Lists (2)
Stars
llama.cpp fork with TurboQuant WHT-rotated KV cache & weight compression + Gemma 4 MTP and Qwen 3.6 NextN speculative decoding (+30-50% throughput).
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.6, Claude Fable 5, Claude Sonnet 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.2, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.7
Cita: a Wikidata addon for Zotero with citations metadata support
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
An open-source AI agent that brings the power of Gemini directly into your terminal.
An extension for Thunderbird 3.0+ that allows you to sort folders in the folder pane.
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
Sotopia-RL: Reward Design for Social Intelligence
The absolute trainer to light up AI agents.
🌟Official code of our AAAI26 paper 🔍WebFilter
This is a repository for DKI group concerning the LLM-related papers alongside with code.
[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Build, enrich, and transform datasets using AI models with no code
Dedoc is a library (service) for automate documents parsing and bringing to a uniform format. It automatically extracts content, logical structure, tables, and meta information from textual electro…
(AAAI 2026) Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
Implementation for FP8/INT8 Rollout for RL training without performence drop.
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
An Open Source implementation of Notebook LM with more flexibility and features
xRFM: Accurate, scalable, and interpretable feature learning models for tabular data