# potpie-ai/potpie

Context Graph for AI Native SDLC

Repository: https://github.com/potpie-ai/potpie
Canonical: https://ross.abutalabs.com/products/potpie
Homepage: https://potpie.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, artificial-intelligence, developer-tools, generative-ai, knowledge-graph, rag, ai-agents, ai-agents-framework, devtools, context-graph
Last push: 2026-08-25T13:15:49+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 91, longevity 53
- inputs: {"age_days": 751, "days_push": 8, "days_rel": 61, "gap_med": 13, "n_releases_24m": 20}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5698, forks 660 (observed 2026-08-28T04:09:28.044144+00:00)

## What it is
Potpie is an open-source context engine that turns a codebase and its development history into a living context graph for AI coding agents. It ships as a Python CLI that indexes repositories and integrates with coding harnesses so agents can answer questions, plan changes, and debug with project-specific context.

## Use cases
- give AI coding agents deep context about my codebase
- index a repository so agents can do multi-hop reasoning across components
- debug production failures with root cause analysis grounded in code history
- plan refactors and implementations that fit existing architecture
- onboard new engineers to a large or legacy codebase with code Q&A
- connect a context layer to harnesses like OpenAI Codex or Claude Code

## When to choose
- you want AI agents to reason over a large or complex codebase with project-specific context
- you need code-aware debugging, RCA, or implementation planning automation in your SDLC
- you prefer an open-source, self-hostable context engine with a simple CLI setup

## When to avoid
- you only need simple keyword code search without agent integration
- your project is tiny and an LLM already has enough context from the raw files
- you need a fully managed SaaS with no local daemon or CLI

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, rag, search-engine, developer-tools, cli, nlp
- domain: developer-tools, artificial-intelligence, large-language-models
- platform: python, cli, cross-platform, windows
- tags: context-graph, code-intelligence, knowledge-graph, ai-coding-assistant, codebase-indexing, sdlc-automation, mcp, ai-agents, retrieval-augmented-generation, command-line, macos, linux

## Member repositories
- potpie-ai/potpie (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.044144+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:53:37.155146+00:00, confidence not recorded.
  - readme: https://github.com/potpie-ai/potpie (fetched 2026-08-28T04:09:28.044144+00:00, sha 26adaf26a2a3)
  - homepage: https://potpie.ai (fetched 2026-08-29T08:49:14.761307+00:00, sha b385538721cd)
  - site_page: https://docs.potpie.ai/ (fetched 2026-08-29T08:49:14.772405+00:00, sha f2e9340f7abd)
  - site_page: https://docs.potpie.ai/introduction (fetched 2026-08-29T08:49:14.774149+00:00, sha 976cd886480d)
  - registry_pypi: https://pypi.org/pypi/potpie/json (fetched 2026-08-29T08:49:14.775787+00:00, sha d80564ac2299)
  - site_page: https://potpie.ai/pricing (fetched 2026-08-29T08:49:14.770305+00:00, sha bac87054c540)
- Data as of 2026-08-30T08:39:29.467469+00:00.