https://github.com/modem-dev/baudbot
Multiplayer, always-on AI dev assistant - like OpenClaw but for your whole team on Slack 🤖
https://github.com/modem-dev/baudbot
Last synced: 28 days ago
JSON representation
Multiplayer, always-on AI dev assistant - like OpenClaw but for your whole team on Slack 🤖
- Host: GitHub
- URL: https://github.com/modem-dev/baudbot
- Owner: modem-dev
- License: mit
- Created: 2026-02-15T19:08:05.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-03-15T03:44:50.000Z (about 2 months ago)
- Last Synced: 2026-03-15T13:48:52.186Z (about 2 months ago)
- Language: TypeScript
- Homepage:
- Size: 1.37 MB
- Stars: 123
- Watchers: 0
- Forks: 12
- Open Issues: 19
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Security: SECURITY.md
- Agents: AGENTS.md
Awesome Lists containing this project
README
# Baudbot
[](https://github.com/modem-dev/baudbot/actions/workflows/ci.yml)
[](https://github.com/modem-dev/baudbot/actions/workflows/integration.yml)
[](LICENSE)
[](https://github.com/modem-dev/baudbot/commits/main)
[](SECURITY.md)
**Always-on, multiplayer dev-assistant for eng teams - write code, act on alerts, and more**
💬 _Join us on the Modem Discord: https://discord.gg/MKkTFvQ4_
---
Baudbot runs a persistent AI control agent on Linux, connected to Slack, with worker agents that take tasks from request to PR. It works on real repositories with real tools (git, test runners, Docker wrapper, cloud browser automation), keeps persistent memory, and reports progress back in-thread.
Built for teams that want autonomous execution speed **without giving up operational control**.
_**⚠️ WARNING: Baudbot is in alpha/early testing. If you use this, prepare to fix things. It might burn tokens. Be careful!**_
## What Baudbot does
- **Shared Slack interface for the whole team.** Anyone in allowed channels can hand work to the same agent system.
- **Always-on response and fast handoffs.** The control agent stays live, triages work instantly, and spins up task-scoped coding agents.
- **End-to-end coding loop.** Branch, code, run tests, open PR, watch CI, push fixes, report status.
- **Linux-native execution.** Agents can run the same project commands your engineers run (including guarded container workflows).
- **Persistent team memory.** The system learns repo quirks, recurring fixes, and collaboration preferences across restarts.
- **Self-improving operations.** Agents can update non-security skills/extensions and propose upstream improvements via PRs.
## Team agent, not a personal copilot
Baudbot is designed as shared engineering infrastructure, not a single-user desktop assistant:
- multiplayer by default (Slack threads, shared todos, multiple sessions)
- persistent service, not one-shot chat
- autonomous task execution with humans in review loops
- admin-managed runtime with deployment + rollback controls
## Requirements
| | Minimum | Recommended |
|--|---------|-------------|
| **OS** | Ubuntu 24.04 or Arch Linux | Any systemd-based Linux |
| **RAM** | 4 GB (3 agents) | 8 GB (6 agents + builds/tests) |
| **CPU** | 2 vCPU | 4 vCPU |
| **Disk** | 20 GB | 40 GB+ (repos, dependencies, Docker images) |
System package dependencies (installed by `baudbot install`): `git`, `curl`, `tmux`, `iptables`, `docker`, `gh`, `jq`, `sudo`.
## Quick Start
```bash
curl -fsSL https://raw.githubusercontent.com/modem-dev/baudbot/main/bootstrap.sh | bash
baudbot install
```
`baudbot install` has a guided config flow: pick an LLM provider, choose Slack integration mode (managed broker vs custom app), then opt into optional integrations (Kernel/Sentry).
After install:
```bash
# deploy latest source/config to runtime
sudo baudbot deploy
# start the service
sudo baudbot start
# check health (includes deployed version + broker connection/health status)
sudo baudbot status
sudo baudbot doctor
```
Upgrade later:
```bash
sudo baudbot update
```
Connect/talk to the control agent:
```
sudo baudbot attach
```
Install with a specific pi version (optional):
```bash
BAUDBOT_PI_VERSION=0.52.12 baudbot install
```
Slack broker registration:
```bash
sudo baudbot broker register
```
Need to rotate/update a key later?
```bash
sudo baudbot env set ANTHROPIC_API_KEY
# or: sudo baudbot env set OPENAI_API_KEY sk-... --restart
```
See [CONFIGURATION.md](CONFIGURATION.md) for required environment variables and secret setup.
## The Slack broker (optional)
The primary way to talk to Baudbot remotely is through Slack.
You have two choices:
1. **Create/manage your own Slack app** (hard)
2. **Use our hosted Slack broker + control plane** at https://baudbot.ai (easy) [ALPHA]
What the Slack broker does:
- One-click install to connect your Slack workspace to your Baudbot instance
- Broker forwards messages to your Baudbot instance (encrypted)
- Broker strips PII and sensitive values
- Broker tool-restricts access to individual Slack users, channels, etc (COMING SOON)
The broker does not have access to your Baudbot instance. Baudbot is pull-only; it doesn't expose additional ports or host a control plane.
## Core agents
| Role | Purpose |
|------|---------|
| **control-agent** | Owns intake, triage, delegation, Slack comms, and lifecycle supervision |
| **dev-agent** | Ephemeral coding worker that executes branch → code → PR → CI loops |
| **sentry-agent** | On-demand incident investigator for Sentry alerts and triage support |
## Architecture at a glance
```text
Slack
↓
control-agent (always-on)
├─ todo + routing
├─ dev-agent(s) in isolated worktrees
└─ sentry-agent for incident triage
↓
git commits, PRs, CI feedback, thread updates
```
Baudbot uses source/runtime separation: admin-managed source and immutable releases are deployed into an unprivileged agent runtime.
## Security as an enabling layer
Baudbot is built for utility **and** containment:
- isolated `baudbot_agent` Unix user (no general sudo)
- per-UID firewall controls + process isolation
- source/runtime separation with deploy manifests
- startup deploy-manifest integrity verification (`warn`/`strict` modes)
- read-only protection for security-critical files
- session log hygiene (startup redaction + retention pruning)
- layered tool and shell guardrails (policy/guidance layer, not sole containment)
See [SECURITY.md](SECURITY.md) for full threat model, trust boundaries, and known risks. In particular: many controls here are defense-in-depth (helpful for drift prevention/detection and keeping healthy agents on-task), while hard containment comes from OS/runtime boundaries.
## Documentation
- [docs/team-workflow.md](docs/team-workflow.md) — request lifecycle and orchestration model
- [docs/agents.md](docs/agents.md) — agent roles, responsibilities, and session model
- [docs/memory.md](docs/memory.md) — persistent memory design and operating rules
- [docs/linux-runtime.md](docs/linux-runtime.md) — Linux execution model, tools, and constraints
- [docs/operations.md](docs/operations.md) — day-2 operations (start/stop/update/rollback/audit)
- [docs/architecture.md](docs/architecture.md) — source/runtime/release architecture
- [CONFIGURATION.md](CONFIGURATION.md) — full env var reference
- [SECURITY.md](SECURITY.md) — deep security model and vulnerability reporting
- [CONTRIBUTING.md](CONTRIBUTING.md) — contribution workflow
## Tests
```bash
# All tests (unified Vitest runner)
npm test
# JS/TS suites only
npm run test:js
# Shell/security script suites only
npm run test:shell
# JS/TS coverage
npm run test:coverage
# Lint (Biome + ShellCheck) + typecheck
npm run lint && npm run typecheck
# ShellCheck only
npm run lint:shell
```
## License
MIT
## About
Brought to you by the team at Modem, your dev team's auto-triage product manager.