Directory

Explore the directory

Tools, libraries, services and references, each reviewed before it goes public. 6,821 resources listed.

6,821 listings

  • A Neovim plugin, formerly hfcc.nvim, that adds Copilot-style ghost-text code completion backed by the Hugging Face Inference API, Ollama, or another HTTP model endpoint.

  • A Telegram client for the OpenCode CLI that runs on the user's own machine, letting them run and monitor AI coding tasks, switch models and manage sessions from their phone.

  • Speech Swift

    soniqo.audio

    An open-source collection of on-device speech AI models for Apple Silicon, covering speech recognition, synthesis, speech-to-speech, voice activity detection, and speaker diarization.

  • Agentic SOC Platform

    asp.viperrtp.com

    An open-source, agent-centric security operations platform that lets AI agents triage alerts, investigate cases, and enrich threat intelligence alongside human analysts.

  • Jonex

    jonex.ai

    An enterprise AI knowledge platform that combines a multimodal document- and video-parsing engine with an ontology-driven knowledge graph, vector and graph indexing, and source-grounded retrieval.

  • SkillPack

    skillpack.sh

    An open-source way to package AI skills into runnable local agents that a team can deploy in their own environment and use from Slack and Telegram.

  • A curated, regularly updated reading list of papers and the author's own reading notes on multimodal large language models, large language models, and diffusion models.

  • A Python framework of post-training and training-time compression algorithms, such as quantization and pruning, for optimizing neural network inference in OpenVINO with minimal accuracy loss.

  • A Python library that detects likely hallucinations in large language model outputs using uncertainty quantification techniques, scoring each response's confidence between 0 and 1.

  • The official Go client library for the Claude API, providing access to Anthropic's language models from Go applications.

  • An independently authored collection of prompt templates for building AI coding agents, covering system prompts, tool prompts, agent delegation, memory management and multi-agent coordination.

  • RAGLite

    github.com

    A Python toolkit for retrieval-augmented generation that stores and searches documents in DuckDB or PostgreSQL, with configurable LLMs, rerankers, and hybrid keyword-and-vector search.

  • An independent, open-source terminal coding agent written in Rust, with an interactive agent shell, workspace-aware tools, session persistence, and a live split-pane TUI dashboard.

  • Example Model Context Protocol servers and clients in five languages, written as companion code for the official MCP server and client tutorials.

  • FyAgent

    github.com

    A local desktop app that centralizes an AI power-user's models, accounts, skills, MCP services and prompts across AI coding tools such as Claude Code, Codex and OpenCode.

  • LightAgent

    github.com

    An ultra-lightweight, open-source Python framework for building OpenAI-compatible agents, with tools, persistent memory, guardrails, tracing, multi-agent collaboration and workflows.

  • Sage

    zhangzhengeric.github.io

    An open-source multi-agent platform for coordinating project work, tool execution, and agent collaboration on the desktop, on the web, or embedded in a Python application.

  • mpmath

    mpmath.org

    A Python library for arbitrary-precision floating-point arithmetic, providing numerical methods, special functions and complex-number support.

  • A set of open-source Agent Skills that benchmark and optimize Xcode build performance across clean builds, incremental builds, compile hotspots, and Swift Package Manager overhead.

  • A vision toolkit and skill that gives a text-only coding agent, such as one running DeepSeek, image Q&A, long-screenshot OCR, frontend UI restoration and GUI automation.

  • Brian2

    briansimulator.org

    A Python simulator for spiking neural networks used in computational neuroscience, designed to be easy to learn, flexible and extensible.

  • MCPJungle

    docs.mcpjungle.com

    A self-hosted MCP gateway that lets teams register many MCP servers once and expose them behind a single endpoint with centralized discovery and access control.

  • Kubetorch

    run.house

    A Python framework for building, iterating on and deploying machine learning workloads on Kubernetes, bringing cluster compute into a local development workflow with fast iteration.

  • Agents Anywhere

    agents-anywhere.com

    An open-source, cross-device workbench for controlling AI coding agents such as Codex, Claude Code and DeepSeek Harness that are running on a work machine, from a desktop, phone, tablet or the web.