Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
464 changes: 464 additions & 0 deletions COMPREHENSIVE_REFORM_SUMMARY.md

Large diffs are not rendered by default.

27 changes: 6 additions & 21 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -67,10 +67,10 @@ From now on, please use this name for both `git clone` and `docker pull` command
- Agent Zero uses the operating system as a tool to accomplish its tasks. It has no single-purpose tools pre-programmed. Instead, it can write its own code and use the terminal to create and use its own tools as needed.
- The only default tools in its arsenal are online search, memory features, communication (with the user and other agents), and code/terminal execution. Everything else is created by the agent itself or can be extended by the user.
- Tool usage functionality has been developed from scratch to be the most compatible and reliable, even with very small models.
- **Default Tools:** Agent Zero includes tools like knowledge, code execution, and communication.
- **Default Tools:** Agent Zero includes tools like knowledge, code execution, communication, GitHub integration, and OSINT toolkit.
- **Creating Custom Tools:** Extend Agent Zero's functionality by creating your own custom tools.
- **Instruments:** Instruments are a new type of tool that allow you to create custom functions and procedures that can be called by Agent Zero.
- **MCP Server Discovery:** Discover and install 250+ MCP servers from npm, GitHub, and Docker Hub with an integrated discovery interface. Browse servers, view details, and add them with one click.


3. **Advanced Multi-agent System with Memory Management**

Expand All @@ -80,20 +80,13 @@ From now on, please use this name for both `git clone` and `docker pull` command
- **Adaptive Coordination**: Intelligent task distribution across agents using sequential, parallel, or adaptive strategies
- **OpenRouter Integration**: Pre-configured support for OpenRouter SDK providing access to multiple LLM providers
- **Agent Hierarchy**: Every agent has a superior giving tasks and instructions, with subordinates helping break down complex problems
- **GitHub Integration**: Comprehensive GitHub API integration with backup/restore capabilities for knowledge base and memory
- See [Multi-Agent Memory System Guide](./QUICK_START_MULTI_AGENT.md) for quick setup

![Multi-agent](docs/res/physics.png)
![Multi-agent 2](docs/res/physics-2.png)

4. **Security & OSINT Capabilities** 🔐

- **Network Reconnaissance**: Perform port scanning, host discovery, service detection, and OS fingerprinting using nmap integration
- **OSINT Tools**: Gather intelligence from public sources including Shodan, Censys, DNS enumeration, and WHOIS lookups
- **Server Orchestration**: Execute commands across multiple servers simultaneously via SSH with parallel execution and file transfer
- **Web Security Testing**: Directory enumeration, SQL injection detection, XSS testing, HTTP header analysis, and SSL/TLS assessment
- **Distributed Operations**: String together multiple servers for coordinated tasks and operations
- **Ethical Guidelines**: All tools include legal warnings and are designed for authorized testing only
- See [Hacking Tools Documentation](./docs/HACKING_TOOLS.md) for detailed usage and setup

5. **Completely Customizable and Extensible**

Expand Down Expand Up @@ -124,11 +117,7 @@ From now on, please use this name for both `git clone` and `docker pull` command

- **Research** - `"Gather and summarize five recent AI papers about CoT prompting"`

- **Security Testing** - `"Perform network reconnaissance on my test lab at 192.168.1.0/24"`

- **OSINT Gathering** - `"Find all subdomains and DNS records for my domain example.com"`

- **Server Orchestration** - `"Check disk space and uptime across all 10 production servers simultaneously"`



Expand Down Expand Up @@ -187,19 +176,15 @@ docker run -p 50001:80 agent0ai/agent-zero
| [Extensibility](./docs/extensibility.md) | Extending Agent Zero |
| [Connectivity](./docs/connectivity.md) | External API endpoints, MCP server connections, A2A protocol |
| [Architecture](./docs/architecture.md) | System design and components |
| [OSINT & Security](./docs/osint_and_security.md) | OSINT tools, security testing, reconnaissance |
| [MCP Setup](./docs/mcp_setup.md) | MCP server configuration and management |
| [Contributing](./docs/contribution.md) | How to contribute |
| [Troubleshooting](./docs/troubleshooting.md) | Common issues and their solutions |


## 🎯 Changelog

### v0.9.7 - MCP Server Discovery (Upcoming)
- **MCP Server Discovery Interface**: Browse and install 250+ MCP servers from npm, GitHub, and Docker Hub
- **Integrated Discovery UI**: Search, filter, and view detailed information about available MCP servers
- **One-Click Configuration**: Generate and copy server configurations directly from the discovery interface
- **Multi-Source Discovery**: Automatic discovery from npm registry, GitHub repositories, and Docker Hub
- **Smart Caching**: 24-hour cache for improved performance with manual refresh option
- **Enhanced MCP Ecosystem**: Added 6 new community MCP servers to default configuration


### v0.9.6 - Memory Dashboard
[Release video](https://youtu.be/sizjAq2-d9s)
Expand Down
300 changes: 0 additions & 300 deletions conf/mcp_servers_available.json
Original file line number Diff line number Diff line change
@@ -1,300 +0,0 @@
{
"mcpServers": {
"memory-manager": {
"name": "Memory Manager",
"description": "Agent Zero Memory Management Server - Manages memories, knowledge base, and agent rules",
"type": "stdio",
"command": "python",
"args": [
"/a0/run_memory_mcp.py"
],
"env": {
"MEMORY_MCP_HOST": "localhost",
"MEMORY_MCP_PORT": "3001"
},
"enabled": true
},
"filesystem": {
"name": "Filesystem",
"description": "Access and manage files and directories with advanced search capabilities",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/tmp",
"/home"
],
"enabled": false,
"notes": "Provides read/write access to specified directories. Configure allowed paths in args."
},
"git": {
"name": "Git",
"description": "Git operations including status, diff, commit, and repository management",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-git"
],
"enabled": false,
"notes": "Provides Git integration. Must be run in a Git repository."
},
"github": {
"name": "GitHub",
"description": "GitHub API integration for issues, PRs, repositories, and code search",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-github"
],
"env": {
"GITHUB_TOKEN": "${GITHUB_TOKEN}"
},
"enabled": false,
"notes": "Requires GITHUB_TOKEN environment variable for authentication."
},
"gitlab": {
"name": "GitLab",
"description": "GitLab API integration for issues, merge requests, and repository management",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gitlab"
],
"env": {
"GITLAB_TOKEN": "${GITLAB_TOKEN}",
"GITLAB_URL": "${GITLAB_URL}"
},
"enabled": false,
"notes": "Requires GITLAB_TOKEN and optionally GITLAB_URL (defaults to gitlab.com)."
},
"postgres": {
"name": "PostgreSQL",
"description": "PostgreSQL database queries and schema inspection",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-postgres"
],
"env": {
"POSTGRES_CONNECTION_STRING": "${POSTGRES_CONNECTION_STRING}"
},
"enabled": false,
"notes": "Requires POSTGRES_CONNECTION_STRING environment variable."
},
"sqlite": {
"name": "SQLite",
"description": "SQLite database queries and management",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sqlite",
"/path/to/database.db"
],
"enabled": false,
"notes": "Configure database path in args."
},
"brave-search": {
"name": "Brave Search",
"description": "Web search using Brave Search API",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-brave-search"
],
"env": {
"BRAVE_API_KEY": "${BRAVE_API_KEY}"
},
"enabled": false,
"notes": "Requires BRAVE_API_KEY environment variable."
},
"google-drive": {
"name": "Google Drive",
"description": "Access and manage Google Drive files and folders",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gdrive"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}"
},
"enabled": false,
"notes": "Requires Google Cloud service account credentials."
},
"slack": {
"name": "Slack",
"description": "Send messages and interact with Slack workspaces",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-slack"
],
"env": {
"SLACK_BOT_TOKEN": "${SLACK_BOT_TOKEN}"
},
"enabled": false,
"notes": "Requires SLACK_BOT_TOKEN environment variable."
},
"puppeteer": {
"name": "Puppeteer",
"description": "Browser automation and web scraping with Puppeteer",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-puppeteer"
],
"enabled": false,
"notes": "Provides headless browser automation capabilities."
},
"docker": {
"name": "Docker",
"description": "Docker container management and operations",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"docker-mcp"
],
"enabled": false,
"notes": "Manage Docker containers, images, networks, and volumes."
},
"kubernetes": {
"name": "Kubernetes",
"description": "Kubernetes cluster management and operations",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-kubernetes"
],
"env": {
"KUBECONFIG": "${KUBECONFIG}"
},
"enabled": false,
"notes": "Requires kubectl and KUBECONFIG environment variable."
},
"sequential-thinking": {
"name": "Sequential Thinking",
"description": "Enhanced reasoning through structured thought processes",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
],
"enabled": false,
"notes": "Provides prompts for step-by-step reasoning."
},
"everything": {
"name": "Everything Search",
"description": "Fast file search using Everything search engine (Windows only)",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-everything"
],
"enabled": false,
"notes": "Windows only. Requires Everything search engine installed."
},
"aws-kb": {
"name": "AWS Knowledge Base",
"description": "Query AWS knowledge bases and documents",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-kb-retrieval"
],
"env": {
"AWS_ACCESS_KEY_ID": "${AWS_ACCESS_KEY_ID}",
"AWS_SECRET_ACCESS_KEY": "${AWS_SECRET_ACCESS_KEY}",
"AWS_REGION": "${AWS_REGION}"
},
"enabled": false,
"notes": "Requires AWS credentials and region."
},
"agentic-flow": {
"name": "agentic-flow",
"description": "Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration, ",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentic-flow"
],
"enabled": false,
"notes": "Source: https://www.npmjs.com/package/agentic-flow"
},
"git-mcp-server": {
"name": "git-mcp-server",
"description": "A secure and scalable Git MCP server enabling AI agents to perform comprehensive Git version control operations via STDIO and Streamable HTTP.",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@cyanheads/git-mcp-server"
],
"enabled": false,
"notes": "Source: https://www.npmjs.com/package/@cyanheads/git-mcp-server"
},
"mcp-server-mysql": {
"name": "mcp-server-mysql",
"description": "MCP server for interacting with MySQL databases based on Node",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@benborla29/mcp-server-mysql"
],
"enabled": false,
"notes": "Source: https://www.npmjs.com/package/@benborla29/mcp-server-mysql"
},
"mcp-server-atlassian-bitbucket": {
"name": "mcp-server-atlassian-bitbucket",
"description": "Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MC",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@aashari/mcp-server-atlassian-bitbucket"
],
"enabled": false,
"notes": "Source: https://www.npmjs.com/package/@aashari/mcp-server-atlassian-bitbucket"
},
"mcp-server": {
"name": "mcp-server",
"description": "Official Railway MCP server",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@railway/mcp-server"
],
"enabled": false,
"notes": "Source: https://www.npmjs.com/package/@railway/mcp-server"
},
"codacy-mcp": {
"name": "codacy-mcp",
"description": "Codacy MCP server",
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@codacy/codacy-mcp"
],
"enabled": false,
"notes": "Source: https://www.npmjs.com/package/@codacy/codacy-mcp"
}
}
}
Loading
Loading