← Open Source
MatrixAges

polywise

The open source agentic content system to make your contents alive. Self-hosted on any platform.

AI EngineeringGive agent knowledgeBuild agent workflow (SDK)TypeScript
Open on GitHub
Momentum
+0stars in 24 hours0.0%
663
Stars
34
Forks
+0
This week
2
Contributors
Created 2025-11-03 · Updated 2026-10-08 · #15310 today
Top developers

MatrixAges/polywise is ranked 15,310 with 663 stars.

Same-category comparison

MatrixAges/polywise is ranked 15,310 among these 8 peers; LucianoCirino/efficiency-nodes-comfyui is ranked 15,309.

Same-category comparison
NameRankMetrics
moeru-ai/xsai15,288
Language:
TypeScript
Stars:
665
Forks:
62
Description:
🤖💬 AI SDK, extra small.
Tencent/AICGSecEval15,296
Language:
Python
Stars:
664
Forks:
113
Description:
A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.
DataArcTech/ToG15,308
Language:
Python
Stars:
663
Forks:
74
Description:
This is the official github repo of Think-on-Graph (ICLR 2024). If you are interested in our work or willing to join our research team in Shenzhen, please feel free to contact us by email (xuchengjin@idea.edu.cn).
LucianoCirino/efficiency-nodes-comfyui15,309
Language:
Python
Stars:
663
Forks:
214
Description:
A collection of ComfyUI custom nodes. ⚠️ WARNING: This repo is no longer maintained.
mem0ai/mem0-mcp15,318
Language:
Python
Stars:
663
Forks:
146
snexus/llm-search15,322
Language:
Jupyter Notebook
Stars:
663
Forks:
71
Description:
Querying local documents, powered by LLM.
aarondfrancis/counselors15,326
Language:
TypeScript
Stars:
662
Forks:
28
Description:
Fan out prompts to multiple AI coding agents in parallel.
spring-ai-community/spring-ai-agent-utils15,335
Language:
Java
Stars:
662
Forks:
144
Description:
A Spring AI library that brings Claude Code-inspired tools and agent skills to your AI applications.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageTypeScript
CategoryAI Engineering
SubcategoryGive agent knowledge, Build agent workflow (SDK)
KeywordsGraph, Knowledge base, Memory management, Retrieval
Stars663
Forks34
Contributors2
Created date2025-11-03
Updated date2026-10-08
Stars in 1 day0
Stars in 7 days0
Rank15,310
Previous rank15,131
Rank change-179
7-day stars rank14,924
Previous 7-day stars rank14,935
7-day stars rank change11
Total stars rank15,506
Previous total stars rank15,484
Total stars rank change-22
README summary

You can use it from the command line or the desktop app to chat with models, save knowledge, retrieve context, and turn repeated working styles into reusable agents. 🚀 Install Polywise has two practical entry points: the CLI and the desktop app. CLI Install the CLI globally: Start the local Polywise service: keeps the service in the foreground. exits immediately and leaves the service running in the background. You can enable Auth login within the settings. Once enabled and a password

has been set, you will be required to log in when accessing the Web UI in order to access the API. This is crucial if you are deploying Polywise as a service on a server for remote access. Desktop App Download the latest desktop build from GitHub Releases. The desktop app is the easiest way to explore sessions, saved content, agents, and posts without working from the terminal. First Run For a first run, Polywise mainly needs: one available model

provider embedding and rerank models if you want saved-content retrieval You do not need to configure every provider or integration on day one. ⬆️ Upgrade CLI Desktop App Install the latest release from GitHub Releases. ⚡ Quick Start If you want the shortest path to first value: 1. Open and configure one provider you can actually use. Open and make sure the default chat model is available. Go to and ask one real question instead of sending . Save one short note

, page summary, or answer into Polywise. Mention that saved item again in chat to verify retrieval. 🧭 Usage Once one provider is connected and the default model is set, stop configuring and go use the product. Desktop App The app becomes easiest to understand when you use each area for one concrete job: for asking real questions, planning work, and staying inside your workspace context for fetching and extracting web content into the system for turning repeated instruction styles into reusable

collaborators for saving knowledge that should live longer than a chat reply Two shortcuts are worth learning early: brings files, agents, and other context into a session brings tools and skills into the workflow CLI The CLI is a thin wrapper over the backend API. By default it talks to ; set if your server lives elsewhere. Start with help instead of memorizing commands: Use when you need the exact input shape for a command: Common commands: When payloads become more

complex, pass JSON directly: 📚 Docs Intro CLI README 🎬 Intro Video Open the intro video file 💭 Motivation Polywise is built upon the belief that **truly intelligent AI requires truly intelligent memory**. It is not merely about storage, but rather a system capable of organically forming connections, strengthening through use, strategically forgetting, and continuously evolving. 📄 References This project was inspired by the following research papers: Long-lasting potentiation of synaptic transmission (1973). pdf>) The Organization of Behavior (1949). pdf>) A Spreading-Activation

Theory of Semantic Processing (1975). pdf>) 🙏 Acknowledgments Polywise stands on the shoulders of these excellent open-source projects: Libraries & Tools

Frequently asked questions

How many stars and forks are recorded?

MatrixAges/polywise has 663 stars and 34 forks.

What is the repository rank?

MatrixAges/polywise is ranked 15,310.

What language and category are recorded?

MatrixAges/polywise has 663 stars, uses TypeScript and belongs to AI Engineering.

Which repository is closest in rank?

MatrixAges/polywise is compared with LucianoCirino/efficiency-nodes-comfyui, ranked 15,309 with 663 stars.

Nearby in the ranking
Similar items