PhD_fleet – Manage a virtual research lab of AI PhD students via Slack

Notifications You must be signed in to change notification settings

Fork 1

Star 1

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

1 Commit

1 Commit

library

library

mentor_template

mentor_template

src

src

student_template

student_template

.env.example

.env.example

.gitignore

.gitignore

LAB_CONTEXT.md

LAB_CONTEXT.md

LICENSE

LICENSE

README.md

README.md

bot.py

bot.py

pyproject.toml

pyproject.toml

requirements.txt

requirements.txt

slack-manifest.yaml

slack-manifest.yaml

Repository files navigation

A small Python toolkit that lets one researcher — the advisor — spawn and converse with a fleet of Claude Code agents through Slack. Each agent is its own Claude Code session in its own workspace directory; Slack messages drive turns; between turns, the agent's filesystem is its long-term memory.

A separate coach agent watches how the advisor advises and gives evidence-based feedback on mentoring craft. The two intertwined goals: get real research done and grow as a mentor.

The host can be anything that runs Python and the Claude Code CLI — a laptop, a lab workstation, a cloud VM, an HPC login node. The bot connects to Slack over Socket Mode, so the host needs no inbound HTTP and works behind a NAT or in a private subnet.

Table of contents

What you get

Requirements

Quick start

Setup in detail

Usage

How it works

Configuration

Security model

Limitations

Project layout

License

What you get

One Slack channel per agent. #student- for each student you spawn; #mentor-coach for the coach (created automatically at first startup).

Three slash commands.

/new-student scaffolds a workspace, creates the channel, and kicks off the first turn.

/coach-review [days] asks the coach to review your mentoring of a specific student.

/claude-status prints a quick local readout — turns, last context size, cumulative tokens, model, cost, and GitHub link per agent. No Claude calls; just a registry view.

Per-agent journal. JOURNAL.md in each agent's workspace is append-only, one section per turn, ending with a Did / Found / Next block.

Shared paper library. library/ at the project root is a single pool every agent reads from and contributes to. First reader of a paper writes the canonical summary; later readers add a separate notes file. library/README.md is a regenerated index — agents only read it.

Per-turn commits to per-agent GitHub branches (optional). If you configure an origin, after each turn the bot stages that agent's workspace into a fresh commit on agent/ and force-pushes it with a lease. The Slack final message links to the branch for review. With no origin, this step is skipped silently.

Quiet by default. During a turn the bot posts at most one short "started" message and the agent's final reply — no per-tool stream of decorative messages. Failures and timeouts post a :warning: line.

Requirements

Python 3.11 or newer.

The Claude Code CLI on PATH. The bot shells out to it, so claude --version must work in the same shell where you run the bot.

A Claude.ai subscription or an Anthropic Console API key (see Claude authentication).

A Slack workspace (free or paid) where you can install a custom app.

Optional: a GitHub repository if you want per-turn review branches. The bot runs fine without one.

Quick start

git clone cd phd_fleet python3 -m venv .venv .venv/bin/pip install -r requirements.txt

cp .env.example .env # then fill in the three required values

.venv/bin/python bot.py

Then in Slack, run /new-student alice "your project briefing" to spawn your first agent. The rest of this section explains each step.

Setup in detail

1. Install dependencies

See the Quick start above. A virtualenv is recommended but not required — any environment with the dependencies in requirements.txt works.

1. Create the Slack app

The repo ships slack-manifest.yaml — a manifest that already lists the three slash commands, the bot scopes, and the event subscriptions. To use it:

Go to https://api.slack.com/apps → Create New App → From a manifest.

Pick your workspace, paste the contents of slack-manifest.yaml, and confirm.

Under Basic Information → App-Level Tokens → Generate Token and Scopes, create a token with the connections:write scope. Copy it (xapp-…) — that's your SLACK_APP_TOKEN.

Under OAuth & Permissions, install the app to your workspace. Copy the Bot User OAuth Token (xoxb-…) — that's your SLACK_BOT_TOKEN.

1. Configure environment

cp .env.example .env

edit .env and fill in SLACK_BOT_TOKEN, SLACK_APP_TOKEN, ADVISOR_SLACK_USER_ID

To find your ADVISOR_SLACK_USER_ID: in Slack, click your profile picture → View full profile → the … menu → Copy member ID. It looks like U0123ABC456. The bot rejects messages from anyone whose user ID does not match this value — the only access-control surface.

1. Claude authentication

Two paths, in order of preference:

Subscription (recommended). If claude is OAuth-authenticated to your Claude.ai account — i.e., ~/.claude/.credentials.json exists from running claude /login once — the bot just uses it. Leave ANTHROPIC_API_KEY unset.

API key. To pay per token through the Anthropic Console, set ANTHROPIC_API_KEY=sk-ant-… in .env. The Agent SDK picks it up and ignores the subscription path.

1. Run

.venv/bin/python bot.py

You should see:

… INFO ready — listening on Socket Mode (advisor=U0123ABC456) … INFO A new session (s_…) has been established … INFO ⚡️ Bolt app is running!

Health check: in any channel where the bot is present, @ ping returns pong.

For long-running operation, run the bot under a process supervisor — tmux is the simplest path, systemd --user if you want auto-restart on crash. The bot reconnects to Slack on transient disconnects but cannot survive a full process exit without a supervisor.

Usage

Spawning a student

/new-student alice "Investigate AlphaFold confidence on disordered regions. Read the recent literature, then propose a small experiment."

What this does:

Validates the name against ^[a-z0-9][a-z0-9_-]{0,40}$.

Scaffolds students/alice/ from student_template/, filling in the name and project briefing.

Creates #student-alice in Slack and invites you.

Registers Alice in agents.json (the runtime registry).

Kicks off the first turn — the agent reads its CLAUDE.md, gets oriented, and reports back.

After that, every message you send in #student-alice becomes the next prompt. The agent's session resumes across turns and across bot restarts.

Talking to the coach

The coach has its own channel, #mentor-coach, created at first bot startup. Two ways to use it:

Free chat. Anything you write in #mentor-coach becomes a prompt — "How should I handle a student proposing a method I think is wrong?" The coach responds in a coaching voice, asks clarifying questions, and names a relevant framework when appropriate.

Structured review. /coach-review alice 7 pulls the last 7 days of #student-alice plus a recent excerpt of Alice's JOURNAL.md, and asks the coach to review your mentoring of Alice — what was done well, what could be sharper, each tied to a specific moment. The result is posted in #mentor-coach, and the coach also updates a longitudinal mentor/coach/notes/advisees/alice.md.

Quick status

/claude-status

Ephemeral reply listing every agent: kind, turns taken, last context size, cumulative input/output tokens, model, total cost, and the GitHub branch link if available. Pure local read — does not call Claude.

Listing and archiving agents

Manual on purpose. To see what you have, look in students/. To archive a student: mv students/ students/_archived/ and remove its entry from agents.json. Slash commands for operations you'll do twice a year aren't worth their weight.

How it works

Students

Each student lives in students//:

CLAUDE.md — persona and project briefing, filled in at create time from student_template/.

JOURNAL.md — append-only research log, one section per session.

notes/ — private scratchpads, design notes, intermediate analyses.

the rest of the directory — actual work artifacts (code, data, results).

Each student is told to check library/ (the shared pool) before reading anything new, to write new paper summaries there, and never to run git — the bot handles publishing.

The lab-wide habits and conventions live in LAB_CONTEXT.md, auto-appended to every agent's system prompt. Edit it once and every agent picks up the new rules on its next turn.

The coach

The coach lives in mentor/coach/, with the same workspace structure as a student plus notes/advisees/.md for longitudinal observations. Its CLAUDE.md carries a coaching persona and a vocabulary of named frameworks (GROW; SBI; Vygotsky's ZPD; feedforward). It uses the same runner, the same per-agent lock, and the same scaffolding as a student. The coach is reactive only: it speaks when summoned — there is no auto-review after every student turn.

The shared library

library/ is a single directory at the project root that every agent reads from and writes to:

First reader of paper X writes library/.md (a markdown summary with YAML frontmatter) and library/.pdf if it's freely downloadable.

Later readers who want to add their take write a separate file — library/__notes_.md. They never edit a peer's summary.

library/README.md is the index. Agents only read it. The bot regenerates it after each turn by walking library/*.md, parsing frontmatter, and rewriting the table.

Citekey collisions (two papers by the same author in the same year) are resolved with letter suffixes — jumper2021a, jumper2021b. The full conventions live in LAB_CONTEXT.md. This per-file-ownership shape avoids the failure mode where two agents append to the same index at once and clobber each other.

Per-turn GitHub publishing

If you've configured origin, the bot publishes each agent's workspace to a per-agent branch (agent/) after every turn, using a force-push with a lease. It stages into a temporary git index so the bot's commits never disturb your working tree. The Slack final message links to the branch on GitHub. The step-by-step rationale is documented in the comments of src/agents.py (commit_and_push).

If you don't want this, simply don't add an origin. The bot skips the publish step silently and the Slack messages won't include review links.

Configuration

Most behavior is set in .env; the per-agent .claude/settings.json files carry the permission deny-list (see Security model). The .env knobs:

Variable Default Purpose

SLACK_BOT_TOKEN required Bot User OAuth Token (xoxb-…).

SLACK_APP_TOKEN required App-Level Token with connections:write (xapp-…).

ADVISOR_SLACK_USER_ID required The single user allowed to talk to the bot.

ANTHROPIC_API_KEY unset Optional. Set to use a Console API key instead of subscription auth.

AGENT_TURN_TIMEOUT_SECONDS 3600 How long one turn may run before being canceled.

Security model

This is defense-in-depth, not a sandbox. Each agent's .claude/settings.json carries a permission deny-list shipped in both templates:

Sensitive paths are never read: /.env*, /.ssh/, /.aws/, /.config/gh/, id_rsa*, id_ed25519*, /etc/, /root/**.

Privilege-escalation and cluster-job verbs are never run: sudo, su, chmod, chown, srun, sbatch, scancel, salloc.

Per-deployment additions (e.g. other cluster schedulers) are easy to add to the same file. The deny-list is not isolation: a determined prompt-injection from a fetched paper could still misuse Bash or Write within the agent's workspace. Run the bot only on a host where that risk is acceptable, and only ever as the single configured advisor — the bot drops every Slack message whose user ID doesn't match ADVISOR_SLACK_USER_ID.

Limitations

Single advisor. No team / multi-advisor mode — the framework is shaped around one researcher's attention.

Reactive only. Agent

[truncated for AI cost control]