{"id":34072672,"url":"https://github.com/saigontechnology/agentcrew","last_synced_at":"2026-04-23T17:01:12.227Z","repository":{"id":279570195,"uuid":"939242211","full_name":"saigontechnology/AgentCrew","owner":"saigontechnology","description":"Chat application with multi-agents system supports multi-models and MCP","archived":false,"fork":false,"pushed_at":"2026-04-20T04:32:41.000Z","size":13019,"stargazers_count":186,"open_issues_count":2,"forks_count":34,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-04-20T06:29:32.408Z","etag":null,"topics":["ai-agents","ai-assistant","anthropic-claude","mcp-client","model-context-protocol","multi-agent-systems","terminal-app","tool-use"],"latest_commit_sha":null,"homepage":"https://agentcrew.dev","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/saigontechnology.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/funding.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"buy_me_a_coffee":"daltonnyx"}},"created_at":"2025-02-26T08:22:06.000Z","updated_at":"2026-04-20T04:32:44.000Z","dependencies_parsed_at":"2025-04-15T05:19:12.032Z","dependency_job_id":"38d72d7b-a869-43e7-bf6c-494a3d2797d0","html_url":"https://github.com/saigontechnology/AgentCrew","commit_stats":null,"previous_names":["daltonnyx/swissknife","daltonnyx/agentcrew","saigontechnology/agentcrew"],"tags_count":150,"template":false,"template_full_name":null,"purl":"pkg:github/saigontechnology/AgentCrew","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saigontechnology%2FAgentCrew","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saigontechnology%2FAgentCrew/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saigontechnology%2FAgentCrew/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saigontechnology%2FAgentCrew/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/saigontechnology","download_url":"https://codeload.github.com/saigontechnology/AgentCrew/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/saigontechnology%2FAgentCrew/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32189660,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-23T15:28:30.493Z","status":"ssl_error","status_checked_at":"2026-04-23T15:28:29.972Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","ai-assistant","anthropic-claude","mcp-client","model-context-protocol","multi-agent-systems","terminal-app","tool-use"],"created_at":"2025-12-14T08:14:42.683Z","updated_at":"2026-04-23T17:01:12.216Z","avatar_url":"https://github.com/saigontechnology.png","language":"Python","readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/saigontechnology/AgentCrew\"\u003e\n    \u003cimg src=\"https://saigontechnology.com/wp-content/uploads/2024/09/logo-black-1.svg\" alt=\"AgentCrew Logo\" width=\"300\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eAgentCrew\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eYour team of AI specialists for coding, research, and automation.\u003c/strong\u003e\u003cbr\u003e\n  Run multiple focused agents from a desktop app, terminal, or API.\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/saigontechnology/AgentCrew/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/saigontechnology/AgentCrew\" alt=\"GitHub stars\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pepy.tech/projects/agentcrew-ai\"\u003e\u003cimg src=\"https://static.pepy.tech/personalized-badge/agentcrew-ai?period=total\u0026units=INTERNATIONAL_SYSTEM\u0026left_color=LIGHTGREY\u0026right_color=BRIGHTGREEN\u0026left_text=Downloads\" alt=\"PyPI Downloads\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/saigontechnology/AgentCrew/actions/workflows/pylint.yml\"\u003e\u003cimg src=\"https://github.com/saigontechnology/AgentCrew/actions/workflows/pylint.yml/badge.svg\" alt=\"Pylint\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/saigontechnology/AgentCrew/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-Apache2.0-yellow.svg\" alt=\"License: Apache 2.0\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.python.org/downloads/release/python-3120/\"\u003e\u003cimg src=\"https://img.shields.io/badge/python-3.12+-blue.svg\" alt=\"Python Version\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## What is AgentCrew?\n\nAgentCrew lets you build and run a **team of specialized AI agents** instead of\nrelying on a single generic assistant.\n\n- Give each agent a role — architect, coder, researcher, reviewer, or browser\n  operator.\n- Agents can hand off work to teammates when a task fits their specialty.\n- Use the same team in a desktop GUI, terminal, automated jobs, or over HTTP.\n\n**[Watch the demo](https://github.com/user-attachments/assets/32876eac-b5e6-4608-bd5e-82d6fa4db80f)**\n\n---\n\n## Quick Start\n\n### 1. Install\n\n**macOS / Linux**\n\n```bash\ncurl -LsSf https://agentcrew.dev/install.sh | bash\n```\n\n**Windows**\n\n```powershell\npowershell -ExecutionPolicy ByPass -c \"irm https://agentcrew.dev/install.ps1 | iex\"\n```\n\n**pip (any platform)**\n\n```bash\npip install agentcrew-ai\n```\n\n**Docker**\n\n```bash\ndocker pull daltonnyx/agentcrew:latest\n```\n\n### 2. Add an API key\n\nAgentCrew needs at least one AI provider key. Pick your preferred provider and\nadd the key:\n\n**Option A — Environment variable**\n\n```bash\nexport ANTHROPIC_API_KEY=\"sk-ant-...\"\n# or\nexport OPENAI_API_KEY=\"sk-proj-...\"\n# or\nexport GEMINI_API_KEY=\"AIza...\"\n```\n\n**Option B — Config file**\n\n```bash\nmkdir -p ~/.AgentCrew\ncat \u003e ~/.AgentCrew/config.json \u003c\u003c 'EOF'\n{\n  \"api_keys\": {\n    \"ANTHROPIC_API_KEY\": \"sk-ant-...\"\n  }\n}\nEOF\n```\n\n**Option C — Subscription login**\n\nIf you have a **ChatGPT Plus / Pro** subscription or a **GitHub Copilot**\nsubscription, you can log in directly instead of using an API key:\n\n```bash\n# ChatGPT Plus / Pro (Codex models)\nagentcrew chatgpt-auth\nagentcrew chat --provider openai_codex\n\n# GitHub Copilot\nagentcrew copilot-auth\nagentcrew chat --provider github_copilot\n```\n\nSupported providers: Anthropic Claude, OpenAI, Google Gemini, GitHub Copilot,\nDeepInfra, Together AI, OpenCode, and any OpenAI-compatible endpoint.\n\n\u003e **Tip:** Not sure which provider to pick? Claude and OpenAI work great for\n\u003e most users. See [CONFIGURATION.md](CONFIGURATION.md) for provider-specific\n\u003e setup details.\n\n### 3. Launch AgentCrew\n\n```bash\n# Desktop GUI\nagentcrew chat\n\n# Terminal mode\nagentcrew chat --console\n```\n\nOn the first launch, AgentCrew will walk you through creating your first agent\nif you do not already have one.\n\n### 4. Create your first agent\n\nIf you already have an API key set and want to create a new agent from scratch:\n\n```bash\nagentcrew create-agent\n```\n\nOr define one manually in `~/.AgentCrew/agents.toml`:\n\n```toml\n[[agents]]\nname = \"CodeAssistant\"\ndescription = \"Helps write and review code\"\ntools = [\"code_analysis\", \"file_editing\", \"web_search\", \"memory\"]\nsystem_prompt = \"\"\"You are an expert software engineer.\nFocus on code quality, security, and maintainability.\nToday is {current_date}.\"\"\"\n```\n\n### 5. Start working\n\nSwitch between agents, attach files, and let your team handle the rest.\n\n```\n/agent Architect\nDesign a clean API for a task manager.\n\n@Coding\nImplement the task manager in Python using FastAPI.\n\n@Reviewer\nReview the code for security issues.\n```\n\n---\n\n## Ways to Use AgentCrew\n\n| Mode              | Command                                                     | Best for                                                    |\n| ----------------- | ----------------------------------------------------------- | ----------------------------------------------------------- |\n| **Desktop GUI**   | `agentcrew chat`                                            | Daily interactive work, file drag-and-drop, visual diffs    |\n| **Terminal**      | `agentcrew chat --console`                                  | Remote servers, low-overhead use, keyboard-driven workflows |\n| **One-shot jobs** | `agentcrew job --agent \"CodeAssistant\" \"your task\" ./files` | CI/CD scripts, automation, batch processing                 |\n| **HTTP API**      | `agentcrew a2a-server`                                      | Integrating with other apps, multi-instance setups          |\n\n**Job mode example:**\n\n```bash\nagentcrew job --agent \"CodeAssistant\" \\\n  \"Review for security issues\" \\\n  ./src/**/*.py\n```\n\n**A2A server example:**\n\n```bash\nagentcrew a2a-server --host 0.0.0.0 --port 41241\n```\n\n---\n\n## What Can Agents Do?\n\nAgents come with a toolkit you enable per agent:\n\n- **Code analysis** — understand repo structure, read files, grep, search\n- **File editing** — write or modify files with search/replace blocks and\n  backups\n- **Web search \u0026 extraction** — pull current information from the web\n- **Browser automation** — navigate, click, fill forms, and capture screenshots\n- **Command execution** — run safe shell commands with rate limits and audit\n  logs\n- **Memory** — remember past conversations and retrieve relevant context\n- **Voice** — speak and listen using ElevenLabs or DeepInfra (optional)\n- **MCP tools** — connect to external services via the Model Context Protocol\n- **Structured output** — enforce JSON schema responses in job mode\n\n---\n\n## Example Agent Configurations\n\nSee the [`examples/agents/`](examples/agents/) folder for ready-to-use agent\nsetups. To use an example:\n\n```bash\ncp examples/agents/agents.simple.toml ~/.AgentCrew/agents.toml\nagentcrew chat\n```\n\n---\n\n## Configuration Files\n\nAgentCrew stores settings in `~/.AgentCrew/`:\n\n| File               | Purpose                                  |\n| ------------------ | ---------------------------------------- |\n| `config.json`      | API keys, theme, global preferences      |\n| `agents.toml`      | Agent definitions, tools, system prompts |\n| `mcp_servers.json` | External tool servers (optional)         |\n\nYou can edit these files directly or manage them through the GUI settings panel.\n\n---\n\n## Common Console Commands\n\nInside the chat interface, type:\n\n- `/agent \u003cname\u003e` — switch to another agent\n- `/clear` — start a new conversation\n- `/file \u003cpath\u003e` — attach a file\n- `/copy` — copy the last response\n- `/think \u003clow|medium|high|xhigh\u003e` — enable reasoning mode\n- `/voice` — start voice recording\n- `/help` - show all available commands\n- `exit` or `quit` — close AgentCrew\n\n---\n\n## Next Steps\n\n- **[CONFIGURATION.md](CONFIGURATION.md)** — Detailed setup for providers,\n  agents, MCP servers, and advanced options\n- **[CONTRIBUTING.md](CONTRIBUTING.md)** — How to build and contribute to\n  AgentCrew\n- **[Docker guide](docker/DOCKER.md)** — Running AgentCrew in containers\n\n---\n\n## License\n\nApache 2.0 License. See [LICENSE](LICENSE) for details.\n","funding_links":["https://buymeacoffee.com/daltonnyx"],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaigontechnology%2Fagentcrew","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsaigontechnology%2Fagentcrew","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsaigontechnology%2Fagentcrew/lists"}