Projects
Things I've built, mostly related to AI security and infrastructure tooling. Some are production systems, some are research tools.
Agent Framework
productionPythonModel Context ProtocolOAuth 2.0Anthropic ClaudePydanticPKCE
Framework for building LLM agents with MCP, OAuth 2.0 with PKCE, persistent memory, and extensible tool architecture. Runs 19 agents in production.
- Runs 19 specialized agents as daily drivers
- Full OAuth 2.0 with PKCE and dynamic client registration
- Built-in web search, memory storage, and Slack integration
- Type-safe architecture with Pydantic validation throughout
TaskManager
productionAstroNode.jsPostgreSQLOAuth 2.0PythonMCP
Task management platform with a full OAuth 2.0 auth server, Python SDK, and MCP server so my AI agents can manage tasks too.
- Full OAuth 2.0 authorization server with PKCE support
- Security testing suite with Vitest
- Python SDK with complete API coverage
- MCP server for integration with LLM frontends
SMS Communications Suite
productionGoPythonGSMSerial CommunicationTyperThreading
Send and receive SMS through GSM modems. Implementations in both Go and Python, with CLI tools for testing and operational use.
- Cross-platform GSM modem interface (Go + Python)
- Interactive CLI chat interface
- Integrates with TaskManager for out-of-band alerts
- Solid error handling and connection management
ReMarkable Research Toolkit
productionPythonGormapiAnthropic ClaudearXiv APIPDF Processing
Tools for managing research papers on reMarkable tablets, with AI-powered classification and automated organization.
- AI-powered research paper classification
- Zero-config rmapi binary management
- Integrates with TaskManager for research workflows
- PDF processing pipeline with content validation