Minutehand

Minutehand runs your proactive agent through simulated days of work in a few seconds and tells you how well it carried the work. The agent talks to fake Slack, Teams, Asana, Jira, YouTrack, Notion, GitHub, Google Drive and others, with people who answer late or not at all. Minutehand owns the clock, records every change in an append-only log, and runs checks on the result. Each failure names the design that fixes it. A finished run can be forked from a checkpoint with the prompt, the model, a person or the world changed, and played forward again.

The agent's code does not change. Minutehand starts the agent's own command, or reaches one already running, and points it at the fakes through its environment: HTTPS_PROXY, NO_PROXY and a CA bundle.

Install

You need uv. It fetches Python 3.12 if you do not have it.

uv tool install git+https://github.com/Alknoma/minutehand@integration-main

This puts the minutehand command in an environment of its own, apart from your agent's dependencies. Minutehand is not published on PyPI.

Quick start

The example agent is in the repository, so clone it for the example files:

git clone --depth 1 -b integration-main https://github.com/Alknoma/minutehand
cd minutehand/examples/follow_up
python3 -m venv .venv && .venv/bin/pip install slack_sdk    # the agent's one library, in the agent's own Python

minutehand run scenario.yaml --agent agent.yaml -- .venv/bin/python agent.py
# exits 0: Rosa answers after a day and a half, and the agent tells Owen and finishes

AGENT_BEHAVIOUR=forgetful minutehand run scenario_silent.yaml --agent agent.yaml -- .venv/bin/python agent.py
# exits 1: Rosa never answers, the agent never follows up, and no_follow_up names the fix

minutehand runs                  # every run, one line each
minutehand findings <run_id>     # a run's findings again, and the checkpoints it can be forked from
minutehand view                  # the runs in a browser, at http://127.0.0.1:8081/

Each run takes a few seconds. Runs are kept in .minutehand/ in the folder you ran them from. The example's README.md explains both runs line by line.

To try your own agent, write an agent file (minutehand schema agent prints its JSON Schema) and a scenario, check them with minutehand validate, and run minutehand doctor -- <your agent's command> to find any HTTP client in the agent that would go around the proxy.

How the agent touches Minutehand

Almost nothing is required. An agent that takes its goal by message and books its own wakes implements no endpoint. An agent can also take a wake (a POST carrying the simulated now), answer a report (still working, done, when to wake next), take pushed events in each provider's own format, and list its own inboxes for the simulated people to decide. Hosts no fake answers are declared in the agent file: acknowledge, pass through, replay, or forward to an emulator of your own. docs/agent-contract.md lists every touch point, and schemas/agent-api.openapi.json describes the endpoints.

Status

Built and tested (docs/design.md, "What exists", counts the tests for each part):

• The proxy, the run loop, the store (SQLite, one file per run and its forks), forks from a checkpoint with the agent's own state restored and verified, and minutehand serve for test suites that open many worlds at once.
• Providers: Slack, Microsoft Teams and Graph, Asana, Jira, YouTrack, Notion, GitHub, Google Drive with Docs and Slides, AWS EventBridge Scheduler and SQS (through moto), and Google Cloud Tasks over its REST transport.
• 19 checks, the scorecard and 10 patterns. Among them, planned_past_due flags a follow-up that was on time only because something other than the agent's own plan woke it; the loop's table of what was due is recorded to answer that. reported_against_world holds what the agent says it is waiting on against what the world shows.
• Checks of the agent's own, kept beside its agent file (checks:) and run with Minutehand's.
• Dispatch rules: a scenario can deliver the agent's own wakes late, twice or not at all, and a fork can change them (DispatchChange).
• Outbound capture, with --capture-unknown for a first run: reads passes only GET, HEAD and OPTIONS, and model lets a model stand in for a service nobody declared once the agent writes to it.
• The agent's machine: machine: commands in a scenario change files at a moment, and the folders an agent file watches: are recorded as they change. The file_removed expectation reads them.
• MCP: an agent's tool calls are recorded over HTTP through the proxy, and over standard input and output with minutehand mcp-relay. The tool_called expectation reads them. minutehand mcp serves the tools a coding agent uses to run scenarios and read findings.
• The agent's own OpenTelemetry received and joined to the world events it caused; telemetry out over OTLP.
• The run viewer (minutehand view), doctor, validate and schema, and a container image (Dockerfile) that serves by default.

Experimental: Contained, an agent in a gVisor sandbox whose clock Minutehand owns, so timers in the agent's own process become its wakes with no code change. It needs a patched gVisor that is kept outside this repository, and has been run on arm64 only.

Checked by hand, not in the test suite: an agent in containers (docs/containers.md).

Not built: people written by a model, checks a model judges, generated providers, a faked system clock (libfaketime), the hosted service. No fake has been checked against the real service's wire details; each is tested against the service's own client library. docs/design.md, "Known issues", lists the limits of what is built.

Docs

Scenarios to start from

minutehand scenarios lists a library of ready-made situations (a person goes quiet, answers late, is away with a delegate; an approval is rejected or never decided; a deadline moves; a scheduled wake comes late, twice or never). minutehand scenarios new --all --goal ... --owner 'Name <email>' --ask 'Name <email>' writes each out with your values. See docs/scenarios.md.

Develop

From a checkout:

uv sync
uv run pytest -q -n auto
uv run pyright
uv run python -m lints
uv run ruff check . && uv run ruff format --check .

CLAUDE.md is the house rules, CONTRIBUTING.md how to contribute, and docs/lints.md argues each lint. uv tool install . installs the checkout's own minutehand.

Licensed under the Functional Source License 1.1 (Apache-2.0 future licence); see LICENSE.md.