Explore the directory

A command-line installer that adds security-review skills and slash commands to AI coding assistants such as Claude, Cursor and Copilot, covering the OWASP Top 10 and CWE Top 25 categories.

• Agent skills
• Security

An open-source agent lifecycle management platform that turns a raw language model into a self-governing agent maintaining a consistent persona, with lifecycle commands for creating, training and evaluating agents.

• Agent frameworks

A Chinese-language book on prompt engineering, covering prompt structure, chain-of-thought and multimodal prompting through to enterprise PromptOps, agent workflows and retrieval-augmented generation.

• Books

A plain-Markdown persistent memory system for the pi coding agent, giving it long-term facts, daily logs, a scratchpad and semantic search across sessions.

• Agent memory

An open, AI-reviewed marketplace where researchers share the plotting scripts behind their published figures, so others can find a template, its rendered output and its source paper side by side.

• Papers

A library of 56 skills for the OpenClaw self-modifying AI agent runtime, adding structured planning, security guardrails, cron-scheduled maintenance, crash recovery and the ability to write its own new skills.

• Agent skills

A curated, actively maintained list of open-weight AI models selected for commercially exploitable licenses, no geographic restrictions, and verified benchmarks, organized by category and VRAM tier.

• Models
• Curated lists

A command-line tool that inspects live LLM inference processes and breaks down GPU memory use into weights, KV cache, workspace and activations, then projects how much memory different quantization strategies would save.

• Inference
• Debugging

A Claude Code plugin that discovers a codebase's actual conventions and encodes them as rules, skills, sub-agents and enforcement hooks, so generated code follows those conventions from the first attempt.

• Agent skills

An open-source, self-hostable knowledge base with rich-text editing, hybrid search and GraphRAG that exposes the same documents to people and to AI agents over MCP, REST, an SDK or a CLI.

• RAG
• Documentation tools

A cross-platform persistent memory MCP server for Codex, Gemini CLI, Claude Code and other local MCP hosts, storing decisions and project context locally in SQLite or PostgreSQL with hybrid retrieval and decay-based consolidation.

• MCP servers
• Agent memory

An MCP server that indexes a codebase into an AST knowledge graph across ten languages via Tree-sitter, giving AI coding assistants semantic search, call-graph traversal, HTTP route tracing and change-impact analysis.

• MCP servers
• Agent memory

A self-hosted chat application for local and self-hosted language models, positioned as a simpler alternative to Open WebUI, with bundled speech and web-search services so it needs no cloud provider API keys to get started.

• Inference

A Java library that adds code completion, parsing and error-underlining for languages such as Java, JavaScript, C, CSS and HTML to the RSyntaxTextArea text-editing component.

• Editors
• Libraries

A pure Go, cgo-free wrapper around stable-diffusion.cpp that runs Stable Diffusion text-to-image and image-to-image generation cross-platform.

• Generative media

A Neovim plugin that drives Cursor's own next-edit prediction backend, giving Neovim the same ghost-text suggestions and cursor jumps as the Cursor editor, using an existing Cursor login.

• Coding agents
• Editors

An MCP server that exposes Appwrite's backend API, databases, users, functions, teams and storage, as tools an MCP client can call.

• MCP servers
• Backend

A native macOS app, CLI and always-on API for running local LLMs on Apple Silicon through MLX, with the inference engine itself implemented in Swift rather than wrapping a Python core.

• Inference

A local macOS control server that exposes shell access, files, browser automation and UI control to MCP clients and Custom GPT Actions, with agent teams, memory and a local operations dashboard.

• MCP servers

A unified, sandboxable execution environment that runs Python code, shell commands and programmatic MCP tool calls together in a stateful IPython kernel.

• Containers

An inference engine for distributed LLM serving that supports dense, mixture-of-experts, multimodal and hybrid-attention models with continuous batching, paged attention and multiple forms of parallelism.

• Inference

A Visual Studio extension that adds a native chat interface and embedded terminal for Claude Code, Codex, Cursor Agent and other AI coding agents, with image and file attachments and an integrated diff viewer.

• Coding agents
• Editors

A hands-on workshop of labs that build semantic search, recommendations, retrieval-augmented generation and agentic incident remediation using pgvector, Aurora PostgreSQL and Amazon Bedrock.

• RAG
• Tutorials

A monorepo TypeScript framework for building tool-driven AI agents, providing LLM abstractions, multiple agent paradigms, a skill system, built-in memory and RAG, and inter-agent communication protocols.

• Agent frameworks