Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A local-first AI chat workspace for models, agents, skills, plugins, search, RAG, voice, memory, and artifacts.
| Date | Stars |
|---|---|
| 2026-07-31 | 1739 |
| 2026-08-04 | 1766 |
| 2026-08-06 | 1766 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
60.0
growth rate 0.00%/day
# Neo Chat <p align="center"> <img src="public/logo.png" width="96" alt="Neo Chat logo" /> </p> <p align="center"> <strong>A local-first AI chat workspace for models, agents, skills, plugins, search, RAG, voice, memory, and artifacts.</strong> </p> <p align="center"> <a href="README.zh-CN.md">简体中文</a> </p> <p align="center"> <a href="https://github.com/u14app/neo-chat/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/u14app/neo-chat/actions/workflows/ci.yml/badge.svg" /></a> <a href="https://github.com/u14app/neo-chat/actions/workflows/docker.yml"><img alt="Docker" src="https://github.com/u14app/neo-chat/actions/workflows/docker.yml/badge.svg" /></a> <img alt="Next.js" src="https://img.shields.io/badge/Next.js-16-black" /> <img alt="React" src="https://img.shields.io/badge/React-19-149eca" /> <img alt="TypeScript" src="https://img.shields.io/badge/TypeScript-6-3178c6" /> </p> Neo Chat is a self-hostable, local-first AI chat application built with Next.js, React, TypeScript, and Zustand. It brings multi-provider chat, assistant presets, text-only Skills, OpenAPI-style plugin tools, remote MCP servers and an optional local stdio bridge, web and local global search, knowledge-base RAG, opt-in encrypted cross-device sync, versioned backup and restore, local memory, an offline PWA, voice, generated media, rich message rendering, citations, and editable artifacts into one clean workspace. It is designed for people who want the power of modern AI workspaces without giving up local data ownership. Chat history, workspace metadata, skills, plugin configuration, memories, search indexes, and files stay in the browser by default; server routes act as controlled proxies for model providers, web search, RAG, document parsing, voice, plugin and MCP execution, and deployment health. ## v2.4.0 Highlights - Added an opt-in, end-to-end encrypted personal vault for convergent WebDAV or S3/MinIO synchronization across devices. Recovery keys, credentials, local baselines, search caches, and vectors never enter remote objects or ZIP files. - Added virtualized long-chat timelines, durable streaming checkpoints, bounded retry before visible output, partial-output continuation, reply snapshots, and explicit model selection when regenerating a sibling branch. - Added per-chat composer drafts, token and context usage summaries, guarded message-tree mutations during generation, and clearer offline behavior. - Added per-chat Agent mode for tool-call-capable models, with five localized, read-only built-ins orchestrated by the browser and auto-approved at runtime. - Added parameterized Skills and ordered bundles of up to four Skills, with validated slot values and reproducible invocation metadata. - Added collection-level chunking controls, Markdown heading-aware previews, explicit reindexing, hybrid lexical/vector retrieval, graceful lexical fallback, stable source previews, file filtering, and serial batch operations. - Added configurable client-side image compression for conversation, workspace, generated, and plugin images, with cancellation and original-file fallback. - Added legacy SSE compatibility for remote MCP, connection-stage-only fallback, encrypted install-time credentials, and an authenticated Docker stdio bridge whose commands remain fixed by deployment configuration. - Added a local-only offline PWA with strict no-API-cache boundaries, an accessible global-search modal, localized settings search and first-run model guidance, plus read-only local storage health diagnostics. - Scoped custom model metadata and locally encrypted server-default credentials to the matching provider, with fail-closed handling for invalid or unavailable defaults. - Preserved existing version 3 ZIP compatibility while advancing the local schema to version 6 and adding English, Chinese, and Japanese UI coverage. See [CHANGELOG.md](CHANGELOG.md) for the complete release notes. ## v2.2.0 Highligh
Excerpt of 31,256 characters
Read on GitHub
293
4
3
2
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2ff46048ec6b0551, llm:Repository topics and description: 'ai, ai-chat, gemini, openai, skills' and description: 'A local-first AI chat workspace for models, agents, skills, plugins, search, RAG, voice, memory, and artifacts.'
matched fp:2ff46048ec6b0551, llm:Repository topics and description: 'ai, ai-chat, gemini, openai, skills' and description: 'A local-first AI chat workspace for models, agents, skills, plugins, search, RAG, voice, memory, and artifacts.'
matched fp:2ff46048ec6b0551, llm:Repository topics and description: 'ai, ai-chat, gemini, openai, skills' and description: 'A local-first AI chat workspace for models, agents, skills, plugins, search, RAG, voice, memory, and artifacts.'
matched fp:2ff46048ec6b0551, llm:Repository topics and description: 'ai, ai-chat, gemini, openai, skills' and description: 'A local-first AI chat workspace for models, agents, skills, plugins, search, RAG, voice, memory, and artifacts.'