An open API service indexing awesome lists of open source software.

https://github.com/saigontechnology/agentcrew

Chat application with multi-agents system supports multi-models and MCP
https://github.com/saigontechnology/agentcrew

ai-agents ai-assistant anthropic-claude mcp-client model-context-protocol multi-agent-systems terminal-app tool-use

Last synced: 4 days ago
JSON representation

Chat application with multi-agents system supports multi-models and MCP

Awesome Lists containing this project

README

          



AgentCrew Logo

AgentCrew


Your team of AI specialists for coding, research, and automation.

Run multiple focused agents from a desktop app, terminal, or API.


GitHub stars
PyPI Downloads
Pylint
License: Apache 2.0
Python Version

---

## What is AgentCrew?

AgentCrew lets you build and run a **team of specialized AI agents** instead of
relying on a single generic assistant.

- Give each agent a role — architect, coder, researcher, reviewer, or browser
operator.
- Agents can hand off work to teammates when a task fits their specialty.
- Use the same team in a desktop GUI, terminal, automated jobs, or over HTTP.

**[Watch the demo](https://github.com/user-attachments/assets/32876eac-b5e6-4608-bd5e-82d6fa4db80f)**

---

## Quick Start

### 1. Install

**macOS / Linux**

```bash
curl -LsSf https://agentcrew.dev/install.sh | bash
```

**Windows**

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://agentcrew.dev/install.ps1 | iex"
```

**pip (any platform)**

```bash
pip install agentcrew-ai
```

**Docker**

```bash
docker pull daltonnyx/agentcrew:latest
```

### 2. Add an API key

AgentCrew needs at least one AI provider key. Pick your preferred provider and
add the key:

**Option A — Environment variable**

```bash
export ANTHROPIC_API_KEY="sk-ant-..."
# or
export OPENAI_API_KEY="sk-proj-..."
# or
export GEMINI_API_KEY="AIza..."
```

**Option B — Config file**

```bash
mkdir -p ~/.AgentCrew
cat > ~/.AgentCrew/config.json << 'EOF'
{
"api_keys": {
"ANTHROPIC_API_KEY": "sk-ant-..."
}
}
EOF
```

**Option C — Subscription login**

If you have a **ChatGPT Plus / Pro** subscription or a **GitHub Copilot**
subscription, you can log in directly instead of using an API key:

```bash
# ChatGPT Plus / Pro (Codex models)
agentcrew chatgpt-auth
agentcrew chat --provider openai_codex

# GitHub Copilot
agentcrew copilot-auth
agentcrew chat --provider github_copilot
```

Supported providers: Anthropic Claude, OpenAI, Google Gemini, GitHub Copilot,
DeepInfra, Together AI, OpenCode, and any OpenAI-compatible endpoint.

> **Tip:** Not sure which provider to pick? Claude and OpenAI work great for
> most users. See [CONFIGURATION.md](CONFIGURATION.md) for provider-specific
> setup details.

### 3. Launch AgentCrew

```bash
# Desktop GUI
agentcrew chat

# Terminal mode
agentcrew chat --console
```

On the first launch, AgentCrew will walk you through creating your first agent
if you do not already have one.

### 4. Create your first agent

If you already have an API key set and want to create a new agent from scratch:

```bash
agentcrew create-agent
```

Or define one manually in `~/.AgentCrew/agents.toml`:

```toml
[[agents]]
name = "CodeAssistant"
description = "Helps write and review code"
tools = ["code_analysis", "file_editing", "web_search", "memory"]
system_prompt = """You are an expert software engineer.
Focus on code quality, security, and maintainability.
Today is {current_date}."""
```

### 5. Start working

Switch between agents, attach files, and let your team handle the rest.

```
/agent Architect
Design a clean API for a task manager.

@Coding
Implement the task manager in Python using FastAPI.

@Reviewer
Review the code for security issues.
```

---

## Ways to Use AgentCrew

| Mode | Command | Best for |
| ----------------- | ----------------------------------------------------------- | ----------------------------------------------------------- |
| **Desktop GUI** | `agentcrew chat` | Daily interactive work, file drag-and-drop, visual diffs |
| **Terminal** | `agentcrew chat --console` | Remote servers, low-overhead use, keyboard-driven workflows |
| **One-shot jobs** | `agentcrew job --agent "CodeAssistant" "your task" ./files` | CI/CD scripts, automation, batch processing |
| **HTTP API** | `agentcrew a2a-server` | Integrating with other apps, multi-instance setups |

**Job mode example:**

```bash
agentcrew job --agent "CodeAssistant" \
"Review for security issues" \
./src/**/*.py
```

**A2A server example:**

```bash
agentcrew a2a-server --host 0.0.0.0 --port 41241
```

---

## What Can Agents Do?

Agents come with a toolkit you enable per agent:

- **Code analysis** — understand repo structure, read files, grep, search
- **File editing** — write or modify files with search/replace blocks and
backups
- **Web search & extraction** — pull current information from the web
- **Browser automation** — navigate, click, fill forms, and capture screenshots
- **Command execution** — run safe shell commands with rate limits and audit
logs
- **Memory** — remember past conversations and retrieve relevant context
- **Voice** — speak and listen using ElevenLabs or DeepInfra (optional)
- **MCP tools** — connect to external services via the Model Context Protocol
- **Structured output** — enforce JSON schema responses in job mode

---

## Example Agent Configurations

See the [`examples/agents/`](examples/agents/) folder for ready-to-use agent
setups. To use an example:

```bash
cp examples/agents/agents.simple.toml ~/.AgentCrew/agents.toml
agentcrew chat
```

---

## Configuration Files

AgentCrew stores settings in `~/.AgentCrew/`:

| File | Purpose |
| ------------------ | ---------------------------------------- |
| `config.json` | API keys, theme, global preferences |
| `agents.toml` | Agent definitions, tools, system prompts |
| `mcp_servers.json` | External tool servers (optional) |

You can edit these files directly or manage them through the GUI settings panel.

---

## Common Console Commands

Inside the chat interface, type:

- `/agent ` — switch to another agent
- `/clear` — start a new conversation
- `/file ` — attach a file
- `/copy` — copy the last response
- `/think ` — enable reasoning mode
- `/voice` — start voice recording
- `/help` - show all available commands
- `exit` or `quit` — close AgentCrew

---

## Next Steps

- **[CONFIGURATION.md](CONFIGURATION.md)** — Detailed setup for providers,
agents, MCP servers, and advanced options
- **[CONTRIBUTING.md](CONTRIBUTING.md)** — How to build and contribute to
AgentCrew
- **[Docker guide](docker/DOCKER.md)** — Running AgentCrew in containers

---

## License

Apache 2.0 License. See [LICENSE](LICENSE) for details.