55,140 visible repositories in the index
121–144 of 179 · Most stars
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
Translated341 code animation style prompts, 196 reference still frames, and an offline picker, packaged as a Claude Code / Codex Skill, with one-click import and HTML video rendering support.
🐋 Run 284B DeepSeek-V4-Flash (<59GiB RAM, 44.4 tok/s pp, 9.1-14.7 tok/s) & 30B MoEs (25-111 tok/s) on a pure 64GB CPU at 256K ctx (0 GPUs). SwiGLU-H2, Stockfish-PVS L3 & 13ms Claude Code restore.
Claude Code on Android: AI-powered mobile coding IDE for Android — chat with a coding agent, run Linux commands, edit files, review diffs, and preview web apps directly from your phone. No root required.
Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
A code repository indexing tool to supercharge your LLM experience.
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.
repository for Publicly Available Clinical BERT Embeddings
This repo offers a simple interface that helps you to read&summerize research papers in pdf format. You can ask some questions after reading. This interface is developed based on openai API and using GPT-3.5-turbo model.
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.
Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.
A unified framework for building, evaluating, and recursively improving embodied agents. 🚀 Code release coming soon.
TranslatedQoder international and China multi-account reverse proxy gateway, a multi-account OpenAI-compatible gateway hub for Qoder's international and China dual regions — COSY-signed inference, stable device fingerprints to avoid risk control, OAuth device authorization for client-free login, daily check-in and Pro benefits, background scheduled task scheduler, web monitoring dashboard, supporting Codex / Claude Code and standard OpenAI clients
TranslatedMeme/sticker plugin for DeepSeek Harness: one-click picker in the composer, text-token memes, mood-driven sending, AI learns your images, marketplace packs.
Cleora AI is a general-purpose open-source model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data. Created by Synerise.com team.
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding && Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~41 in fast mode, 512K context. Plus GLM-5.3-Flash, Qwen3.8 and LFM3-Omni. MoE experts tiered across VRAM, pinned RAM and NVMe, with Xolotl Direct NVMe->VRAM. OpenAI + Anthropic API.
TranslatedBullFlow — Open-source enterprise RAG solution: knowledge base → automated marketing content → omnichannel publishing. The entire knowledge base pipeline runs on local open-source models, with no paid models needed; AI Agent creates image-text posts / images / videos, with one-click publishing to 17 platforms including Douyin, Xiaohongshu, WeChat Official Accounts, LinkedIn, and YouTube. Commercial-grade, multi-tenant, billing & admin built in. MIT
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
🧱 Experimental library for building inference engines