monkeybot

Multi-cloud agent harness — GCP-first docs, portable runtime

monkeybot is an owned agent runtime for tool-using LLMs: a FastAPI SSE gateway, pluggable storage, MCP tools, skills, and memory. Run locally with zero cloud dependencies, or ship the same container image anywhere Docker runs.

Docs and examples are GCP-first (Vertex, GCS, Cloud Run); AWS paths ship in the Pattern guides. See Cloud deployment — Positioning.

Quick start

Install uv, then:

uv tool install monkeybot-cli

monkeybot new --dest ./my-agent --provider openai --yes
cd my-agent
uv sync
cp .env.example .env   # add provider keys
monkeybot doctor
monkeybot chat

Upgrade the CLI with uv tool upgrade monkeybot-cli. Full walkthrough: Getting Started.

What you get

SSE gateway — sessions, streaming, health; wire your own UI or use the CLI
Realtime talk — WebSocket voice/text via monkeybot talk
MCP + skills — stdio/HTTP tools and trusted Python skill bundles
Pluggable storage — SQLite by default; Postgres, Firestore, GCS, S3
Multi-provider — Gemini/Vertex, OpenAI, Anthropic, Bedrock, Ollama, and more

CLI

Command	Purpose
`monkeybot new`	Scaffold config, workspace, agent `pyproject.toml`, `.env.example`
`monkeybot validate`	Check `monkeybot.yaml`, paths, and MCP config
`monkeybot doctor`	Verify Python, extras, credentials, and port
`monkeybot run`	Start the SSE gateway in the foreground
`monkeybot chat`	Talk over SSE (spawns the gateway; `--attach` to join one)
`monkeybot talk`	Realtime voice/text over WebSocket (`--text` for typed input)

monkeybot chat            # spawn gateway + REPL
monkeybot run             # terminal 1: gateway with logs
monkeybot chat --attach   # terminal 2: attach to it

Provider extras live on the agent pyproject.toml (monkeybot[<provider>]), not the global CLI. See Getting Started and Features — CLI.

Agent skill

npx skills add human-plus-machine/monkeybot --skill monkeybot

Walks through install, scaffold, config, and first chat. Source: cli/skills/monkeybot/.

Documentation

Guide	Description
Getting Started	Install, configure, sessions + SSE from the CLI
Features	Architecture, capabilities, CLI, task queue
SSE gateway and custom UI	HTTP + SSE endpoints, event types, CORS
Skills	Skill directory layout and `SKILL.md` discovery
Model Context Protocol	MCP config, env interpolation, OAuth2
Cloud deployment	Positioning + Patterns A–D index
Live evals	Smoke suite, local + CI scorecard
Observability	OpenTelemetry tracing runbook

Integrations matrix and roadmap: CHANGELOG · BACKLOG.

Contributing

Clone only if you are changing the harness. Setup, checks, and the release workflow are in CONTRIBUTING.md. Live eval smoke fixture: evals/smoke_agent/.

Support

Search or open an issue in the GitHub issue tracker.

Credits

MonkeyBot builds on two open-source projects:

Browser Use — browser automation for the browser MCP (via browser-harness and the interactive-element DOM walker). MIT licensed.
OpenSandbox — sandbox runtime used for isolated run_command / code execution. Apache-2.0 licensed.

License

MIT — see LICENSE.

Metadata

Release files for monkeybot 3.7.0

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

Source distribution (sdist)

Source distribution for monkeybot 3.7.0
File	Size	Uploaded
monkeybot-3.7.0.tar.gz	3.8 MB	Sep 30, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for monkeybot 3.7.0
File	Interpreter	ABI	Platform	Reset
monkeybot-3.7.0-py3-none-any.whl 750.3 kB Sep 30, 2026	Python 3	none	any	Details

Total release size: 4.6 MB

Release files / monkeybot-3.7.0.tar.gz

Download URL	monkeybot-3.7.0.tar.gz
Size	3.8 MB
Tags	Source
SHA-256 checksum How to use checksums	`755677f26de6ea8fce3317e3006bfbc714f4b0e73d740a23f42fe500f63f27ea`
BLAKE2b-256 checksum How to use checksums	`bc615a86d39d8fd13893d0510c4dc69250be71b28417040899f9994ebe261515`
Upload date	Sep 30, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

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.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/human-plus-machine/monkeybot
Publishing commit: github.com/human-plus-machine/monkeybot/tree/1faaeadc1456bed46466f55c0a02bc094f8f4532

Workflow

Publishing configuration: github.com/human-plus-machine/monkeybot/blob/1faaeadc1456bed46466f55c0a02bc094f8f4532/.github/workflows/publish-release.yml
Publishing logs: github.com/human-plus-machine/monkeybot/actions/runs/36747479000/attempts/1

Artifact

Subject: monkeybot-3.7.0.tar.gz
SHA-256 checksum: 755677f26de6ea8fce3317e3006bfbc714f4b0e73d740a23f42fe500f63f27ea Verifying attestations

Release files / monkeybot-3.7.0-py3-none-any.whl

Download URL	monkeybot-3.7.0-py3-none-any.whl
Size	750.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`fd1cbcfb06c81ef409bf58ec89d562728c55c938b616ce671da2c2c56f40d7ee`
BLAKE2b-256 checksum How to use checksums	`bb0476e27d113a22ba6b3c9bde97b82753cde39e9891ffd3935d26905d026c2d`
Upload date	Sep 30, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/human-plus-machine/monkeybot
Publishing commit: github.com/human-plus-machine/monkeybot/tree/1faaeadc1456bed46466f55c0a02bc094f8f4532

Workflow

Publishing configuration: github.com/human-plus-machine/monkeybot/blob/1faaeadc1456bed46466f55c0a02bc094f8f4532/.github/workflows/publish-release.yml
Publishing logs: github.com/human-plus-machine/monkeybot/actions/runs/36747479000/attempts/1

Artifact

Subject: monkeybot-3.7.0-py3-none-any.whl
SHA-256 checksum: fd1cbcfb06c81ef409bf58ec89d562728c55c938b616ce671da2c2c56f40d7ee Verifying attestations