#145 · Primary category： AI Coding Assistants
potpie
Context Graph for AI Native SDLC
Project last updated：08/29/26
GitHub Stars
5.7K
Forks
666
Contributors
45
License
Apache-2.0
Why we included this project
Potpie is for teams whose AI agents produce shallow suggestions because they lack real codebase context. It turns your code, history, and engineering workflows into a context graph that agents query, so they can plan changes, debug failures, and write code that fits your conventions instead of guessing from a single file. Setup runs through a CLI wizard that provisions local storage, a daemon, and agent skills, and it plugs into your existing coding harness rather than demanding a separate platform. Teams doing spec-driven development will like how it captures planning and architecture decisions to keep AI-generated changes aligned with project conventions.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.