@kentcdodds: I ran an experiment of running Python on Kody now that Cloudflare has GA for python in workers (and dynamic workers): h…
Summary
Kent Dodds experimented with running Python on Kody using Cloudflare's GA for Python in Workers, but decided against implementing it due to slow startup times.
View Cached Full Text
Cached at: 09/22/26, 07:54 PM
I ran an experiment of running Python on Kody now that Cloudflare has GA for python in workers (and dynamic workers): https://github.com/kentcdodds/kody/pull/2429…
Really cool if you care about running python, but it’s much slower to start up (even when warm) and doesn’t unlock new capabilities. So passing on Python support in Kody for now.
kentcdodds/kody
Source: https://github.com/kentcdodds/kody
Your assistant's home — the memory, keys, code, and automations your AI agent keeps, portable across every MCP host. Built on Cloudflare Workers.
Kody is your assistant’s home—the memory, keys, code, and automations your AI
agent keeps, portable across every MCP host. Built on Cloudflare Workers and the
Model Context Protocol (MCP), it ships a Remix UI, Worker-based request routing,
package runtime plumbing, and OAuth-protected MCP endpoints. The project favors
a compact MCP surface with powerful search and Code Mode execute flows over
a large static tool catalog.
Kody is a multi-user personal assistant: each signed-in user gets a fully isolated assistant (packages, jobs, secrets, memories, and related state). Tests and fixtures may seed deterministic local accounts, but no account is privileged at runtime. The repo follows several epicflare starter conventions.
The repo is organized as an Nx monorepo, with shared modules in
packages/shared (@kody-internal/shared), the origin app worker under
packages/worker, sibling workers under packages/platform-worker,
packages/runtime-worker, and packages/jobs-worker, and mock Workers under
packages/mock-servers/*. Production topology lives in
docs/contributing/architecture/index.md.
Quick Start
npm install
npm run dev
The dev server runs at localhost:3742 by default (the CLI picks the next free
port and prints the resolved URL). Wrangler handles the local Cloudflare Workers
runtime and D1 database automatically.
To scaffold a new project from the epicflare template instead, run
npx create-epicflare.
See
docs/contributing/getting-started.md
for the full setup paths and expectations. Contributors and agents should start
with AGENTS.md for repo-specific guidance.
If you are trying to understand what this repository is for, start with
docs/contributing/project-intent.md.
Tech Stack
| Layer | Technology |
|---|---|
| Runtime | Cloudflare Workers |
| UI Framework | Remix 3 (beta) |
| Package Manager | npm |
| Workspace | Nx + npm workspaces |
| Database | Cloudflare D1 |
| Session/OAuth | Cloudflare KV |
| MCP State | Durable Objects on kody-platform |
| E2E Testing | Playwright |
| Bundler | Vite |
Scope
- Fair Source personal assistant platform, not a general-purpose agent harness
- MCP-first architecture intended to work across compatible AI agent hosts
- Compact MCP surface area preferred over a large static tool inventory
- ChatGPT is a likely primary host target, while keeping the server usable from other MCP hosts where practical
How It Works
kody.codes → kody-production (origin: Remix, /mcp HTTP, OAuth, email, queues)
├─→ kody-platform (MCP / mailbox / meter / repo-session DOs)
├─→ kody-runtime (package apps, invoke API, StorageRunner)
└─→ kody-jobs (cron + JobManager; calls back via JobsHost)
kody.run → kody-runtime (package-app zone routes)
packages/worker/src/index.tsis the origin entrypoint; platform, runtime, and jobs have sibling entrypoints (see architecture)- OAuth requests are handled first, then MCP requests, then static assets
- Non-asset requests fall through to the server handler and router
- Client assets are bundled into
packages/worker/public/and served via theASSETSbinding
Documentation
| Document | Description |
|---|---|
docs/contributing/getting-started.md | Setup, environment variables, deploy |
docs/contributing/environment-variables.md | Adding new env vars |
docs/contributing/cloudflare-offerings.md | Optional Cloudflare integrations |
docs/contributing/project-intent.md | Scope, goals, and non-goals |
docs/contributing/index.md | Developing and extending Kody |
docs/use/index.md | Using Kody over MCP |
docs/contributing/setup/ | Local development and verification |
Contributing
Outside pull requests to this repository need a signed inbound Contributor License Agreement. Public packages do not use that CLA.
See CONTRIBUTING.md and
docs/contributing/index.md.
License
Kody is licensed under the Functional Source License, Version 1.1, ALv2 Future License (FSL-1.1-ALv2). You can use, copy, modify, create derivative works from, publicly perform, publicly display, and redistribute the software for any purpose other than Competing Use. Competing Use means making the software available to others in a commercial product or service that substitutes for Kody, substitutes for another product or service the licensor offers using Kody that existed when the version was made available, or offers the same or substantially similar functionality. Each version becomes available under the Apache License 2.0 on the second anniversary of the date that version was made available.
Public packages published through Kody do not use this repository’s CLA and have no license gate; that is separate from this repository’s license.
Similar Articles
@kentcdodds: Can you believe this was done in a single day by a solo dev? https://github.com/kentcdodds/kody/releases/tag/v2026.08.1…
Kody is a portable personal assistant platform for AI agents, built on Cloudflare Workers and Model Context Protocol, enabling memory, code, and automation management across hosts.
@kentcdodds: I've already updated @kodykoala to the latest spec (thanks to Cloudflare for making it so easy). Can't wait for clients…
Kent C. Dodds has updated Kody Koala to the latest MCP spec, praising Cloudflare for easing the process and highlighting the rewritten stateless core that runs on Workers.
@kentcdodds: We'll see how this goes. #selfhealingsoftware
Kody is an open-source framework for AI agents, built on Cloudflare Workers and the Model Context Protocol, providing a portable home for memory, keys, code, and automations.
@kentcdodds: This is now built into Kody to make setting up new integrations a lot more straightforward for your agents https://gith…
Kody is an experimental personal assistant platform built on Cloudflare Workers and MCP; a recent update simplifies integration setup for agents.
@kentcdodds: Man this is so clutch. I don't know how I ever would have figured out this friction agents are experiencing without the…
Kent C. Dodds highlights a debugging feature in Kody, an open-source AI agent platform built on Cloudflare Workers and the Model Context Protocol (MCP), designed to manage memory and automations for agents across hosts.