#llm Repositories
2,314 repositories total
The official Redis MCP Server is a natural language interface designed for agentic applications to manage and search data in Redis efficiently
End-to-end AI-powered academic paper writing system โ from idea generation and literature search to experiment execution, result backfill, and LaTeX paper compilation. Supports multi-LLM routing, SSH remote training, incremental sync, and anti-AI-detection writing style.
Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.
[CVPR 2025] Official implementation for "Empowering LLMs to Understand and Generate Complex Vector Graphics" https://arxiv.org/abs/2412.11102
โจโจWoodpecker: Hallucination Correction for Multimodal Large Language Models
Free MIT AI coding agent โ no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & desktop automation, built in Rust.
Embedded agents your customers use to automate work, build views, and connect their tools.
Private local model studio, AI chat, and agent workspace powered by WebGPU and WebLLM.
A resource repository for machine unlearning in large language models
Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.
Free AI-Tips is a FREE Newsletter provided by Business Science. It comes with bite-sized Python AI for Business tutorials every week. Sign up here:
AI-powered assistant workbench for FreeCAD โ generate 3D models from natural language
๐ Better text detection by combining multiple OCR engines (EasyOCR, Tesseract, and Pororo) with ๐ง LLM.
SenWeaver IDE โ an openโsource multiโagent collaborative AI programming platform that comes with a builtโin autonomous online reinforcement learning (APO) engine. The system learns in realโtime from every user interaction, can independently build knowledge bases and use internal data for training, automatically optimising prompt strategies and becoming smarter the more you use it. It supports parallel collaboration between a main agent and subโagents, over 40 builtโin tools (file/terminal/search/documentation/browser/visual), AI code security detection and repair, WebRTC P2P remote collaboration, and flexible switching among multiple models (GPT/Claude/DeepSeek/Ollama, etc.). Licensed under MIT, it is fully openโsource and can be selfโdeployed on both client and backend fullโstack.
AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis
[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchestration.
[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers โ OAuth login in the web UI, no API keys
A local AI agent harness in Go that runs 24/7 with auto-built tools, MCP, and Ollama
This project aims to collect open-source datasets for table intelligence tasks (such as table question answering, table-to-text generation, etc.), organize raw data into instruction fine-tuning format and fine-tune LLMs, thereby enhancing LLM's understanding of tabular data, and finally building large language models specifically oriented towards table intelligence tasks.
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.
Secure memory management for AI Agents โข Ensures data integrity โข Reduces hallucinations โข Maintains consistent long-term context
Ollama alternative for Rockchip NPU: An efficient solution for running AI and Deep learning models on Rockchip devices with optimized NPU support (rkllm)
AI image generation. Every day, a verse of a classical Chinese poem to generate an AI image.
A framework to evaluate the generalization capability of safety alignment for LLMs
๐ค Optimum Intel: Accelerate inference with Intel optimization tools
a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP
๐งฟ AutorizePro is a powerful authorization enforcement detection Burp plugin that significantly reduces the false positive rate and improves the efficiency of vulnerability detection by adding AI-assisted analysis && further optimizing the detection logic. [ AutorizePro is an authorization enforcement detection extension for burp suite. By adding Ai-assisted analysis, it significantly reduces the false positive rate and improves the efficiency of vulnerability detection.
Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.
A powerful and flexible frontend & AI gateway for large language models, supporting 21+ mainstream AI model providers.
Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.
The Theia IDE: an open-source, AI-native IDE for desktop and browser, built on the Theia Platform and Theia AI. Bring your own key for any LLM, with MCP, Agent Skills, Claude Code and GitHub Copilot support.
AI-Hedge-Fund for Crypto ๐ AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent decision-making.
RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.
MDA Open Spec โ a Markdown superset for agent-facing documents. One .mda source compiles to drop-in SKILL.md, AGENTS.md, MCP-SERVER.md, and CLAUDE.md. JSON Schema validated, with typed dependency graph, footnote relationships, and Sigstore-anchored signatures. For agentskills.io and AAIF runtimes.