ComoRAG
[AAAI 2026 🔥 Poster] ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning
GraphCanon updated 3w · GitHub synced 3w · 27 views this month
Decision brief
ComoRAG is a specialized tool for stateful long narrative reasoning with cognitive-inspired memory organization and RAG capabilities.
Good fit when
- When working on projects that require the processing of lengthy narratives while maintaining state throughout the story or document, such as in literature analysis or long-form content generation.
- For tasks where accurate recall and application of information over extended texts are crucial, leveraging ComoRAG's memory-organized design could be beneficial.
Avoid when
- When project requirements do not align with its specific cognitive-inspired memory organization, thus making it suboptimal for tasks needing a more general retrieval mechanism.
- If the application scope is limited to short-form text or does not require stateful reasoning across large texts, ComoRAG may introduce unnecessary complexities.
- Requirements:
- Requires Python version 3.10 or above and CUDA 12.x for optimal GPU utilization.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Slowing (337d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- 106 low (106 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install ComoRAGSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A tool designed for stateful long narrative reasoning with a focus on cognitive-inspired memory organization and RAG (Retrieval-Augmented Generation).
Capability facts
- Languages
- python
Source: github.language · Aug 1, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 1, 2026)
3. 🔑 **Environment variables**: Set your OpenAI API Key or local LLM/embedding paths as neededSource link
Source: README excerpt (regex_v1, Aug 1, 2026)
1. 🐍 **Python version**: Python 3.10 or above recommendedSource link
Tags
README
Installation & Environment 🛠️
- 🐍 Python version: Python 3.10 or above recommended
- 📦 Install dependencies:
pip install -r requirements.txt
- 🔑 Environment variables: Set your OpenAI API Key or local LLM/embedding paths as needed
- ⚙️ GPU (optional but recommended): CUDA 12.x supported by many dependencies in requirements.txt
For agents
This page has a .md twin and JSON over the API.