Explore the directory

A library that defines one universal file format for vector datasets, so data can be exported from one vector database, re-embedded with a different model, and imported into another, without writing custom conversion code for each pair.

• RAG
• Databases

A native macOS application for fine-tuning large language models on Apple Silicon, letting a user pick a model and a training algorithm and watch the training loss fall entirely on-device, with no cloud step required.

• Models

A single markdown knowledge source covering HarmonyOS NEXT app development in ArkTS and ArkUI that automatically generates configuration files for more than eleven AI coding tools, so a general-purpose model stops answering HarmonyOS questions with React or Android conventions.

• Agent skills
• Mobile

A tool that mines a developer's own past messages to their coding agents into a personal profile of working rules, each backed by a dated quote from an actual session, then installs that profile where the agent can read it.

• Agent skills

A dependency analyzer that builds a temporal knowledge graph of a codebase and scores each file's blast radius, how many other files would break if it changed, so an AI coding assistant can judge the risk of an edit before making it.

• Agent memory
• Code quality

A curated, weekly-audited list of tools, frameworks and practices for building retrieval-augmented-generation systems at production scale, with reference architectures, real case studies and source-tagged benchmark numbers.

• RAG
• Curated lists

A beginner-friendly tutorial that teaches the Jujutsu version control system from scratch, without assuming any prior experience with Git or other version control tools.

• Git
• Tutorials

A set of Chinese-language notes that rebuild the internal mechanisms of coding agents such as Claude Code, Codex and OpenCode as small, dependency-free, runnable Node.js programs, one mechanism per chapter.

• Tutorials

An extension suite of 43 extensions and skills that turns the Pi terminal coding agent into a multi-agent orchestration platform, adding operational modes for planning, specification and team or pipeline execution.

• Agent skills

An open knowledge base cataloging cybercriminal concealment tactics, techniques, and procedures, built from over 200 clear- and dark-web OpSec guides using a MITRE ATT&CK-style structure.

• Security

A curated Chinese-language guide to DeepSeek Harness (dsh), an open-source, plugin-based AI agent harness, covering quick start, official resources, community plugins, and developer tools.

• Coding agents
• Curated lists

A collection of 50 complete Next.js SaaS application templates for generative-AI products, each with Stripe billing, Google sign-in and a model-routing layer already wired up, meant to be relaunched under a new brand.

• Generative media
• Web frameworks

A bounded, local long-term memory system for the Hermes, Codex and Claude Code agents, backed by SQLite as the authority with rebuildable vector search alongside it, letting a user inspect, correct or delete anything it remembers.

• Agent memory

A short block of text pasted into a coding agent's configuration file that names four shapes of unnecessary defensive behavior, hashing, edge-case handling, rubric-chasing and overbuilding, so a developer can call out which one just happened instead of arguing about vibes.

• Agent skills

A fork of vLLM focused on running recent frontier models on older NVIDIA GPUs such as the A6000, 3090, and A100, distributed as prebuilt Docker images.

• Inference

A native Swift and Metal backend plugin for vLLM on Apple Silicon that replaces the Python inference hot path, serving an OpenAI-compatible API with faster short-context decoding than the existing Python and MLX engine.

• Inference

A governed execution layer that sits around coding agents such as Claude Code and Codex, turning a plain request into a clarified goal, splitting work across capabilities, reviewing the result, verifying evidence, and writing back lessons for the next run.

• Coding agents

A curated list of research papers on using multimodal large language models to generate code from non-text inputs, covering web and mobile UI screenshots, scientific plots, slides, SVG logos, CAD, posters and games.

• Curated lists
• Papers

A fine-tuning skill for Claude Code, Gemini CLI and other agent hosts that runs the whole LoRA fine-tuning lifecycle from a plain-language request: environment setup, data formatting, training, evaluation and export.

• Agent skills
• Models

A local-first governance layer for AI-agent skills that adds a multi-agent collaboration panel, a routing system that only suggests which skill fits a request, and a schema for controlling how skills are promoted, without granting permissions or executing anything itself.

• Agent skills

An extension suite for the Pi coding agent that adds a structured engineering loop of clarifying a goal, driving verified execution, reviewing changes and searching code, implemented as plain, inspectable TypeScript and Markdown.

• Agent skills

A self-hosted, single-binary observability backend for local AI coding assistants that tracks token usage, cost, latency and error rates across tools such as Claude Code, Gemini CLI and OpenAI Codex CLI in one dashboard.

• AI evals
• Monitoring

A bilingual Chinese and English edition of the book Agentic Design Patterns, keeping the original English text alongside added Chinese annotations, with high-resolution figures extracted from the source PDF.

• Books

A local-LLM runner that auto-tunes launch flags to the user's GPU, serves models behind a web UI and an OpenAI or Anthropic-compatible API, and can run any llama.cpp-compatible engine, including community forks, instead of one fixed build.

• Inference