Context, Memory & RAG tools for Local / Ollama

5 projects · 5 with stars to rank by · 28,016 combined stars · snapshot 2026-11-01

Everything that decides what the model actually sees: retrieval, memory stores, compaction, and the chat-with-your-data apps built on them.

Runs against a named local runtime: Ollama, llama.cpp, vLLM, LM Studio, llamafile or GPT4All.

Filter this live on the atlas →

Runs on: Windows WSL2 macOS Linux Docker

#ShotProject StarsPlugs into What it doesLang / licence / push
1Local GPTPromtEngineer/localGPT22,199
3 lists
Local / Ollama
LocalGPT is an open-source project for secure, private interactions with documents locally, featuring comprehensive model support, embeddings, API for RAG applications, and GUI options, with a focus on privacy and local data processing github
git clone https://github.com/PromtEngineer/localGPT.git
Python
MIT
2026-08-26
2Sidekickjohnbean393/Sidekick3,321
found by search
Local / Ollama
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
brew install --cask arcadi4/tap/sidekick-ai
Swift
MIT
2026-09-30
3AI-Novel-WriterEthanYoQ/AI-Novel-Writer2,215
found by search
Local / Ollama
书童 Pagekin(原名 AI 小说作家):开源免费的 AI 长篇小说写作桌面软件,从设定、蓝图到正文、审稿、定稿;支持拆解仿写、续写、改写,可导入写作 Skill(如去 AI 味)。模型需自行配置,作品在本地。Pagekin (formerly AI Novel Writer): free, open-source AI novel writing app for long novels and web fiction. Imitate, continue, rewrite; import writing skills. Local-first, no model bundled. Windows & macOS.
git clone https://github.com/EthanYoQ/AI-Novel-Writer.git
TypeScript
GPL-3.0
2026-10-29
4AnimaWorksxuiltul/animaworks269
1 list
Claude / AnthropicCodex / OpenAIGemini / GoogleCursorLocal / Ollama
Organization-as-code with brain-inspired memory
irm https://raw.githubusercontent.com/xuiltul/animaworks/main/scripts/setup.ps1 | iex
Python
Apache-2.0
2026-11-01
5fastdocparsepranjalparmar/fastdocparse12
1 list
Codex / OpenAILocal / Ollama
Extracts structured data from documents with an LLM, then grounds every field against the source text to flag hallucinated values automatically
pip install fastdocparse
Python
MIT
2026-10-29