sony-a7m4-custom-firmware

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Put the look of a .cube LUT into your RICOH GR IV as an Image Control look. Fits the LUT, then builds firmware from RICOH's official 1.11.

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

Official repository for "OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining".

Agents for robot physical reasoning

自动检测 Codex(ChatGPT 桌面版)额度重置时间，到点用 UI 注入发送「继续」续跑 / Auto-resume Codex desktop tasks after the 5h usage-limit window resets

LlamaIndex is the document processing platform for AI

The open-source AI workbench for scientific research

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

A git-aware, read-only file viewer for herdr. Mouse friendly, keyboard-driven TUI: tree + content pane with diffs, rendered markdown, and syntax highlighting.

An open-source model family for long-form speech, dialogue synthesis, voice design, sound effects, and real-time streaming TTS

SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Train transformer language models with reinforcement learning.

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, P…

AdaHVLA connects task-level reasoning and memory with vision-language-action (VLA) execution through an adaptive harness. Preprint version of our paper is coming soon. The real-world deployement pa…

JEPA Policy: paired action and future representation prediction for robot imitation learning

[EMNLP 2026 Oral] RoboSPA Official Code Repo

The agent that grows with you

Offical Implementation of "PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing"

Embodied In-Context Learning for GPT-6 Astra

Very simple regulation can mitigate reconstruction-generation gap.