🔓✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
// ragChatGPTNextWeb/⟨TypeScript⟩★ 88,619◷ MIT[ claude ]
RAG & Knowledge for Mobile
25 RAG & Knowledge that run on Mobile for Claude, ranked by overall signal. Top pick right now: NextChat (★88,619). A live, auto-updated collection from the Claudeers registry.
// ranked (25)
🔓
🔓Sub2API is an open-source relay platform that unifies Claude, OpenAI, Gemini, and Antigravity subscriptions into a single endpoint. It supports account shari…
// ragWei-Shaw/⟨Go⟩★ 37,064◷ LGPL-3.0[ claude ]
🔓Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
// ragvolcengine/⟨Python⟩★ 31,044◷ AGPL-3.0[ claude ]
🔓Multi-channel AI proxy with intelligent key rotation. 智能密钥轮询的多渠道 AI 代理。
// ragtbphp/⟨Go⟩★ 6,287◷ MIT[ claude ]
🔓An awesome & curated list of best LLMOps tools for developers
// ragtensorchord/⟨Shell⟩★ 5,917◷ CC0-1.0[ claude ]
🔓The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separa…
// ragraullenchai/⟨Python⟩★ 3,513◷ Apache-2.0[ claude ]
🔓The largest open-source medical AI skills library for OpenClaw🦞.
// ragFreedomIntelligence/⟨Python⟩★ 2,935[ claude ]
🔓A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.
// ragBitterbot-AI/⟨TypeScript⟩★ 2,453◷ NOASSERTION[ claude ]
🔓OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool call…
// ragwaybarrios/⟨Python⟩★ 1,534◷ Apache-2.0[ claude ]
🔓Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, memory and security gates.
// ragagentlas-ai/⟨Python⟩★ 1,158◷ Apache-2.0[ claude ]
🔓ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloads, seamless closed LLM integration, and offlin…
// ragxark-argo/⟨Python⟩★ 813◷ NOASSERTION[ claude ]
🔓AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
// ragverygoodplugins/⟨Python⟩★ 798◷ MIT[ claude ]
🔓One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.
// ragrahilp/⟨TypeScript⟩★ 716◷ MIT[ claude ]
🔓🔴 VERY LARGE AI TOOL LIST! 🔴 Curated list of AI Tools - Updated 2026
// rageudk/★ 571◷ CC0-1.0[ claude ]
🔓
🔓An open standard for portable, interoperable AI memory across tools, sessions, and devices.
// ragSMJAI/⟨TypeScript⟩★ 76◷ NOASSERTION[ claude ]
🔓AI-powered file organization and context engineering that understands content, not patterns. Automatically sorts temporary scripts from permanent docs while…
// ragramakay/⟨TypeScript⟩★ 69◷ MIT[ claude ]
🔓ContextX: Context-driven AI development framework powered by Claude Code. Transform documents into complete projects with intelligent agent workflows.
// ragyzfly/⟨Shell⟩★ 66◷ Apache-2.0[ claude ]
🔓Local, deterministic, git-native memory for coding agents — one set of Markdown files serves Claude Code, Codex, Gemini CLI, Cursor, and Grok CLI.
// raggrpcer/⟨JavaScript⟩★ 12◷ Apache-2.0[ claude ]
🔓Graph + local semantic context for Obsidian, with guarded remote MCP access and edits from Codex, ChatGPT, Claude, and any MCP client.
// ragjunnnnnw00/⟨TypeScript⟩★ 12◷ MIT[ claude ]
🔓Unofficial source-linked AWS best practices for every AWS service, organized by Well-Architected pillar for Claude Code, OpenAI Codex, and AI coding agents.
// ragferdinandobons/⟨Python⟩★ 37◷ MIT[ claude ]
🔓Operating Soul for AI coding agents that captures how to think, not just rules — principle-over-rule, 7 delegation levels (Tell→Delegate), a git-gated learni…
// ragtomdwipo/⟨Shell⟩★ 24◷ MIT[ claude ]
🔓Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works wit…
// ragVonderVuflya/⟨Python⟩★ 21◷ AGPL-3.0[ claude ]
🔓Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Ollama/VLLM/llama.cp…
// ragiKislay/⟨Python⟩★ 17◷ Apache-2.0[ claude ]
🔓Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.
// ragozankasikci/⟨Python⟩★ 13◷ MIT[ claude ]
// at a glance
| project | ★ stars | language | license | works with |
|---|---|---|---|---|
| NextChat | 88,619 | TypeScript | MIT | claude |
| sub2api | 37,064 | Go | LGPL-3.0 | claude |
| OpenViking | 31,044 | Python | AGPL-3.0 | claude |
| gpt-load | 6,287 | Go | MIT | claude |
| Awesome-LLMOps | 5,917 | Shell | CC0-1.0 | claude |
| Rapid-MLX | 3,513 | Python | Apache-2.0 | claude |
| OpenClaw-Medical-Skills | 2,935 | Python | — | claude |
| bitterbot-desktop | 2,453 | TypeScript | NOASSERTION | claude |
| vllm-mlx | 1,534 | Python | Apache-2.0 | claude |
| Hephaestus | 1,158 | Python | Apache-2.0 | claude |
// faq
What are the best rag & knowledge for mobile?
NextChat, sub2api, OpenViking, and more — ranked by community score from 25 options on Claudeers.
How many are listed?
25 are currently ranked on this page, refreshed continuously from the live registry.
Are they free to use?
Every project on Claudeers is free to browse and install; many are open source. Listing is free too.
Own a rag project for Claude? Suggest it free.
Suggest your project →