AgentCrew
Your team of AI specialists for coding, research, and automation.
Build a crew of focused agents that code, research, architect, review, and automate.
Use them from a desktop app, terminal, HTTP API, or CI pipeline.
Why AgentCrew?
AgentCrew lets you build a team of specialists, each with the right tools and personality for the job.
- An Architect that weighs trade-offs before a line of code is written.
- A Coder that implements cleanly — no scope creep, no over-engineering.
- A Reviewer that catches what others miss.
- A Researcher that cross-references multiple sources before drawing conclusions.
- A Browser Operator that navigates web apps, fills forms, and clicks through workflows.
Agents hand off work to each other when a task needs a different specialty. You stay in control, orchestrating the team from one interface.
When AgentCrew fits: You have a complex task that benefits from multiple perspectives — building a feature from design to deployment, researching and writing a report, or automating a multi-step workflow.
When a single assistant is enough: You need one focused conversation with no tool access or multi-agent orchestration.
Quick Start
1. Install (10 seconds)
macOS / Linux
curl -LsSf https://agentcrew.dev/install.sh | bash
Windows
powershell -ExecutionPolicy ByPass -c "irm https://agentcrew.dev/install.ps1 | iex"
pip (any platform)
pip install agentcrew-ai
2. Add an API key — or skip this step entirely
Most tools need a paid API key. AgentCrew supports several options that don't require one:
Subscription-based (no API key needed):
# OpenCode Go — curated open-source models (GLM, Kimi, MiMo, Qwen)
agentcrew chat --provider opencode_go
# ChatGPT Plus / Pro (uses Codex models)
agentcrew chatgpt-auth
agentcrew chat --provider openai_codex
# GitHub Copilot subscribers
agentcrew copilot-auth
agentcrew chat --provider github_copilot
Pay-as-you-go API keys:
export CROFAI_API_KEY="your-key" # CrofAI — OpenAI-compatible, budget-friendly
export DEEPINFRA_API_KEY="your-key" # DeepInfra — open models (LLaMA, Qwen, etc.)
export OPENAI_API_KEY="sk-proj-..." # OpenAI GPT-4o
export GEMINI_API_KEY="AIza..." # Google Gemini — free tier available
Or store keys in ~/.AgentCrew/config.json:
{
"api_keys": {
"CROFAI_API_KEY": "your-key",
"OPENAI_API_KEY": "sk-proj-..."
}
}
Custom providers:
Custom providers such as Ollama, llama.cpp, and LM Studio are configured in
the same ~/.AgentCrew/config.json file.
See Custom LLM Providers for the full
schema, llama.cpp configuration, model capabilities, and sampling options.
All supported providers:
| Provider | Cost profile | Best for |
|---|---|---|
| OpenCode Go | Subscription-based | Curated open-source models, no API key |
| CrofAI | Pay-as-you-go, low cost | General tasks, OpenAI-compatible |
| Command Code | Subscription-based | Frontier models via subscription |
| DeepInfra | Pay-as-you-go, low cost | Open models (LLaMA, Qwen, etc.) |
| Together AI | Pay-as-you-go | Open models, fine-tuning |
| Fireworks | Pay-as-you-go | Fast open model inference |
| OpenAI | Per-token pricing | GPT-4o, broad ecosystem |
| Anthropic | Per-token pricing | Claude family |
| Google Gemini | Free tier available | Budget-friendly, strong reasoning |
| GitHub Copilot | Included with subscription | Coding-focused, no extra cost |
| ChatGPT Codex | Included with Plus/Pro sub | No extra cost for subscribers |
| Custom | Free (local) | Fully offline (Ollama, llama.cpp...) |
Which provider should I pick?
If you... Pick this Want curated open-source models OpenCode Go — subscription-based Want low-cost, open-source friendly CrofAI or DeepInfra Have a Command Code subscription Command Code Have ChatGPT Plus / Pro openai_codex— no extra costHave GitHub Copilot github_copilot— no extra costWant a free tier to start Google Gemini Need fully offline / air-gapped Custom (Ollama, llama.cpp, etc.)
3. Launch
# Desktop GUI (default)
agentcrew chat
# Terminal mode — great for SSH, tmux, low-resource environments
agentcrew chat --console
On the first launch, AgentCrew walks you through creating your first agent.
4. Create your first agent
agentcrew create-agent
Or define one manually in ~/.AgentCrew/agents.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
> /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.
The @AgentName syntax hands off a subtask to another agent. The receiving
agent picks up with full context and its own specialized tools and instructions.
What's in the box?
Four ways to use AgentCrew
| Mode | Command | Best for |
|---|---|---|
| Desktop GUI | agentcrew chat |
Daily work, drag-and-drop files, visual diffs |
| Terminal | agentcrew chat --console |
Remote servers, keyboard-first workflows |
| One-shot jobs | agentcrew job --agent "Name" "task" ./files |
CI/CD, batch processing, automation |
| HTTP API | agentcrew a2a-server |
Integrate with other apps, multi-instance agent networks |
Job mode example:
agentcrew job --agent "CodeAssistant" \
"Review for security issues" \
./src/**/*.py
A2A server example:
agentcrew a2a-server --host 0.0.0.0 --port 41241
Tools — enable only what each agent needs
| Tool | What it does | When to enable it |
|---|---|---|
code_analysis |
Read files, grep, analyze repo structure | Any agent working with code |
file_editing |
Write/modify files (search-replace blocks, backups) | Coding and documentation agents |
web_search |
Search the web via Tavily | Research and fact-checking agents |
fetch_webpage |
Extract content from a URL | Research agents |
browser |
Full browser automation (navigate, click, form fill) | QA, web scraping, form-filling agents |
command_execution |
Run shell commands (rate limits, audit logs) | DevOps, code execution agents |
memory |
Store and retrieve conversation context | Almost every agent |
clipboard |
Read/write system clipboard | Agents that interact with other apps |
adaptive_learning |
Learn behavioral patterns from interactions | Agents that should adapt over time |
voice |
Speak and listen (ElevenLabs or DeepInfra) | Voice-interactive agents |
| MCP tools | External tools via Model Context Protocol | Any agent needing external integrations |
transfer |
Hand off tasks to other agents | Automatically available in multi-agent setups |
Communication protocols
AgentCrew speaks three protocols:
- Console / GUI — Human-to-agent: the chat interface you use daily.
- A2A (Agent-to-Agent) — HTTP+JSON-RPC protocol. Connect multiple AgentCrew instances so one can delegate to agents on another machine.
- ACP (Agent Communication Protocol) — WebSocket protocol for custom clients, IDE integrations, and headless agent control.
Real-world workflows
🧑💻 Feature development — from idea to PR
You: @Architect Design the data model for a multi-tenant SaaS app
@Coding Implement it with SQLAlchemy
@Reviewer Review the code for security issues
Three agents, one conversation. The Architect thinks about trade-offs, the Coder implements cleanly, the Reviewer catches blind spots.
📊 Financial report generation
# Five specialized agents, each focused on one step
[[agents]] name = "FinancialDataExtractor" # parse raw statements
[[agents]] name = "RatioAnalyst" # compute key ratios
[[agents]] name = "TrendAnalyst" # spot patterns over time
[[agents]] name = "RiskAssessor" # flag red flags
[[agents]] name = "ReportingSynthesizer" # compile into final report
Each agent handles one step of the pipeline. The Synthesizer collects all
findings and writes the final report. See
examples/agents/agents-financial-report.toml.
🌐 Multi-instance agent network
# Server A — hosts research agents
server-a$ agentcrew a2a-server --port 41241
# Server B — hosts coding agents
server-b$ agentcrew a2a-server --port 41241
# Your machine — connects to both
# ~/.AgentCrew/agents.toml:
[[remote_agents]]
name = "RemoteResearcher"
url = "http://server-a:41241"
[[remote_agents]]
name = "RemoteCoder"
url = "http://server-b:41241"
Common commands (once you're inside)
| Command | What it does |
|---|---|
/agent <name> |
Switch to another agent |
@<name> <task> |
Hand off a subtask |
/clear |
Start a fresh conversation |
/file <path> |
Attach a file |
/think <low|medium|high|xhigh> |
Enable extended reasoning |
/model <provider/model> |
Switch AI model |
/voice |
Toggle voice recording |
/help |
Show all commands |
exit or quit |
Exit |
Ctrl+C |
Stop the current response |
Next steps
- GUIDE_GETTING_STARTED.md — Your first 30 minutes with AgentCrew: install, create agents, run a multi-agent workflow.
- GUIDE_WORKFLOWS.md — When and why: pattern guides for common scenarios with decision trees and best practices.
- CONFIGURATION.md — Deep dive into providers, agents, MCP servers, themes, and plugins.
- PLUGIN_DEVELOPMENT.md — Build plugins with EventBus subscriptions and hooks.
- CONTRIBUTING.md — How to build, test, and contribute.
- Docker guide — Running AgentCrew in containers.
License
Apache 2.0 License. See LICENSE for details.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agentcrew_ai-0.21.2.tar.gz.
File metadata
- Download URL: agentcrew_ai-0.21.2.tar.gz
- Upload date:
- Size: 1.6 MB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
uv/0.12.6 {"installer":{"name":"uv","version":"0.12.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
92c0c128e9cc1644581d433315b729eb2af073c86544dca3bd3dd9a0fcf346e7
|
|
| MD5 |
157ef90e106cb3625b0a1ba681a13296
|
|
| BLAKE2b-256 |
cad326df72c9a435311cd1cca408ec337b5690ed44e09c81ad9a5b40fcce64cb
|
File details
Details for the file agentcrew_ai-0.21.2-py3-none-any.whl.
File metadata
- Download URL: agentcrew_ai-0.21.2-py3-none-any.whl
- Upload date:
- Size: 1.8 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
uv/0.12.6 {"installer":{"name":"uv","version":"0.12.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
832b53fd84618e9aa0931ebbd50f15138ec7a54b05a40202101e5b7d2c0dd51a
|
|
| MD5 |
a932fd0a8d5f6a83dafcaf81e0ebfd5c
|
|
| BLAKE2b-256 |
99e7af7445817639a6ca1399510c2f4440174d8edce468b0c9b35aba2cf8d00e
|
