activity / project scope

Agent runs

Review what an AI agent did, how long it took, what it cost, and which tools it used.

Recorded runs: 1

Choose a run
Open it
Inspect steps and recorded data

Search and filters

Run	Agent	Recorded	Status	Action
Research answersample.research-answer`8044491c…d889`	research-agentRequested by founder-review	Steps 3 steps Duration 1.25 s Model cost $0.0040 Started 22 Jul, 14:53:01	Succeeded	Open run

Open-source test path

Install and test AgentRail

Install the scoped npm packages or run the local stack from source. npm install agentrail is not this project; that unscoped npm package belongs to another maintainer.

Try from source today

Clone the repository, install dependencies, then seed one run.

pnpm install
pnpm bootstrap:local

Open source checkout

Install from npm

Use the live scoped packages published under @agentrail-sdk.

SDK packagenpm install @agentrail-sdk/sdk

Record traces from a TypeScript AI application.

Context CLInpm install -D @agentrail-sdk/cli

Install local Context Relay commands in a project.

Create Context Packnpx -y @agentrail-sdk/cli context --root . --task "Audit this change" --token-budget 4000 --json

Return a bounded source pack before an AI coding run.

MCP trace readernpx -y @agentrail-sdk/mcp

Inspect AgentRail traces from Codex-style local tools.

MCP Context profilenpx -y @agentrail-sdk/mcp --profile context

Expose Context Relay tools to MCP-capable local agents.

MCP Context profile 0.1.2 is published on npm and can be started through npx.