#llm Repositories
2,314 repositories total
โท๏ธ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)
A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry
Armor-breaking experiment project targeting GPT 6.0 and WorkBuddy V4.1 Flash
"AI-Compass" will guide the community in navigating the ocean of AI technology. Whether you are a beginner or an advanced developer, you can find a path towards all major AI directions here. It aims to help developers systematically understand AIโs core concepts, mainstream technologies, cuttingโedge trends, and, through practice, master the entire process from theory to implementation.
Open-source, self-hosted AI app builder โ an agent builds real apps in isolated sandboxes on your own server, each live at a preview URL. Self-host in one command. MIT.
A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks.
Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.
Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.
Provides product-level IOCR custom template recognition, image-based search, facial recognition, and more. Free and commercially available, this is a one-stop Java AI solution designed to reduce workload and accelerate product development. Project categories include AI SDKs, web applications, and more.
MaiMai Savings Assistant โ a meal-ordering cost optimization skill based on McDonaldโs MCP. It calculates the cheapest way to order at your current location and proactively warns you about spending traps when adding items to reach a deal threshold.
DeepSeek Harness (dsh) In-Depth Guide from 0 to 1: Installation / Plugin Development / Performance Tuning / Real-World Case Studies / Empirical Comparison of Multiple Agents Using the Same Model (Chinese + English PDF)
A complete guide to start and improve your LLM skills in 2026 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!
๐ Efficient forwarding service for large language models. ยท An efficient forwarding service designed for LLMs. ยท OpenAI API Reverse Proxy
AI Agent Engineer Interview Resource Library - Interview Experiences, Job Requirements, and Frequently Asked Interview Questions from Major Chinese Tech Companies
Coordinate Claude, Codex, and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs, and independent review. Built-in skills recall lessons, simplify code, and forecast work. Track progress, decisions, and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together.
An open-source daily arXiv / OpenReview paper recommendation and AI reading platform, supporting automatic updates via GitHub Actions, GitHub Pages deployment, and paper Q&A.
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
The operational superset of Pi Coding Agent โ everything in Pi, plus observability, governance, recovery, evaluation, and multi-agent orchestration.
A production-oriented AI workflow runtime for rapidly developing, validating, and recovering complex AI workflows, and reliably delivering them as services.
AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI add-on and plugin, copilot for 3D, bpy Python scripting, MCP integration.
Open-source LLM gateway in Rust. One endpoint for OpenAI, Anthropic, Gemini, and every other vendor. Any SDK, any model, any tool.
Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.
Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU โ no API keys, no cloud, no data leaving your machine.
OpenEverest is an open-source platform for automated database, storage and LLM provisioning and management. It supports multiple technologies and can be hosted on any Kubernetes infrastructure, in the cloud or on-premises.
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
MCP server for reverse engineering tasks in Ghidra ๐ฉโ๐ป
Agent communication SDK. The open-source agent communication layer for AI agents โ email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices, and scores with probabilities, on your laptop's CPU.
[ICLR2024 Spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise, Supabase, ComfyUI, Qdrant & 30+ tools. Docker Compose, automatic HTTPS via Caddy, built-in monitoring. Free Zapier/Make alternative.
AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.
A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.
Open-source AI gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
A structured 3-agent AI dev team โ Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.