Skip to main content
Loopcaptain: monitor and steer your agent loops from one local board. An open protocol lets any loop report to it.

CI Docs PyPI Python License

Loopcaptain is an open protocol for agent loops and a local dashboard to monitor and steer them: a human in the loop without a chat window. Alpha: protocol 1 only grows, so a loop written today keeps working; the board may change.

How it works. On the left, a loop in any repository: a script that pastes the helper from LOOPS.md, or an agent session that uses the MCP server. Both write the loop's folder, .loops/loop-id, with loop.json, events.jsonl and inbox.jsonl. On the right, the board on this machine reads the folder and shows every loop, one loop in detail, and the protocol to copy. Your answer, a stop or a start goes back through inbox.jsonl, which the loop reads at its next round.

Get started

Paste one line into your coding agent, whichever you use.

Start a new loop

Use Loopcaptain to build an agent loop in this repository: follow https://github.com/faviens/loopcaptain/blob/v0.9.1/standard/AGENTS.md.

Connect a loop you have

Connect the agent loops on this machine to the Loopcaptain board: follow https://github.com/faviens/loopcaptain/blob/v0.9.1/AGENTS.md, section A.

The board

Every loop on your machine on one page: what waits for you, what needs a look, what runs, what it cost. One loop in detail: whether it converges, every round and what each reviewer found, and where you answer, steer, stop or start it.

The board's front page with eight invented loops in four projects: one waits for an answer, some run, others need a look, each with its rounds, open findings, time and cost.

Waiting for you: a loop's question with two answer buttons and a box for your own words. One loop: key figures, rounds against the cap, and a line per measure showing whether it converges.

The rounds of one loop: every round against every step, and one round with what each step did, found and cost. Open findings of one loop: what the last reviewed round left open, by reviewer, each with your call on it.

Invented loops, photographed from the board itself: make shots.

Setup

uv tool install loopcaptain    # or put uvx in front of the two lines below
loopcaptain demo               # writes the example loop and puts it on the board
loopcaptain serve              # the board, on this machine only

Open the address serve prints in a browser: it lets that browser in. The example loop costs nothing, no model and no network: press Start, answer its question with a button and watch it end done. It needs Python 3.12 or later, on macOS or Linux, and uv, pipx or pip. From a checkout: make setup && make demo && make serve.

It works with any loop that can write a file: a script, a Ralph loop, a long-running session of a coding agent (Claude Code's /loop, Codex's goal mode, for example), a loop built on an agent framework. None of them is needed: a loop has no dependency and never imports this repository. The documentation has Installation, Get started and Setup.

Steer a loop: answer, note, stop, start

  1. Answer. A loop that asks shows its question on the board, with buttons where it offered choices. Your answer is one signed line in the loop's inbox.jsonl; the loop reads it at its next round.
  2. Note. The same line without a question: a direction for the next round.
  3. Stop. The loop finishes the round it is in and ends. loopcaptain doctor checks that a loop really takes a stop.
  4. Start. The board runs the one command the loop declared in its own loop.json, without a shell, after you tick it once.

The loop protocol

A loop does not import this repository. It writes a few small files into .loops/<loop-id>/ in its own repository; the board reads them and writes the person's answers back.

File Written by Holds
loop.json the loop what it is: the brief, the steps of a round, its caps, its start command
events.jsonl the loop, appending what happened: rounds, steps, findings, cost, metrics, questions
inbox.jsonl the board, signed what you sent: answers, notes, a stop

The whole protocol is one page, standard/LOOPS.md. A Python loop pastes a helper of under 110 lines, standard/loops.py; an agent session uses the MCP server, which every coding agent adds its own way: docs/agents.md.

An agent loop runs an agent on one task again and again, until a bar is met or a cap is reached. One pass is a round: a few steps, usually one that makes something and others that judge it. A reviewer is such a judging step: it reads what the round made and lists what is wrong, as findings. A loop reports by appending one line per thing that happened to .loops/<loop-id>/events.jsonl. One round, in which a reviewer finds a fault and the loop asks you what to do:

{"ts": "2026-11-14T21:03:00Z", "event": "round_started", "round": 1, "plan": "Draft the memo"}
{"ts": "2026-11-14T21:09:40Z", "event": "step_finished", "round": 1, "step": "build", "cost": {"usd": 0.34}}
{"ts": "2026-11-14T21:12:10Z", "event": "step_finished", "round": 1, "step": "facts", "findings": [{"id": "1", "text": "The 40 percent has no source", "severity": "material"}]}
{"ts": "2026-11-14T21:12:30Z", "event": "step_finished", "round": 1, "step": "gate", "passed": false, "summary": "One material finding is open"}
{"ts": "2026-11-14T21:12:31Z", "event": "question", "id": "q1", "text": "Drop the figure?", "options": [{"id": "yes", "label": "Drop it"}, {"id": "no", "label": "Find a source"}]}
{"ts": "2026-11-14T21:12:32Z", "event": "round_finished", "round": 1, "verdict": "wait"}

Connect a loop by hand

  1. A script (Python, shell, anything): paste the helper from standard/LOOPS.md and call it where a round and a step begin and end, or append the JSON lines yourself.
  2. A Ralph loop or any loop around an agent's command line: the shell form, loopcaptain emit <loop> <event> key=value, once per iteration.
  3. A long-running agent session: add the MCP server (loopcaptain mcp-config <agent>), and the session reports its rounds through five tools.

standard/AGENTS.md walks an agent through each, and through building a loop from nothing.

Commands

loopcaptain serve                         # the board, 127.0.0.1 only
loopcaptain watch <folder> [--root]       # show a repository, or every one under a folder
loopcaptain demo                          # the example loop, written and watched
loopcaptain validate <repository>         # check a repository's .loops folders
loopcaptain doctor <repository> <loop>    # does the loop take a stop?
loopcaptain mcp-config <agent>            # how your agent adds the MCP server
loopcaptain emit <loop> <event> key=value # one event from a shell loop

From a checkout, put uv run in front, or use the make targets in AGENTS.md.

How it differs

  1. A dashboard for one kind of loop watches the loops of its own runner. Loopcaptain watches any loop that writes the protocol's files.
  2. A session monitor shows an agent's live session and its transcript. Loopcaptain shows what sits above: rounds, steps, findings, verdicts, cost and the question that waits for you.
  3. A loop runner or control plane runs the loop. Loopcaptain runs none: it is a protocol and a board, and your loop stays your own.
  4. Agent observability traces model calls. Loopcaptain sends and takes no telemetry; docs/opentelemetry.md maps the protocol onto the GenAI conventions for those who want both.

What it is not

No agent runtime: the board runs no model and schedules nothing; it starts only the one command a loop declares, after you tick it once. No database: the files are the truth. No cloud and no login: it answers on 127.0.0.1 only, and to a browser that opened the address serve prints. No transcripts: a loop reports summaries and paths. See SECURITY.md for what it trusts.

More

AGENTS.md runs the board and changes this repository. docs/ARCHITECTURE.md says why it is built this way. CHANGELOG.md says what changed.

License

Apache License 2.0: use it, change it and ship it, also commercially; keep the licence and the NOTICE, and say what you changed. It comes with a patent grant from every contributor. A contribution is taken under the same licence.

Metadata

Release files for loopcaptain 0.9.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for loopcaptain 0.9.1
File Size Uploaded Provenance Actions
loopcaptain-0.9.1.tar.gz 1.8 MB Without provenance Details for loopcaptain-0.9.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for loopcaptain 0.9.1
File Interpreter ABI Platform Actions
loopcaptain-0.9.1-py3-none-any.whl Python 3 none any Details for loopcaptain-0.9.1-py3-none-any.whl

Total release size: 2.1 MB

Release files / loopcaptain-0.9.1.tar.gz

Download URL loopcaptain-0.9.1.tar.gz
Size 1.8 MB
Tags Source
SHA-256 checksum
How to use checksums
bd26dbdc80bc5772ed7bb0492dc2f3ac87b48f9b3ecf0fcb3eae00c6aa0fe388
BLAKE2b-256 checksum
How to use checksums
809d0d7c54531af9eae9a839f1e79869378e7c5ecc154a47346b70961345d1b5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / loopcaptain-0.9.1-py3-none-any.whl

Download URL loopcaptain-0.9.1-py3-none-any.whl
Size 241.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
31d6af49da1a728cd45129f314aaa5e95a764156a1f5ac17e92dc8bca4c2573b
BLAKE2b-256 checksum
How to use checksums
a15bdd3fa99554fbc62817455d888d3c123302a3f1a95b1955bec10fea8aa5f1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for loopcaptain 0.9.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page