LLM Inference

Raven is a self-improving agent harness built on EverOS that enables LLM-based agents to refine tools, skills, memory, and policies across multiple...

OpenScience is an AI-powered workbench for scientific research that automates the full research loop—literature review, hypothesis formation, code...

A self-hosted quantitative trading workbench for Chinese A-stock analysis, combining stock screening, monitoring, and backtesting with LLM-powered...

Meetily is a privacy-first AI meeting assistant that runs entirely locally on macOS and Windows, providing real-time transcription via...

OpenBiliClaw is a local-first, privacy-focused AI agent that learns user preferences through cross-platform activity and feedback, then proactively...

AI Berkshire is a specialized investment research framework that applies value investing methodologies from Warren Buffett, Charlie Munger, Duan...

Loop Engineering provides practical patterns, CLI tools, and starter templates for designing AI agent orchestration systems that separate prompt...

OpenKnowledge is a WYSIWYG markdown editor with AI-native features (Claude, Codex integration), available as a macOS app and web UI, designed for...

OpenSERP is a self-hosted SERP API and CLI that aggregates search results from Google, Bing, Yandex, Baidu, DuckDuckGo, and Ecosia with browser...

Zero is a terminal-based AI coding agent written in Go that lets developers use their choice of LLM models (OpenAI, Anthropic, Gemini, Ollama, etc.)...

TencentDB Agent Memory is a TypeScript library that provides local long-term memory for AI agents through a 4-tier progressive pipeline with symbolic...

Dao Code is an open-source terminal-based AI coding agent optimized for DeepSeek V4, designed to read code, write code, run commands, and fix bugs...

Gini Agent is a personal AI agent platform designed to maintain memory, learn from interactions, and operate autonomously across multiple interfaces...

QuantMind is an AI-powered knowledge extraction and retrieval framework that transforms unstructured financial research (papers, news, reports, SEC...

Commonly is an open-source workspace platform that enables agents (Claude Code, Cursor, Codex, OpenAI, and custom implementations) and humans to...

ODS is a self-hosted AI server platform that bundles Ollama, Open WebUI, n8n, ComfyUI, and related tools into a single installation for running LLM...

A curated collection of extracted system prompts from major AI assistants including Claude, ChatGPT, Gemini, Grok, Copilot, and others, updated...

Paper Notes is a curated repository of 23,000+ concise summaries (5-minute reads) of AI, LLM, NLP, and CV papers from top-tier conferences including...

Agency Orchestrator is a multi-agent AI orchestration platform that automates task decomposition and role assignment across 216+ pre-built AI expert...

Omnigent is an open-source orchestration layer and meta-harness for managing multiple AI agents (Claude Code, Codex, Cursor, and custom agents) with...

Council of High Intelligence is a multi-agent AI deliberation system that routes questions across 18 distinct AI personas spanning multiple LLM...

OpenMed is a local-first healthcare AI platform that performs clinical named entity recognition and HIPAA-compliant PII de-identification entirely...

A comprehensive trilingual learning roadmap and curated resource collection for AI agents, spanning from LLM fundamentals to multi-agent systems. It...

A comprehensive, systems-level Chinese-language tutorial for learning AI agents and large language model application development, structured from...

9Router is an AI gateway and token optimization service that routes requests from coding tools (Claude Code, Cursor, Cline, Copilot) to 40+ AI...

Ponytail is a prompt-engineering skill/plugin for AI coding agents (Claude Code, Cursor, and ~18 others) that instructs them to apply YAGNI and...

Unity MCP is a bridge between AI assistants (Claude, Copilot, local LLMs) and the Unity Editor via Model Context Protocol, enabling developers to...

A curated, auto-generated list of free LLM inference APIs and providers (OpenRouter, Google AI Studio, Groq, HuggingFace, etc.) with their rate...

This is a learning project that reconstructs Claude Code's core architecture in ~5000 lines of TypeScript/Python, designed to teach developers how AI...

Agent Teams AI is a desktop application that orchestrates multiple AI agents to collaborate on tasks through a kanban-style interface, supporting...