Potpie is an LLM codebase analysis platform and multi-agent orchestration framework designed to act as an AI software engineer. It parses repositories into a structured code knowledge graph, enabling AI agents to perform multi-hop reasoning, dependency tracing, and grounded technical analysis across large codebases.
The system distinguishes itself through a spec-driven development framework where agents generate detailed technical specifications and architecture plans before implementing multi-file code changes. It utilizes a durable execution engine to coordinate specialized AI personas for complex workflows, such as automated root-cause analysis for memory leaks and race conditions or the generation of pattern-aligned code that adheres to existing project conventions.
The platform covers a broad range of capabilities including semantic indexing via abstract syntax trees, automated pull request creation, and transitive change impact mapping. It also provides integrations for external documentation retrieval and connectivity with tools like GitHub, Jira, and Linear to manage the end-to-end software development lifecycle.
The project is implemented in Python and provides an agent interaction API with support for streaming responses.
