AbliteratedOutTheBox
llama.cpp fork that abliterates at inference
← Smolmaxxing
Best Smolmaxxing alternatives
AI tools similar to Smolmaxxing — maxxing the ability to run different LLMs on the smallest devices possible
Hob
Open-source, on device alternative to Claude Cowork and ChatGPT
Gpt with taste
Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.
Project maya
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE)…
PolyStrata
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash…
Codex chatgpt web
Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using…
Hashference
Fund 45+ top AI models using your idle CPU/GPU compute
Z80-μLM
a 'Conversational AI' That Fits in 40KB
HN Wrapped 2025
an LLM reviews your year on HN
Sand3d
3D modeling in Python, built for LLMs.
Whale girl
鲸鲸 · 让 DeepSeek 用你的微信账号陪聊（Windows 桌面端 + WPF 启动器）。WeChat chat bot powered by DeepSeek/Qwen.
Trnrt
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By…
Llama modchip
🐋 Run 284B DeepSeek-V4-Flash (
Inferssd
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Qwenputer
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as…
Lot map
A live map beside the chat that shows what Claude Code is doing: tool calls, model steps, hooks, skills and subagents…
Agentes chat
Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run…
WebsiteBench
Can AI agents rebuild websites through browser exploration?
Mika
An on-device AI agent for Android that operates apps and the web to get things done for you.
Kairos
Open-source risk and fraud decisioning platform
Image to Video
Turn a photo into a 10-second video — free, no GPU queue
Mirage · On-device structured vision
22 MB vision model - description, boxes, masks, OCR, forms
AnyModelBot
🤖 Open-source, local-first alternative to Grok Bot, OpenAI dots and Claude Duet. Your own AI bots on any model: GPT…
NextTransformer
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with…
Kanzo
Self-hosted, sharable kanban for humans and agents. One 4.5 MB binary, 4.5 MB of RAM, 10 to 60 tokens per agent reply…
Price comparison
AI 订阅与卡网比价平台，说出需求，让 AI 帮你选。聚合 ChatGPT / Codex、Claude、Gemini 等代充或账号报价，对比价格走势、充值渠道与质保。AI-powered shopping and price…
SIE Serverless
managed inference powered by self-hostable stack
Qwen3.5 4B 3D Coder Studio
Interactive Three.js 3D scenes from a prompt
Flide
🔥🔥 The extremely fast inference engine for decision model
RigSpark
Know which AI to run on your own computer