Is roampal-core open source?

Yes, licensed under Apache-2.0.

AgentIndex

Submit Tool

roampal-core

Active·★ 46·Apache-2.0·Updated 2026-05-12

★ Trending★ Code Assistant★ RAG / Knowledge Base

Outcome-based memory for Claude Code and OpenCode

Roampal Core provides outcome-based memory for AI coding assistants, enabling them to learn and improve their advice across multiple sessions. It automatically injects relevant context into conversations, promoting good advice and demoting bad advice to make the AI smarter over time.

#AI Memory

#LLM

#RAG

#Python

#Coding Assistant

#Outcome-Based Learning

#Context Injection

#Developer Tool

01

Features

01Implements an outcome-based memory system that learns from good and bad advice, making the AI smarter over time.

02Automatically and seamlessly injects relevant context into AI coding assistant conversations without manual intervention.

03Utilizes five distinct memory collections (working, history, patterns, memory_bank, books) to ensure persistent learning across sessions.

04Allows ingestion of external reference documents ('books' collection) that are permanently searchable by the AI.

05Compatible with popular AI coding tools such as Claude Code and OpenCode, with platform-specific integration mechanisms.

02

Compatibility

Python

Runtime

Verified via docs

Claude Code

AI Tool

Verified via docs

OpenCode

AI Tool

Verified via docs

Windows

OS

Verified via docs

macOS

OS

Verified via docs

Linux

OS

Verified via docs

03

Quick start

1

$ pip install roampal

2

$ roampal init

04

Use cases

↳Enhancing AI coding assistants to remember architecture, preferences, and conventions across different sessions.

↳Improving the quality of AI-generated code and suggestions by learning from past outcomes (promoting good, demoting bad).

↳Providing AI with a searchable personal knowledge base from uploaded documentation for development tasks.

↳Reducing the need to repeat context to AI coding tools, enabling more efficient and productive coding sessions.

05

Alternatives

mindsdb★ 39.2k

Federated Query Engine for AI - The only MCP Server you'll ever need

vs →

Brave Search MCP★ 86.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

vs →

ragflow★ 81.5k

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Comments

Log in to leave a comment

E
Ellis JohnsonMay 12, 2026
Outcome-based memory for Claude Code is a refreshing framing compared to simple storage
S
Sage RiveraApr 23, 2026
Works well with OpenCode too, the cross-tool memory is genuinely useful
J
Justice GarciaMar 21, 2026
Used across multiple projects, the outcome-focused context improves decision quality
E
Elliot NguyenMar 11, 2026
The memory model tracks what worked, not just what happened