Platform-native config generation
Generate native configuration files for 21 AI coding platforms from one source of truth, so team prompts stay synchronized across tools instead of drifting apart.
Assemble
Assemble by Cohesium AI is an open-source prompt orchestration system for AI coding tools. It generates native config files that turn one project into a structured multi-agent setup across 21 platforms.
Overview
Assemble by Cohesium AI is an open-source prompt orchestration system for AI coding tools. It generates native configuration files that turn an IDE into a structured AI team, so users can direct specialist agents through commands instead of managing separate prompt formats for each platform.
The product centers on a single source of truth for team behavior across 21 AI coding platforms. Its docs describe a zero-runtime setup: you install the generator, answer an interactive wizard, and receive platform-specific files such as `.cursorrules`, `CLAUDE.md`, and `.github/copilot-instructions.md` alongside agent and workflow definitions under `.assemble/`.
Features
34 specialized agents
Use 34 predefined AI agents that cover roles such as architecture, backend, frontend, QA, security, product, marketing, and data.
Command-driven orchestration
Route work through `/go`, `/feature`, `/bugfix`, `/review`, `/security`, and other commands, with Jarvis selecting a single specialist, chaining agents, or running a structured 5-phase process for complex work.
Interactive setup flow
Install with `npx cohesiumai-assemble` or the provided shell installer, then answer an interactive wizard that writes `.assemble.yaml` and related project files.
Extensible configuration
Extend the system with custom agents, skills, workflows, and platform adapters when the defaults do not match your team.
Zero-runtime design
Run without a daemon, server, or runtime dependency; the generated output is static config rather than a background service.
Use Cases
Keep multiple AI tools in sync
Set up one repository so Cursor, Claude Code, Copilot, Windsurf, and similar tools all read aligned instructions from generated native files.
Route coding work to specialists
Assign work through `/go` and let Jarvis choose the right specialist, chain agents for multi-step work, or trigger the structured 5-phase path for complex tasks.
Standardize repeatable delivery workflows
Use prebuilt workflows such as `/feature`, `/bugfix`, `/review`, `/security`, or `/release` to standardize common engineering tasks with consistent agent handoffs.
Work as a structured solo team
Generate a project team structure for solo developers or small teams who want role-specific help for architecture, QA, security, product, or copywriting inside one IDE.
Adapt the setup to local processes
Extend the default setup with custom agents, skills, or platform adapters when a team needs its own process or unsupported tool coverage.
Pros and Cons
Pros
- Open-source and MIT licensed, with the site stating no premium tier, feature gating, or usage limits.
- Generates native config files for many tools from one project-level source of truth.
- Includes a defined set of 34 specialized agents and 15 preconfigured workflows.
- Works without a runtime, daemon, or background process.
Cons
- The pricing page returns a 404, so the public site does not provide a separate pricing structure to review.
- The source is strongest on orchestration and file generation; deeper operational details for every supported platform are not fully spelled out on the pages provided.
FAQ
Is Assemble free to use?
Yes. The site states that Assemble is MIT licensed, free forever, with no premium tier, feature gating, or usage limits.
Does Assemble run in the background?
Assemble does not run as a daemon or background process. It generates static, platform-native config files that your IDE or AI coding tool reads directly.
Which platforms does Assemble support?
The source shows support for 21 AI coding platforms, including Cursor, Claude Code, GitHub Copilot, Windsurf, Gemini CLI, Codex, Cline, Roo Code, Kiro, Trae, Google Antigravity, CodeBuddy, Crush, iFlow, Kilo Code, OpenCode, QwenCoder, Rovo Dev, Claude Code Desktop, and Augment.
What do I need to get started?
The docs describe Node.js 18 or later and an AI coding tool such as Cursor, Claude Code, or VS Code with Copilot as prerequisites.
What does Assemble create in a project?
Assemble generates platform-native config files such as `.cursorrules`, `CLAUDE.md`, `.github/copilot-instructions.md`, `.windsurfrules`, and `.assemble.yaml`, plus agent and workflow files under `.assemble/`.
Quick Facts
- Category
- Developer Tool
- Source domain
- assemble.cohesium.ai
- License
- MIT
- Platform support
- 21 AI coding platforms
- Core workflow
- `/go` plus specialist routing
- Primary output
- Platform-native config files and `.assemble/` project files
Alternatives à Assemble
Ghost
Ghost est un assistant IA en terminal pour discuter, générer du code et lancer des tâches en ligne de commande. Modèles gratuits, Linux, macOS, Windows, open source.
Devin
Devin is an AI coding agent and software engineer that helps developers and engineering teams plan and execute complex software tasks. It is available through desktop, cloud, JetBrains, and CLI surfaces, with plans for individuals, teams, and enterprises.
图像大厨imgcook
imgcook is a design-to-code tool that converts design drafts into front-end code. It supports plugin-based and developer workflows for Sketch, Photoshop, VS Code, and CLI usage.
Pi Coding Agent
Pi Coding Agent is a terminal-based coding agent for developers who want a minimal, extensible harness for interactive work and automation. It supports model switching, session branching, and multiple run modes including TUI, print/JSON, RPC, and SDK.
Biji
Biji est une plateforme polyvalente conçue pour améliorer la productivité grâce à des outils et des fonctionnalités innovants.
Ably Chat
Ably Chat is a chat API platform for building custom realtime chat applications. It supports room-based messaging, typing indicators, presence, reactions, and message updates, with usage-based pricing options for different deployment stages.