Tag: Open Source AI

Discover Xinity AI, the open-source on-premise AI platform enabling enterprises to deploy GPT-class models with zero data egress. Features OpenAI-compatible API, full management dashboard, multi-GPU orchestration, and 80% cost savings over cloud alternatives.

Discover athena-core, the open-source AI agent that controls your computer, automates browsers, executes Python code, and schedules tasks. Complete installation guide with real code examples from the repository.

Discover InSpatio-World, the open-source 4D world simulator that generates controllable video from text and depth. Learn installation, real code examples, trajectory control, and why researchers are abandoning traditional video diffusion for this spatial AI breakthrough.

Discover Adala, the open-source autonomous data labeling framework from HumanSignal. Learn how self-improving AI agents eliminate manual annotation through iterative learning with ground truth data. Complete setup guide, real code examples, and best practices included.

Parallax by Gradient is a distributed model serving framework that transforms personal devices into a decentralized AI cluster. Run 70B+ models across Mac, NVIDIA, and cloud nodes with pipeline parallelism, paged KV caching, and dynamic routing—no cloud API required.

Discover Letta Code, the open-source memory-first coding harness that creates persistent AI agents learning from every session. Unlike Claude Code or Codex CLI, Letta Code agents remember your codebase, improve over time, and work across any LLM provider including local models.

EurekaClaw is an open-source, local-first AI research agent that autonomously crawls arXiv, generates and proves theorems, runs experiments, and writes LaTeX papers. Discover installation, real code examples, and why it's replacing manual research workflows.

Discover how AirLLM enables running 70B parameter LLMs on 4GB GPUs and 405B models on 8GB VRAM through innovative layer-wise inference streaming. Complete setup guide, real code examples, and performance optimization tips included.

Discover free-voice-clone, the most comprehensive GitHub repository for open-source voice cloning, TTS, and music generation models. Stop paying for expensive APIs and build powerful audio AI locally with 40+ free models.

Discover See-Through, the SIGGRAPH 2026 research project that automatically decomposes anime illustrations into 23 inpainted, semantically organized layers for 2.5D animation pipelines. Free and open-source.

Discover how NousResearch's Nomos reasoning harness achieved 87/120 on Putnam 2025 through parallel workers, self-critique, and tournament selection. Complete setup guide and code analysis included.

Discover AIRI, the self-hosted AI companion platform inspired by Neuro-sama. Build your own digital being with real-time voice chat, game-playing agents, and complete privacy. Runs in browser, desktop, and mobile.

Discover how AgentGym-RL trains 7B parameter LLM agents to surpass GPT-4o on real-world multi-turn tasks using progressive horizon scaling reinforcement learning. Complete setup guide, code examples, and performance benchmarks included.

DataFlex is an open-source dynamic training framework that revolutionizes LLM training through intelligent data selection, mixture, and reweighting. Built on LLaMA-Factory, it delivers proven performance gains while slashing compute costs.

VoxCPM2 is a tokenizer-free multilingual TTS system with 48kHz output, voice design from descriptions, and controllable cloning. Built on a 2B parameter diffusion autoregressive architecture, it supports 30 languages with production-ready deployment options.

Discover NVIDIA PersonaPlex, a real-time full-duplex speech-to-speech model with independent voice and role control. Learn installation, code examples, and why it's disrupting voice AI.

Heretic is a fully automatic censorship removal tool for language models that uses advanced directional ablation with TPE optimization. Run one command to decensor AI models while preserving their intelligence. Over 3,000 community models created.

dot-skill transforms colleague communication data into interactive AI personas that preserve institutional knowledge. This open-source framework distills real cognitive patterns from chat logs, emails, and documents into installable Skills for Claude Code, Hermes, OpenClaw, and Codex.