Show HN: OSS framework to launch Instinct like iMessage assistants

Flow released an open-source TypeScript framework that lets developers write tools and skills once and expose them as an MCP server, a plugin, a CLI and a messaging agent across Claude, ChatGPT, WhatsApp, iMessage, Telegram, SMS and custom apps. The framework requires Node 22.18 or later, is scaffolded with `npx @flow-engineer/flow new my-agent`, and includes a café example whose tools run in an MCP server, CLI and messaging agent without a model key; `npx @flow-engineer/flow link --channel telegram` (or `whatsapp`/`imessage` when available) signs in and sets up trial keys. Flow positions the release around chat-first product use, with authentication hooks, simulated conversation testing and deployment on the user's own infrastructure or Flow Cloud.

Build once. Ship to every chat. One open-source TypeScript framework to bring your product to Claude, ChatGPT, the terminal, WhatsApp, iMessage, Telegram and your own app. Write your tools and skills once; use them as an MCP server, a plugin, a CLI and a messaging agent. We're building Flow for a chat-first world: people should be able to use a product by asking for what they need, where they already chat. Moving a booking or placing an order should happen in the conversation—not end with a link to a form. Whether someone texts your business or asks their own assistant, the same product capabilities should be available to them. Documentation https://docs.flow.engineer/framework · Quickstart https://docs.flow.engineer/framework/quickstart · For coding agents https://docs.flow.engineer/agents · Website https://flow.engineer | Build | Reach | |---|---| | MCP server https://docs.flow.engineer/framework/mcp | Claude, ChatGPT and other MCP clients | | Plugin https://docs.flow.engineer/plugins | Hosts that load native skills and an MCP connection | | CLI https://docs.flow.engineer/cli | People, scripts, Claude Code, Codex and other coding agents | | Messaging agent https://docs.flow.engineer/conversations | WhatsApp, iMessage, Telegram, SMS and your own web or app chat | Tools are typed TypeScript functions that call your APIs. Skills teach the workflows around them. Flow exposes the same capabilities through each interface, with authentication hooks for your users and room to customize the generated tools, commands and handlers. In Claude and ChatGPT, the host's model uses your MCP tools. In messaging, Flow runs the conversation with your model, handling double texts, acknowledgements, background tools, channel rules, reminders, persistent history and the agent's own records. Start with whichever interface you need. Node 22.18 or later. Create a project from the café example: npx @flow-engineer/flow new my-agent --display-name "My agent" cd my-agent npm install The starter includes the same tools in an MCP server, a CLI and a messaging agent. Start the server: npm run mcp It prints the MCP URL and a command to connect Claude Code. In another terminal, try the CLI: npm run cli -- --help npm run cli -- menu --json To test any MCP server from the current chat, use npx @flow-engineer/flow inspect <url tools with the URL the server prints. call , auth , resources and prompts exercise its tools, sign-in and other capabilities as a host does, without requiring a CLI configuration. These tool calls need no model key. To reach Claude or ChatGPT remotely, host the MCP server over HTTPS and connect it in the host. MCP and sign-in https://docs.flow.engineer/framework/mcp · Plugin packages https://docs.flow.engineer/plugins npx @flow-engineer/flow link --channel telegram npm start link signs in, sets up the trial keys and prints a phone link. Use --channel whatsapp or --channel imessage for those platforms when available. Open the playground URL from npm start to try the agent locally, then text it from your phone while it runs. You can also use your own model key and messaging provider. Full setup and trial details https://docs.flow.engineer/framework/quickstart flow new includes coding-agent skills and an AGENTS.md pointing to them. Give Claude Code, Codex or another coding agent your product's codebase and tell it which interfaces to build. Replace the café tools with calls to your APIs and teach your workflows through skills. Read the coding-agent guide https://docs.flow.engineer/agents , or explore the café example https://github.com/flow-engineer/flow/blob/main/examples/cafe . Check tools, skills and CLI configuration with npx @flow-engineer/flow check . Test the messaging agent with simulated conversations, inspect traces, and deploy on your own infrastructure or Flow Cloud. The playground simulators follow each app’s behavior, including channel-specific controls, media and voice notes; Debug mode shows the underlying platform payloads. Flow Messaging provides channels through one API; you can also bring your own providers. Deployment https://docs.flow.engineer/hosting · Self-hosting https://docs.flow.engineer/self-hosting · Testing https://docs.flow.engineer/testing · Traces https://docs.flow.engineer/traces The documentation site https://docs.flow.engineer covers the Framework and the Unified Messaging API https://docs.flow.engineer/unified-messaging-api . Its source lives in the private flow-engineer/docs repository. Public behavior changes update the relevant guide there for people and coding agents; see AGENTS.md https://github.com/flow-engineer/flow/blob/main/AGENTS.md . Tools https://docs.flow.engineer/build-agent · Skills https://docs.flow.engineer/skills · Models and options https://docs.flow.engineer/reference In this repository: channel options https://github.com/flow-engineer/flow/blob/main/docs/channels.md · patterns that worked https://github.com/flow-engineer/flow/blob/main/docs/patterns.md enforce what matters in beforeSend , keep prompts for judgement, render in code, refuse with a reason the model can act on, test a long chat . A channel's sendMessage resolves when your platform accepted the message and rejects when it refused it: the agent's next message waits for it, and a rejection reaches the agent as Not delivered. What is ordered, what is sent once and what send resolving means: docs/guarantees.md https://github.com/flow-engineer/flow/blob/main/docs/guarantees.md . Ready-made beforeSend checks compose with guards ... , the first refusal winning: oncePerChat line a disclaimer at most once per conversation , noRepeats , linkAllowlist hosts and noWriteButtons actions ; they read what was sent from the stored history context.sent , so they hold after a restart. agent.resetHistory { to, note } starts the history the model is sent again from now nothing is deleted . Each model call carries at most 24,000 tokens of history, or 60% of the model's contextTokens when that is less createAgent { history: { maxTokens } } to change it . What the agent must remember across days and people a buyer's question waiting for the seller's answer it keeps as records: small JSON documents in collections declared on createAgent { records } , read by id or matched on a few declared fields, in the same store as its conversations, so they survive restarts and deploys and work the same in the playground, self-hosted and on Flow's hosting. Forgetting a person deletes the records that name them, and flow records export prints them all. The rule: if anything other than the agent reads it, it belongs in your own database. docs/agents.md https://github.com/flow-engineer/flow/blob/main/docs/agents.md the-agents-own-records Flow Framework is 0.x: until 1.0 its API exports, options, file formats, the CLI's commands, --json fields and exit codes may change between releases. Every release's notes call out each breaking change with a migration note saying what to change. The API freezes at 1.0. Pin the exact version in package.json for production, and read the notes before you move it. What freezes at 1.0: docs/stability.md https://github.com/flow-engineer/flow/blob/main/docs/stability.md .