OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Potpie

An open-source Python framework and CLI that indexes a codebase and software-development lifecycle information into a context graph for AI agents.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Potpie — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Potpie when an AI agent needs context drawn from a repository and related engineering knowledge before answering, planning, debugging or coding.

Who it is for

  • Software developers using AI coding agents
  • Engineering teams that want repository-specific context in AI-assisted development
  • Teams evaluating a self-managed context-graph tool

Documented uses

  • Answer questions about a repository
  • Plan software changes using project context
  • Investigate debugging failures
  • Write code informed by indexed engineering knowledge
  • Record and retrieve durable project learnings
Before you choose

Requirements & limits

The repository is public and describes Potpie as open source under the Apache-2.0 license. Installation is documented through PyPI using uv or pip, with a local CLI setup flow.

  • Potpie uses a context-graph approach rather than only direct code lookup.
  • The CLI includes commands for setup, source registration, context resolution, search, recording project knowledge and diagnostics.
  • Listed integrations include GitHub, Linear, Jira and Confluence.
  • Listed coding harnesses include Claude Code, OpenAI Codex, Cursor and OpenCode.
  • A local web UI is available for exploring the graph.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Potpie for a repository

Install the CLI, run local setup, connect selected integrations and prepare an agent harness for repository-aware work.

Before you start

  • Python package installation through uv or pip
  • A repository to register
  • A supported coding harness selected during setup

Steps

  1. Install Potpie with the command below or the command below.

    Documented command
    uv tool install potpie
    Documented command
    python3 -m pip install --user potpie

  2. Run potpie setup, which provisions local configuration, storage, the daemon, a default pot and agent skills.

  3. Select integrations and the coding harness that Potpie should configure.

  4. Open the selected harness and ask it to use Potpie for the repository.

  5. Use potpie ui to open the local context-graph explorer, if needed.

Expected outcome

Potpie is configured locally and the selected agent harness can use the repository's project context.

Guide limitations

  • The documented setup flow does not describe the contents or behavior of every integration.
  • The repository says a separate manual ingest command is not required; the configured agent can ingest or update context when the task requires it.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
potpie-ai/potpie · Official homepage title · retained in its source language
How we review sourcesSuggest a correction