Jan.ai
ChatGPT
GPT4All
Ollama
LM Studio
Claude AI
AnythingLLM
DeepSeek
Cachely.dev
nxCloud
Cachely is the managed self-hosted remote cache for Nx and Turborepo - the cache backend you'd otherwise build and run yourself, hosted for you on Cloudflare's edge (R2). It's a drop-in replacement for a DIY @nx/s3-cache / S3 bucket setup: point your build tool at Cachely with a token and two environment variables, and share build cache across CI and every developer's laptop.
Unlike a self-hosted cache, Cachely enforces read-only tokens at the API, so pull-request and fork builds can read but never write - closing the Nx cache-poisoning attack (CVE-2025-36852). It adds ROI reporting (the real build minutes and dollars the cache saved), per-tool insights, and build-optimization suggestions on top.
Pricing is a flat per-workspace subscription with no per-seat fees - add every developer, bot, and CI actor without watching the bill. Cachely never stores your source code; it caches only task outputs and their content hashes. Nx and Turborepo today; Bazel on the roadmap.
Cachely.devNo Cachely.dev videos yet. You could help us improve this page by suggesting one.
Based on our record, Jan.ai seems to be more popular. It has been mentiond 14 times since March 2021. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
There is also https://github.com/ml-explore/mlx-swift-lm which is what https://jan.ai uses. - Source: Hacker News / 28 days ago
Jan is the most polished open-source AI client available. Built with Tauri, it's lighter than Electron apps and has a genuinely clean, minimal design โ the kind where you notice the absence of clutter rather than the presence of features. It runs local models through llama.cpp and MLX, has native MCP support, an extension system, and an OpenAI-compatible API server at localhost:1337 so you can point other tools at... - Source: dev.to / 2 months ago
Jan takes a different approach, prioritizing user privacy and simplicity over advanced features with a 100% offline design that includes no telemetry and no cloud dependencies. - Source: dev.to / 9 months ago
I really like Jan, especially the organization's principles: https://jan.ai/ Main deal breaker for me when I tried it was I couldn't talk to multiple models at once, even if they were remote models on OpenRouter. If I ask a question in one chat, then switch to another chat and ask a question, it will block until the first one is done. Also Tauri apps feel pretty clunky on Linux for me. - Source: Hacker News / about 1 year ago
I believe there's a couple of similar apps like https://msty.app and https://jan.ai that do the same and allow you to plug in your own API keys. - Source: Hacker News / about 1 year ago
ChatGPT - ChatGPT is a powerful, open-source language model.
nxCloud - nxCloud is a commercial OwnCloud provider
GPT4All - A powerful assistant chatbot that you can run on your laptop
Ollama - The easiest way to run large language models locally
LM Studio - Discover, download, and run local LLMs
Claude AI - Claude is a next generation AI assistant built for work and trained to be safe, accurate, and secure. An AI assistant from Anthropic.
