Directory

Explore the directory

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

6,821 listings

  • An Agentic GraphRAG framework that separates the AI decision layer from the graph database, running the same ingestion, retrieval and evaluation pipeline across Neo4j, Memgraph, Apache AGE and Kuzu.

  • Video2GUI

    weiminxiong.github.io

    Research code and the WildGUI dataset for a pipeline that extracts grounded GUI interaction trajectories from unlabeled internet videos to pretrain generalized graphical interface agents.

  • unsorry

    unsorry.agentics.org.nz

    A distributed swarm of autonomous AI agents that turn open Lean 4 proof obligations into kernel-verified proofs, using the git repository as a work queue and continuous integration as the verification gate.

  • TogoLM

    togolm.com

    An open infrastructure layer for Togolese public data: a scraped corpus of laws, government records and press, a retrieval-augmented generation engine, and a REST API with JS/TS and Python client SDKs.

  • SWARM

    swarm-ai.org

    A research framework for measuring emergent safety failures that appear only when many AI agents interact, even when each individual agent behaves safely on its own.

  • SnapLLM

    github.com

    A local multi-model inference engine, built on llama.cpp and stable-diffusion.cpp, that keeps several models resident in memory at once and switches between them without reloading weights.

  • Search Mode V4

    github.com

    A reality-anchored prompt framework for GPT and Gemini that switches between an offline mode and an online, search-verified mode based on a fixed date threshold, with a shared output structure across both platforms.

  • RMS Memory MCP

    rms-ds.com

    A persistent, local, cross-IDE memory server for AI coding agents that keeps a Markdown vault outside the repository, searchable by hybrid vector and full-text search, so a project's context survives switching between editors.

  • OTAIP

    telivity.app

    An open-source platform that models the full airline and hotel booking lifecycle, search through settlement, as typed, testable AI agents whose pipeline contracts are meant to prevent hallucinated bookings.

  • OpenClix

    openclix.ai

    An open-source, local-first foundation for mobile app onboarding, habit and re-engagement messaging, delivered as vendored source templates plus AI-agent skills instead of a hosted SDK.

  • MemVanta

    sauravsingla.github.io

    A memory-first C++20 inference runtime for quantized GGUF language models on CPU, trading throughput for a large cut in peak memory use compared with llama.cpp.

  • ContextStream MCP Server

    contextstream.io

    A hosted MCP server that gives an AI coding agent persistent memory and millisecond code search over a project's code, docs and past conversations, with cited sources and scoped access.

  • A Model Context Protocol server that lets an AI assistant drive browser and mobile automation through WebdriverIO, controlling Chrome, Firefox, Safari, Electron, iOS and Android through one interface.

  • logana

    pauloremoli.github.io

    A terminal log analyzer that turns files, compressed archives, Docker containers or OpenTelemetry streams into structured, filterable, annotatable data, with an MCP server for exporting findings to an AI assistant.

  • The lab materials for a university course on large language models for software engineering, covering transformer foundations and their application to prompt engineering, RAG and code-review tasks.

  • Horizun Revit MCP

    horizunhub.com

    A free, open-source Windows MCP server and Revit add-in that lets an AI client model, document, coordinate and export Autodesk Revit projects through natural-language requests across more than 100 tools.

  • gptpmt

    gptpmt.com

    A prompt engineering best-practices guidebook written for a general audience rather than as a technical reference, published as a free website in Chinese and English.

  • Dense-Mem

    markhuang.ai

    A self-hosted MCP memory server that stages exact evidence, derives semantic state through server-side policy rather than trusting a model's output directly, and returns recall only when its supporting evidence is eligible.

  • A local-first application for curating, tagging, downloading and managing datasets and models, with built-in AI assistants for tag editing, code and dataset-pipeline work, plus 3D generation and media metadata handling.

  • Awesome DeepSeek Harness

    deepseekserver.com

    A community-maintained, weekly-refreshed directory of plugins, skills, workflows, agents and tools for DeepSeek AI's open-source agent harness, DeepSeek Harness.

  • AntNest

    github.com

    A desktop AI agent that runs entirely on the user's own machine, splitting a task between a queen process that only plans and decides and disposable worker processes that execute commands in an isolated temporary directory.

  • Amiga DevBench

    github.com

    A cross-development environment that connects a modern host machine to an emulated or real Commodore Amiga over serial, for live debugging, memory inspection and full MCP integration with Claude Code.

  • AI-History

    github.com

    A 66-chapter narrative walk through ninety years of AI history, from Turing in 1936 to Blackwell in 2025, written for readers with no technical background as much as for engineers.

  • COSMOS

    github.com

    An open-source semantic search engine for retrieving information from PDF documents, built from ingestion of text, tables and figures, ElasticSearch-based retrieval with an optional neural reranker, and a question-answering model for extracting answers from the retrieved spans.