Directory
Explore the directory
Tools, libraries, services and references, each reviewed before it goes public. 6,821 resources listed.
SkyRL
docs.skyrl.aiA modular, full-stack reinforcement learning library for training large language model and vision-language model agents, combining a training framework, a Tinker API backend, an agent layer for long-horizon tasks, and a gymnasium of tool-use environments.
agents-best-practices
github.comA provider-neutral Agent Skill that helps design, generate an MVP blueprint for, audit, refactor and explain agentic coding and workflow harnesses, covering tool permissions, planning, context and memory, evals and production readiness.
Coding Interview Questions from Internet Companies
interview.doocs.orgA collection of frequently asked coding interview questions from major internet companies, together with study notes on programming books such as Clean Code and Effective Java.
Awesome Architecture
study8677.github.ioA bilingual, open-source knowledge base focused on system architecture rather than code: 26 tutorials, 25 architecture templates and 6 end-to-end case studies covering distributed systems, AI-native systems, retrieval-augmented generation and coding agents.
VexDB
vexdb.comA vector similarity search engine that plugs into PostgreSQL, DuckDB, and SQLite, sharing the same graph index algorithm, SIMD distance calculations, and quantization across all three backends.
ComfyUI LLM Party
github.comA set of ComfyUI nodes for building LLM-driven workflows visually: multi-tool agent calls, role-based assistants, local knowledge-base RAG and GraphRAG, multi-agent interaction patterns, chat-platform integrations, and speech and image generation nodes in one graph.
AiSOC
beenuar.github.ioAn open-source, self-hostable AI security operations center that ingests security telemetry, correlates alerts into incidents, investigates them with an auditable AI agent, and proposes a response for a human to approve, running with no API keys required.
mcp2cli
github.comA tool that turns any MCP server, OpenAPI specification, or GraphQL endpoint into a command-line interface at runtime, without generating any code.
Supacode
supacode.shA native macOS command center for running several coding agents in parallel, giving each task its own git worktree and real terminal, with sessions that persist in the background even if the app quits or an SSH connection drops.
PenguinHarness
penguin.oooAn open-source, local-first platform that automates building, evaluating, optimizing and deploying multi-agent AI applications, generating a runnable agent app from a single natural-language description and having agents evaluate and rewrite their own skills.
MFLUX
github.comA line-by-line MLX port of several state-of-the-art generative image and video models from the Hugging Face Diffusers and Transformers libraries, letting a Mac run models such as FLUX and Qwen-Image locally through native Apple Silicon acceleration.
ailia-models
github.comA collection of 419 pretrained AI models covering object detection, speech recognition, image generation, large language models and more, each runnable from the same simple command-line interface using the ailia SDK.
Olive
microsoft.github.ioAn AI model optimization toolkit for the ONNX Runtime that, given a model and target hardware, composes fine-tuning, conversion, quantization and other optimization techniques to produce the most efficient ONNX model for inference on CPUs, GPUs and NPUs.
Apify Agent Skills
skills.shA collection of Agent Skills giving an AI coding assistant expert use of the Apify web-scraping platform: selecting from more than 130 curated scraping Actors, building and deploying new Actors, wrapping existing code as an Actor, and generating an Actor's input/output schemas.
Token Monitor
javis-ai.comA local-first desktop widget that shows live token usage, account limits and session details across more than 40 AI coding tools, including Claude Code, Codex, Cursor and GitHub Copilot, with historical trends and multi-device sync.
Agent Skills Platform
francyjglisboa.github.ioA tool that turns an existing workflow, described in a prompt plus supporting evidence such as spreadsheets or transcripts, into a tested, installable agent skill with evals and security checks, then governs its lifecycle through a marketplace with rollback and quarantine.
Agentic Project Management (APM)
agentic-project-management.devAn open-source framework that coordinates a team of specialized AI agents, a Planner, a Manager and Workers, to manage a large software project through structured planning documents and reviewed task assignments instead of one long, degrading chat.
PenEcho
penecho.aiA shared canvas application for thinking with AI beyond a chat window, where a hand sketch, equation or note can be turned by a built-in agent or a connected MCP client such as Codex or Claude Code into a diagram, document or small interactive widget next to the original sketch.
SAG
zleap.comAn open-source knowledge base application, built on an original retrieval architecture called SAG, that turns uploaded documents into a searchable, source-traced knowledge graph and answers questions with citations back to the original text.
TorchLeet
torch-leet.vercel.appA collection of 68 PyTorch problems drawn from real machine learning and AI engineering interviews at companies such as Google, Meta and Anthropic, worked through in Jupyter notebooks with an optional MCP-based AI tutor that gives progressive hints without the answer.
Lanhu MCP Server
github.comAn MCP server for the Lanhu (蓝湖) design and requirements platform letting AI coding assistants read design handoff files and requirement documents directly, extract UI assets, translate a design into HTML/CSS reference code, and share notes across a team's AI tools.
Supabase CLI
supabase.comA command-line tool that brings the Supabase platform to a developer's terminal, running the full local stack, managing database migrations, deploying edge functions, and generating types.
Inference
inference.roboflow.comA self-hostable inference server that turns any computer or edge device into a command center for computer vision: running fine-tuned or foundation vision models, chaining them into workflows, and connecting cameras, video streams and external systems.
pi-skills
github.comA collection of skills for the pi coding agent, also compatible with Claude Code, Codex CLI, Amp and Droid, adding web search, browser automation, Google Calendar/Drive/Gmail tools, speech-to-text transcription, VS Code diff integration and YouTube transcript fetching.