Explore the directory

A command-line tool that fetches Learn X in Y Minutes programming tutorials and browses them in the terminal, with an offline cache and fuzzy search.

• CLI tools
• Tutorials

An AWS sample multi-agent chat platform, built on Amazon Bedrock AgentCore and serverless TypeScript services, letting a team create, customize and share AI agents, with preset agents, event-driven triggers and extensible tools.

• Agent frameworks

A minimalist, workflow-first multi-agent coding harness in a single native Go binary that keeps the plan, active work, tool activity, tests and delegated subagent tasks visible in one terminal, running against Anthropic, OpenAI, Google Gemini or OpenRouter models.

• Coding agents

A cross-session memory plugin for DeepSeek Harness that automatically deduplicates and merges memories in the background, freezes contradictions for the user to decide, and stores memory as local, human-editable Markdown files, no API key needed.

• Agent memory

A kernel-enforced sandbox for AI coding agents that wraps tools such as GitHub Copilot CLI, Claude Code or Gemini CLI so the agent can write code but is blocked from reading SSH keys, pushing to the default branch or exfiltrating secrets.

• Security
• Containers

A CLI and public leaderboard that reads local session files 41 AI coding clients already write to disk, totals token usage locally, and uploads only aggregate counts and timestamps, never prompts or file contents, with an iOS companion app.

• Monitoring

Python bindings for the stable-diffusion.cpp C library, giving low-level ctypes access and a high-level Python API for Stable Diffusion, FLUX and Wan image and video generation, with pip-installable hardware acceleration for CUDA, ROCm and other backends.

• Generative media
• Libraries

A command-line, semantic code-bookmarking tool that anchors a bookmark to a named structure such as a function using tree-sitter instead of a file-and-line reference, so it still points at the right place after a refactor, with a skill for agents.

• Agent skills
• CLI tools

A set of seven standalone Claude Code hooks, plus an enforce-hooks component, that block dangerous shell commands and other tool calls Claude Code's own permission system can miss, backed by over 1,900 tests and a corpus of known permission gaps.

• Agent skills
• Security

A Chinese self-study path for LLMs that hand-implements a transformer in native PyTorch and runs pretraining, SFT, LoRA, DPO and GRPO on a single consumer GPU, then covers an industrial fine-tuning framework, agent engineering and a RAG system.

• Tutorials

An open-source safety layer for autonomous AI agents that groups background activity by originating request, surfaces scope drift and failed verification for review, lets a user set per-tool allow, ask or block policy, and creates recovery points.

• AI evals

A research framework that treats speculative decoding as an online learning problem, continuously updating the draft model from feedback produced during verification to keep speedups high as a workload shifts.

• Inference

A self-hosted, privacy-first LLM proxy and AI gateway sitting between applications and providers such as OpenAI, Anthropic or Ollama, adding access control, virtual API keys, usage tracking and load balancing, while never storing prompt content.

• LLM gateways

A monorepo of Unraid server tooling: Python and Rust MCP servers exposing an Unraid box's GraphQL API for system info, Docker, VMs and notifications, plus OS plugins and Claude/Codex agent integrations that install them in one command.

• MCP servers

A Terraform module that deploys a generative-AI retrieval-augmented-generation solution on Google Cloud, provisioning a choice of Cloud SQL MySQL, Cloud SQL PostgreSQL, AlloyDB or Cloud Spanner as the database and prebuilt frontend and retrieval service containers.

• RAG
• Hosting

A Model Context Protocol server that lets an AI assistant query Socket's dependency security scores to check a package, audit a package.json or identify risky dependencies across npm, PyPI, Cargo and other ecosystems, hosted or self-run locally.

• MCP servers
• Security

A living, auto-curated, machine-readable catalog of over 37,000 open-source projects with practical summaries, categories and transparent quality scoring, meant to give coding agents grounded starting points before a deeper technical, security and license review.

• Curated lists

A production-ready Python and FastAPI retrieval-augmented-generation framework that swaps vector databases, language models, rerankers and caches with a one-line configuration change, running as a full Docker API server or as an offline local CLI chatbot with no API key required.

• RAG

An open-source Python cost controller for AI agent loops that measures real-time convergence and stops or rolls back a loop once it has converged, instead of a fixed iteration cap, with adapters for LangGraph, CrewAI, AutoGen and Claude Agent SDK.

• Agent frameworks

A Chinese-language collection of practical notes, benchmark tables and released training code for building domain-specific large language models, covering small reasoning models, SFT and DPO data pipelines, and multi-round SFT-then-DPO training on large GPU clusters.

• Tutorials

A local-first tool that backs up and restores the memory, history and configuration Claude Code, Codex, Cursor and Gemini write on a machine, then consolidates the durable, transcript-linked lessons into shared project memory reviewed before use.

• Agent memory

The official SDK for SAP AI Core, SAP Generative AI Hub and the Orchestration Service, published as a set of TypeScript and JavaScript packages covering chat completion, foundation models, LangChain clients, orchestration, document grounding and prompt registry.

• Agent frameworks

A framework for training custom wake-word detection models, offering a range of neural network architectures suited to different devices from a Raspberry Pi Zero to a cloud server.

• Speech

A set of Jupyter notebook tutorials for PyPOTS, a Python toolbox for modeling partially observed, incomplete time series data.

• Data engineering
• Tutorials