II Agent
A self-hosted, multi-model intelligent agent for building, research, and document work with your own API keys.
- Source repo
- Intelligent-Internet/ii-agent
- Stars
- ★ 3.4k
- Last updated
- 2mo ago
- License
- Apache-2.0
- Primary language
- Python
- FA score
- 46/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A solo developer wants to start a mobile app or website from a short prompt while running the full frontend and backend stack locally.
- Not a fit if
- Teams wanting zero-infrastructure setup without Docker and local databases
- Developers needing a stable external API or SDK contract
- Source review
- 46/100 · Major gaps
What does this agent do, and when should you use it?
II Agent is an Apache-2.0 open-source AI agent that individuals, research teams, and enterprises can run, fork, and extend. It uses a browser frontend and backend service with a local stack comprising PostgreSQL, Redis, and MinIO. Documented capabilities include prompt-driven mobile apps, websites, picture books, and slide decks, plus fast and multi-step research. It also covers multi-model chat, file attachments, a code interpreter, text-file search, and PDF, Excel, Word, and PowerPoint tasks. In the documented full development stack, the backend runs at localhost:8000 and the frontend runs at localhost:1420.
Run make setup to create .env files and install dependencies, then configure models either through MODEL_CONFIGS in .env or by copying model_configs.example.yaml to model_configs.yaml and setting MODEL_CONFIGS_FILE. make dev-all starts the infrastructure, backend, and frontend; the documented services are PostgreSQL, Redis, MinIO, the Backend at http://localhost:8000, and the Frontend at http://localhost:1420. In the running product, users can hold multi-model conversations, switch providers mid-thread, attach files, use a code interpreter and text-file search, and run fast or multi-step research that can turn a research brief into a website with structure, visuals, citations, and embedded Q&A. The README also lists prompt-driven mobile apps, websites, picture books, video and image generation, plus PDF extraction and creation, Excel formulas and charts, Word editing, and PowerPoint manipulation.
- A solo developer wants to start a mobile app or website from a short prompt while running the full frontend and backend stack locally.
- A research team needs to choose between fast and multi-step research, then deliver a research brief as an interactive website with citations and embedded Q&A.
- An internal-tools team wants to supply its own model API keys and configure OpenAI, Anthropic, or Google models in one system.
- A content creator wants to produce an illustrated picture book from one prompt or use multiple video and image models in one workflow.
- A knowledge-work user needs PDF extraction or creation, Excel formulas and charts, Word editing, or PowerPoint manipulation.
How do you install or deploy this agent?
Prerequisites: Docker, uv, Node.js, and npm.
git clone https://github.com/Intelligent-Internet/ii-agent.git- cd ii-agent
- make setup
- Set MODEL_CONFIGS for at least one model provider in .env, or copy model_configs.example.yaml to model_configs.yaml, add API keys, and set MODEL_CONFIGS_FILE=model_configs.yaml in .env.
- Run make dev-all.
How do you use this agent?
After startup, open http://localhost:1420; the backend is available at http://localhost:8000. Once at least one provider and API key are configured, use chat with file attachments, the code interpreter, or text-file search, and initiate build, research, or document tasks. To run only part of the stack, use make infra, make backend-dev, or make frontend-dev. For the containerized full stack, create and fill docker/.stack.env, then run make stack.
What are this agent's strengths and limitations?
- Bring-your-own-key configuration lets operators control model providers and costs, with documented OpenAI, Anthropic, and Google model configuration.
- It provides both a local development stack and a Docker Compose full-stack path with PostgreSQL, Redis, and S3-compatible MinIO.
- The documented product spans app generation, research-site generation, document handling, and multi-model chat instead of a single workflow.
- Local operation requires Docker, uv, Node.js, and npm, plus PostgreSQL, Redis, and MinIO services.
- At least one LLM provider API key is required; service availability and cost depend on the selected provider.
- The supplied material lists Gmail, Slack, GitHub, Notion, Google Calendar, Discord, Dropbox, and Canva integrations but does not provide authentication or setup steps for each one.
- The supplied material does not document a stable external API, SDK, or version-compatibility commitment.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| II Agent This agent | 46 · Major gaps | CLIFree + model costs | ★ 3.4k | 2mo ago | Python | OpenAI API · Claude API |
| Loki Mode | 67 · Some gaps | CLIFree + model costs | ★ 1.1k | 1d ago | Shell | Claude Code · Claude API |
| MS-Agent | 67 · Some gaps | Web appFree + model costs | ★ 4.4k | 5d ago | Python | — |
| Claude Code Skills & Agents | 66 · Some gaps | Agent plugin / skillFree + model costs | ★ 1.7k | 3d ago | Python | Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The code shows API key configuration, authentication modules, sandboxes, and a billing reservation flow, but the supplied material does not explain least-privilege tool permissions, confirmation for destructive actions, sensitive-data lifecycle, or recovery. The MCP service can dynamically mount configurations from a request and serves HTTP on 0.0.0.0; the material does not show authentication on that route, so data-flow and external-effect controls are thin. agent.py identifies its Agno adaptation and retains an Apache notice, supporting partial attribution. The docx skill is marked proprietary, creating an unresolved scope tension with the repository’s Apache metadata.
The documentation covers architecture, startup, and dependencies, and the tool service validates configuration and returns some specific errors. However, the README and contributor guides describe differing layouts and startup paths, and the README documents default MinIO credentials. Static evidence does not establish dependency availability or compatibility; error handling includes useful status codes and messages, but startup connectivity exceptions are swallowed.
The README names developers, research teams, and enterprise internal tooling, with research, development, document, and integration use cases. Skill descriptions provide task-oriented triggers, and the browser skill lists concrete actions, but the boundaries and unsuitable cases for sandboxes, tools, and connectors are not well documented. Local and Docker setup and several model providers show broad environment fit.
The README, architecture guide, and quick-start lookup provide navigation, installation steps, configuration choices, commands, and examples. The repository map in the supplied guides differs, and naming conventions are not consistently established in the evidence. The LICENSE is Apache-2.0, but the docx skill is marked proprietary and its complete terms are not supplied, leaving the license scope unclear. The material lacks a clear release or changelog path and named maintenance ownership, though the README gives community links.
The product targets practical tasks and lists chat, research, application creation, media, documents, and third-party integrations. The Agent implementation supports tools, sub-agents, events, and streaming, indicating reusable value. These broad capabilities require substantial infrastructure, external services, and credentials; the supplied material gives little evidence about typical operating costs or limits, so cost-benefit support is thin.
The README setup and feature descriptions, AGENTS.md architecture map, CLAUDE.md development guide, and Agent and MCP source corroborate that the framework includes a server, tools, skills, and external integrations. Promotional capability claims lack per-feature implementation evidence or quantified results in the supplied material; documentation also mixes architecture rules with product capability claims, with limited separation of fact and inference. No deduction is made for tests that would require execution.
- The MCP example accepts configuration through a request and mounts external servers, while listening on all interfaces; the material does not show authentication or authorization for that route. Confirm network boundaries and access controls before deployment.
- The README shows default MinIO credentials; do not use the example credentials in shared or production environments.
- The docx skill is marked Proprietary while the repository supplies an Apache-2.0 license; the material does not clarify the skill’s separate license scope.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/ii-agent)<a href="https://followagents.com/en/agents/ii-agent"><img src="https://followagents.com/badge/ii-agent.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
🚀 Big Release Alert: Full-Stack Web Agent Are Live! 🌐 We’re thrilled to announce a major milestone for the Intelligent Internet Agent project! Say hello to v0.4, packed with powerful new features, integrations, and real-world full-stack demos. This is our biggest release yet! --- 🔧 New Features – Full-Stack Web Agent Showcases Experience the magic of autonomous full-stack development: - 🌟 Live Showcases → [View on GitHub](https://github.com/Intelligent-Internet/ii-agent-community#) …View on GitHub ↗ -
Release notes excerpt
Release v0.3 - Simplified Setup & Enhanced Experience We've made significant improvements to make ii-agent easier to set up and use, while adding powerful new features for a better AI agent experience. 🚀 Easier Setup - Streamlined Configuration: Simplified settings dialog with intuitive options that make initial setup much faster - Removed Complex Dependencies: Eliminated the need for Anthropic base URL configuration, reducing setup complexity - Better Default Settings: Intelligent defaults that work out of the box for most users ✨ Enhanced User Experience …View on GitHub ↗ -
Release notes excerpt
🛠 ii-agent v0.2 Release Notes We’re excited to announce the v0.2 release of the ii-agent! This update brings major feature upgrades, critical bug fixes, improved tooling, and support for more powerful LLM backends such as Gemini-2.5-pro. Here's what’s new: 🚀 What's Changed ✨ New Features - Prompt Enhancements & User Controls - Improved prompt generation logic and message handling. - Users can now cancel or edit prompts during interactions. - Tooling Enhancements - Introduced Message Tool and Return Control Tool for better user-agent interaction. …View on GitHub ↗
FAQ
Am I locked into one model provider?
What credentials are required before it can run?
What does the full development environment start?
Can I start only part of the system?
Thanks — we use this to improve the page.