ai-supply

Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.

High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.

Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.

ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.

Official GitHub MCP server — give your AI agent full read/write access to repos, issues, PRs, and actions.

Hugging Face's state-of-the-art library for diffusion-based image, video, and audio generation models.

The Natural Language Toolkit — Python's foundational NLP library for tokenization, POS tagging, parsing, and corpora.

Official TypeScript/JavaScript SDK for building MCP servers and clients — the Node.js foundation for the Model Context Protocol.

Fast and flexible image augmentation library with 70+ transforms for computer vision model training.

End-to-end ML lifecycle platform — experiment tracking, model registry, serving, and LLM evaluation.

In-process OLAP SQL database that runs inside your Python, R, or Node.js process — no server required.

Fast, memory-mapped dataset library for NLP and ML — 50,000+ datasets, streaming, and Arrow-backed processing.

Conversational AI coding agent that builds entire codebases from natural-language specs with one prompt.

Ultra-fast tokenizer library (Rust core) — BPE, WordPiece, SentencePiece — tokenize GBs in seconds.

Industrial-strength NLP library for Python with pre-trained pipelines for tokenization, NER, parsing, and more.

Low-code visual builder for LLM-powered agents and multi-step AI workflows with 100+ pre-built components.

Distributed Python framework for scaling ML workloads — training, serving, hyperparameter tuning, and pipelines.

Drop a screenshot or Figma design and get clean HTML/Tailwind/React/Vue code generated by GPT-4o or Claude.

Open-source AI software engineering agent that writes, edits, runs, and tests code autonomously in a sandboxed environment.

Apache-2.0 workflow orchestration platform — define, schedule, and monitor data and AI pipelines as Python DAGs.

The world's most popular computer vision library with Python bindings — image processing, video, and ML pipelines.

Run PyTorch training scripts on any hardware — single GPU, multi-GPU, TPU — with minimal code changes.

High-performance, model-agnostic Python framework for building, running, and managing production AI agents at scale.

Open-source durable execution platform for building reliable distributed workflows and long-running processes.

Princeton's autonomous agent that resolves real GitHub issues end-to-end using a custom agent-computer interface.

Industrial-grade multilingual OCR toolkit supporting 80+ languages with text detection, recognition, and layout analysis.

OpenAI's lightweight Python framework for building multi-agent systems with handoffs, tracing, and guardrails.

Blazing-fast DataFrame library written in Rust with a Python API — handles datasets that don't fit in RAM.

Open-source vector similarity search for PostgreSQL — store and query embeddings directly in your Postgres DB.

Asset-oriented data orchestration platform for building, testing, and monitoring data pipelines in production.

The most popular open-source Yahoo Finance connector — historical prices, fundamentals, options chains, and real-time quotes as pandas DataFrames.

Pioneering autonomous task-management AI that uses GPT-4 and vector memory to self-generate and prioritize tasks.

Run large language models locally with a single command. OpenAI-compatible API for Llama, Mistral, Gemma, and more.

Python wrapper for TA-Lib: 150+ technical indicators (MACD, RSI, Bollinger, candlestick patterns) in C speed.

Open-source agentic software engineer that understands high-level instructions, plans steps, and writes full code solutions.

Google's on-device ML framework for face, hand, pose, and object detection across mobile, desktop, web, and edge.

MIT-licensed rule-based sentiment analysis tool tuned for social media, brand monitoring, and ad copy: compound scores with no model training required.

ProjectDiscovery's fast, template-driven vulnerability scanner with 9,000+ community templates for web apps, APIs, cloud, and AI service endpoints.

Aqua Security's comprehensive vulnerability scanner for containers, filesystems, Git repos, IaC, and SBOMs — now with AI/ML workload scanning.

Microsoft Research's system connecting LLMs to 1000+ Hugging Face models for multi-modal task planning and execution.

One-line OCR for 80+ languages including Latin, Chinese, Arabic, Devanagari, and Cyrillic — no training required.

The largest open prompt collection — thousands of curated system prompts for personas, coding, writing, education, and creative tasks. CC0 licensed.

Cloud-native open-source vector database built for billion-scale similarity search and AI applications.

The leading framework for building LLM-powered applications and agents with chains, tools, memory, and retrieval.

Farama Foundation's MIT-licensed reinforcement learning toolkit — the standard interface for RL environments including Atari, MuJoCo, CartPole, and 100+ more.

Fast LLM serving framework with RadixAttention KV cache reuse and structured output (JSON/regex) natively.

AI pair programming tool in your terminal — chat with LLMs to edit code across your entire git repository.

Whisper with fast forced alignment, accurate word-level timestamps, and multi-speaker diarization.

Modular topic modeling framework using transformer embeddings and c-TF-IDF for interpretable, coherent topics.

Secure cloud sandboxes for running AI-generated code — spin up a Python/JS interpreter in 150ms from your agent.

Build, ship, and scale AI services — unified framework from local development to production Kubernetes.

Official reference MCP servers: filesystem, git, fetch, memory, and more — the fastest way to give agents real-world tool access.

NVIDIA's modular framework for training, fine-tuning, and deploying speech recognition, TTS, and large language models at scale.

Open-source vector database with hybrid search, multi-tenancy, and native ML module integrations.

Unified API gateway for 100+ LLM providers — call OpenAI, Anthropic, Gemini, Cohere, and local models with a single consistent interface.

Production LLM serving platform by BentoML — deploy any open-source LLM with one command.

CLI scaffolder for full-stack LlamaIndex RAG and agentic apps — Next.js, FastAPI, or Express in one command.

Roboflow's reusable computer vision utilities for annotation, tracking, and visualising detection model outputs.

Combines Grounding DINO and Segment Anything for text-prompt-driven object detection and precise segmentation in one pipeline.

Microsoft's autonomous R&D agent for iterative hypothesis generation, experimentation, and quantitative research automation.

MIT-licensed comprehensive guide and prompt library — techniques, examples, and templates for every major LLM prompting method.

Project MONAI's Apache-2.0 PyTorch framework for medical image segmentation, classification, and registration — the standard for AI radiology research.

MIT-licensed Python NLP library with sentiment polarity/subjectivity scoring, spell correction, noun phrase extraction, and translation for copywriters.

DLR's MIT-licensed PyTorch implementations of PPO, SAC, TD3, DQN, A2C, and HER — battle-tested RL algorithms for game AI and simulation.

Open-source AI code assistant VS Code and JetBrains extension — autocomplete, chat, and edit with any LLM.

Data quality framework for defining, testing, and documenting expectations about your data pipelines.

Cross-browser automation library for agents: control Chromium, Firefox, and WebKit with a single reliable API.

OpenMMLab's comprehensive object detection toolbox with 40+ architectures and 300+ pretrained models.

First multi-agent framework based on role-playing LLM societies; supports 20+ agent types, tool use, RAG, and multi-modal tasks.

Microsoft's open-source PII detection and anonymization engine supporting 50+ entity types across text, images, and structured data.

Scripting language that lets LLMs interact with any system via natural language — run shell commands, call APIs, and chain tools.

MIT-licensed security toolkit by ProtectAI that sanitizes LLM prompts and responses — blocking prompt injection, toxic content, PII leakage, and secrets.

Simple NLP library with SOTA models for NER, POS tagging, chunking, text classification, and contextual string embeddings.

Microsoft's open-source toolkit for building, evaluating, and deploying high-quality LLM applications end-to-end.

Hugging Face's minimalist library for building agents that write and execute Python code as their primary action.

Apache-licensed multi-cloud security assessment tool covering 500+ checks across AWS, Azure, GCP, and Kubernetes, including AI service misconfigurations.

Connect AI agents to the web: Browser Use lets LLMs browse, interact, and extract from any website autonomously.

Open-source Python library for building self-maintaining, schema-evolving data pipelines with minimal code.

Apache-2.0 autonomous coding agent VS Code extension — plans, writes, runs, and debugs code end-to-end in your editor.

The leading data framework for LLM apps — 150+ data loaders, RAG pipelines, and agent tools for connecting any data source to any model.

Minimal keyword and keyphrase extraction using BERT embeddings — finds the most representative terms in any content for SEO and content strategy.

Apache-2.0 toolkit for training intelligent game agents using deep RL and imitation learning directly inside Unity game environments.

Microsoft's universal document-to-Markdown converter: PDF, DOCX, PPTX, XLSX, HTML, images, audio, and ZIP — all to clean Markdown.

Differentiable computer vision library built on PyTorch: geometry, augmentation, colour, filtering, feature extraction, and more.

Python library for portfolio performance analytics: Sharpe/Sortino/Calmar ratios, drawdown reports, tearsheets.

Farama Foundation's MIT-licensed multi-agent RL environment library — 50+ cooperative and competitive games for training and evaluating MARL algorithms.

Meta FAIR's PyTorch library for deep learning with 3D meshes, point clouds, and volumetric data.

Microsoft's open-source quant research and trading platform with ML/RL model support, factor mining, portfolio optimization, and backtesting.

Open-source ML and LLM observability framework for evaluating, monitoring, and testing AI system quality.

AI data lake with multimodal tensor storage, vector search, and serverless SQL — stream datasets directly to PyTorch and TensorFlow.

The open-source AI-native vector database — store, query, and filter embeddings with a simple Python API. Perfect for RAG and semantic search.

EleutherAI's MIT-licensed unified benchmark suite — the de-facto standard for evaluating language models across 200+ tasks.

Role-based multi-agent orchestration framework — define a crew of AI agents with distinct roles, tools, and goals that collaborate autonomously.

Platform for building stateful AI agents with advanced memory that can learn and self-improve over time.

DeepMind's Apache-2.0 framework for game theory and RL research: 70+ games (Chess, Go, Poker, Hex), CFR, MCTS, deep RL, and Nash equilibrium solvers.

Build stateful, multi-actor agent workflows as directed graphs — cycles, branching, human-in-the-loop, and persistent state built in.

TypeScript toolkit for building AI-powered apps and agents: streaming UI, structured outputs, tool calls, multi-step agents.

MIT-licensed 4.2M instruction dataset — GPT-4/3.5 augmented CoT traces that power top open-source fine-tunes.

NVIDIA's open-source toolkit for adding programmable safety, topical, and quality guardrails to LLM-based conversational systems.

Self-hosted, open-source ML training metadata tracker with a powerful exploratory web UI.

Python tool to scrape, extract, and clean main text from web pages, with CSV/JSON/Markdown/XML output.

Modular Python framework for building AI agents with chain-of-thought reasoning, tool use, memory, and structured workflows.

Modern open-source data pipeline builder with an interactive code editor, real-time execution, and built-in ML integrations.

Microsoft's multi-agent conversation framework — build teams of LLM agents that converse, code, debate, and solve complex tasks together.

Autonomous AI research agent that searches the web and produces detailed, cited research reports in minutes.

Serverless, embedded vector database built on Lance columnar format — zero-copy, multimodal, no server needed.

Stanford's framework for programming — not prompting — LLMs: compile, optimize, and auto-tune modular AI systems.

High-performance vector database with filtering, payload storage, and a REST/gRPC API — built for production AI.

MIT-licensed Python library computing 12 readability scores (Flesch, Gunning Fog, SMOG, Dale-Chall, etc.) for content optimization and SEO.

Goldman Sachs's open-source Python library for derivatives pricing, risk analytics, and systematic trading.

Fast and accurate physics engine for robotics, biomechanics, and RL research, now open-sourced by DeepMind.

Production-ready NLP pipeline framework for building search, RAG, and question-answering systems with any LLM.

Declarative YAML-based orchestration platform with 1500+ plugins for automating data, AI, and infrastructure workflows.

Allen AI's Apache-2.0 spaCy models for biomedical text with UMLS, MeSH, GO, HPO, and RxNorm entity linking and NER for genes, diseases, chemicals, and proteins.

MIT-licensed deep learning framework for drug discovery and computational biology — molecular property prediction, virtual screening, and ADMET modelling.

MIT-licensed framework for evaluating LLMs and AI systems — build custom evals, run model comparisons, log results.

DKFZ's Apache-2.0 framework that automatically configures a U-Net for any medical image segmentation dataset — state-of-the-art results with zero manual tuning.

Intelligent memory layer for AI agents — automatically extracts, stores, and retrieves relevant context across sessions.

Farama Foundation's Apache-2.0 fast gridworld RL environments for goal-conditioned, partially observable, and language-conditioned agent research.

Official MIT-licensed Python SDK for the Model Context Protocol — build MCP servers and clients with full spec compliance.

Microsoft's open-source SDK for building AI agents and skills in C#, Python, and Java — composable, enterprise-ready, and model-agnostic.

Kubernetes-native ML and data workflow orchestrator with first-class type safety, reproducibility, and multi-cloud support.

Stanford's LLM-powered knowledge curation agent that researches any topic and generates a full Wikipedia-style article.

AI4Finance Foundation's framework for training RL agents to trade stocks, crypto, and forex with backtesting, paper trading, and live execution support.

Microsoft's graph-based RAG: build knowledge graphs from documents for global, multi-hop reasoning beyond vector search.

Apache-2.0 LLM testing framework — pytest-style unit tests for RAG pipelines, chatbots, and LLM outputs.

HuggingFace's few-shot text classification framework — match Legal-BERT accuracy with as few as 8 labeled contract examples, no prompt engineering.

MIT-licensed spaCy extension for clinical text processing — section detection, clinical concept extraction, negation, temporality, and UMLS entity linking.

Modern workflow orchestration — turn any Python function into a scheduled, observable, retriable data or AI pipeline with zero boilerplate.

Framework-agnostic MLOps framework — build portable, production-ready ML pipelines that run anywhere.

LLM-powered multiagent persona simulation for synthetic UX research, focus groups, and business scenario testing.

Real-time physics simulation for robotics and game AI using the Bullet physics engine with Python bindings.

All-in-one conversational AI toolkit for ASR, speaker recognition, speech enhancement, and language identification.

OpenAI's MIT-licensed suite of 16 procedurally-generated 2D game environments for measuring generalization in reinforcement learning agents.

CC-BY-SA-3.0 instruction dataset of 15k human-written prompts — the first commercially licensed open instruction dataset.

Python library for audio and music analysis: spectrograms, MFCCs, beat tracking, pitch detection, and feature extraction.

Python library with 7 summarization algorithms (LSA, Luhn, Lex Rank, TextRank) for documents and HTML pages.

Stanford NLP's Python library for tokenisation, sentence segmentation, NER, dependency parsing, and coreference across 70+ languages.

Expert-labeled dataset of 13,000+ annotations across 510 commercial contracts covering 41 legal clause types for contract review AI.

Open-source document ingestion library — partition PDFs, HTML, DOCX, and 25+ formats into clean elements for RAG pipelines.

OpenTelemetry-based observability SDK for LLM applications — traces, metrics, and logs for any AI framework.

NVIDIA's open-source LLM vulnerability scanner that probes language models for prompt injection, jailbreaks, hallucinations, and more.

DeepMind's MuJoCo-based physics simulation library and continuous-control RL benchmark suite.

End-to-end speech processing toolkit covering ASR, TTS, speech translation, enhancement, and speaker diarisation.

Meta FAIR's C++/Python 3D simulator for embodied AI: 10,000+ SPS, photorealistic rendering, RGB-D/semantic sensors.

MIT-licensed Python library for SEO, SEM, and digital marketing analysis: sitemap parsing, robots.txt analysis, keyword planning, and log file analysis.

Apache-2.0 RAG evaluation framework — faithfulness, answer relevancy, context recall, and more in one pip install.

LLM eval + red-teaming framework — test prompts and models against custom assertions, compare providers, and catch regressions in CI.

Git-like version control for ML datasets and pipelines — track experiments, reproduce results, and collaborate on data science projects.

Python SDK for AI agent monitoring, LLM cost tracking, session replay, and benchmarking across all major agent frameworks.

Open-source toolkit that extracts safety and quality signals — injection, PII, toxicity, sentiment, relevance — from LLM prompts and responses.

Official Tavily MCP server giving agents real-time web search, content extraction, site mapping, and crawling.

MCP server exposing Ghidra tools so LLMs can decompile and reverse-engineer binaries.

Guaranteed structured generation from LLMs: enforce JSON, regex, grammar, or Pydantic schemas at the token level.

Pydantic's type-safe agent framework: build production agents with structured I/O, dependency injection, and full observability.

Autonomous agent by OpenBMB with outer/inner loop planning, tool execution, and a human-in-the-loop GUI for long-horizon tasks.

All-in-one semantic search, RAG, and LLM workflow engine — embeddings, vector DB, and pipelines in one library.

Apache-licensed Java/Python NLP toolkit with tokenization, sentence detection, NER, POS tagging, and chunking — production-ready for legal document pipelines.

Anthropic's human-preference (helpful/harmless) dataset for RLHF and alignment research.

Structured outputs for LLMs using Pydantic — patches any OpenAI-compatible client to return validated Python objects.

Meta FAIR's modular library to train and evaluate embodied AI agents (navigation, manipulation, social tasks).

Open-source LLM evaluation and observability platform — trace, test, and monitor LLM apps end-to-end.

Connect Supabase projects to AI assistants to manage tables, fetch config, and query Postgres data.

Microsoft's code-first agent framework that converts user requests into executable Python snippets for complex data analytics tasks.

Persistent local Markdown-based memory so your AI assistant remembers across sessions.

Microsoft's open-source AI red-teaming toolkit for systematically finding risks in generative AI systems through automated adversarial probing.

Official Firecrawl MCP server — web search, scraping to clean data, and autonomous deep research.

CLI and Python library to access many LLM providers with a plugin system and SQLite logging.

ProtectAI's self-hardening prompt-injection detector using a multi-stage defence: heuristics, LLM analysis, and a vector canary database.

Block's Apache-2.0 on-machine AI developer agent — runs tasks end-to-end in your terminal, any LLM backend.

AI agent that retrieves, reads, and synthesises answers from scientific PDFs with citation-level accuracy.

AI-powered literature discovery and review engine for medical and scientific papers, built on txtai semantic search.

Lightweight BSD-licensed Python library providing 80+ stock technical indicators (RSI, MACD, Bollinger Bands, ATR) as simple DataFrame column lookups.

Physics-based 11-vs-11 football RL environment for training and benchmarking game-playing agents, from the Google Brain team.

Stanford CRFM's reproducible, multi-metric benchmark framework for evaluating any foundation model.

Apache-2.0 Python framework for building MCP servers fast — decorator-based, zero boilerplate, typed tool definitions.

MMLU: 57-subject multiple-choice benchmark for broad LLM knowledge and reasoning.

AWS Labs' suite of MCP servers for AWS docs, infrastructure, containers, databases, and cost analysis.

Python library for robot kinematics, dynamics, and trajectory planning with a familiar MATLAB-like API.

Python library for ML on brain imaging data: fMRI decoding, connectivity analysis, surface plotting.

Maintained fork of Quantopian's pyfolio providing comprehensive risk and return analytics, tear sheets, and performance attribution for quantitative strategies.

Open-source, self-hostable ChatGPT-style chat UI that works with any model.

LLM-friendly open-source web crawler that turns pages into clean Markdown/JSON ready for RAG and agent pipelines.

Gives your AI good taste — an anti-slop review/style contract that stops agents from shipping generic, boring frontends.

Official Qdrant MCP server — a semantic memory layer for storing and retrieving vectors.

Google's Apache-2.0 TensorFlow library for quantitative finance — GPU-accelerated options pricing, rate models, Monte Carlo simulation, and autodiff Greeks.

Apache-2.0 unsupervised clinical NER and linking library that maps free-text clinical mentions to SNOMED CT, ICD-10, UMLS, and other biomedical ontologies.

CCS'24 dataset of 15,140 in-the-wild ChatGPT prompts including 1,405 real jailbreak prompts for training and benchmarking jailbreak detectors.

Compress tool outputs, logs, files and RAG chunks before they reach the LLM — 60-95% fewer tokens, same answers.

Open-source annotation platform for building high-quality fine-tuning and RLHF datasets; integrates with Hugging Face Hub.

Official MCP servers to operate Cloudflare services (Workers, DNS, observability, security) via natural language.

Library and REST API that scans LLM prompts for prompt injection and jailbreaks using an ensemble of vector, transformer, YARA, and canary detectors.

Pythonic client for the arXiv API: search, download, and stream 2M+ preprints by query, author, or ID.

Open-source AI-powered app starter built with Next.js and E2B sandboxes — let users generate and run full-stack apps from natural language.

Modular node-graph GUI, API, and backend for diffusion-model image/media generation pipelines.

The pattern-matching engine for malware researchers — write rules to identify and classify malware by textual or binary signatures.

MCP server that injects up-to-date, version-specific library documentation and code snippets into an LLM's context.

Connect Blender to AI assistants for prompt-assisted 3D modeling, scene creation, and assets.

Validate, fix, and filter LLM outputs — define structured schemas and safety rules, then automatically retry when outputs fail validation.

Microsoft's official MCP server that gives AI agents deterministic browser control via Playwright's accessibility tree.

AI4Finance Foundation's multi-agent platform for financial tasks — market forecasting, report generation, portfolio management, and earnings analysis.

Local MCP server that lets agents run analytical SQL over DuckDB files and MotherDuck cloud warehouses.

Modular robot simulation framework built on MuJoCo for benchmarking robot learning algorithms.

Red-teaming kit for agentic LLM workflows: 2000+ adversarial probes, RL-crafted injections, CI-ready.

Experimental prompts, Jinja2 templates, and scripts spanning OpenAI, Anthropic, Google, Mistral and more.

Lightweight, fast text-chunking library purpose-built for RAG ingestion, with token, sentence, semantic, and code-aware chunkers.

Multi-task benchmark for legal NLP with 7 datasets covering EURLEX classification, contract clause labeling, court judgement prediction, and more.

A domain-specific language for translating statutory and regulatory text into correct, auditable executable code, pairing lawyers and programmers.

Code and the 52K instruction-following dataset behind Stanford's Alpaca models.

Makes your AI agent think like the laziest senior dev — the best code is the code you never wrote (YAGNI-first).

Python dataflow engine that wraps FSL, SPM, FreeSurfer, ANTs, and AFNI into reproducible neuroimaging pipelines.

Farama Foundation's collection of robotics simulation RL environments: FetchReach, ShadowHand, Maze, AdroitHand.

Pure-Python SQL parser and transpiler that translates queries between 20+ dialects and rewrites, optimizes, and analyzes SQL.

Generate and run property-based tests against any OpenAPI or GraphQL API to automatically surface crashes and spec violations.

Obsidian plugin that generates note content via OpenAI, Anthropic, Google, and local models.

MIT-licensed Django email marketing platform: subscriber management, campaign builder, open/click tracking, and segmentation — fully self-hosted.

Retrieval-augmented text-to-SQL: train on your schema and docs, then ask questions in English and get accurate, runnable SQL.

Active-learning annotation server for medical images: auto-segmentation, interactive refinement, OHIF/3D Slicer integration.

Framework that lets a multimodal model view the screen and control mouse and keyboard to complete tasks on a computer.

A Python library implementing classical and modern portfolio optimization: efficient frontier, Black-Litterman, HRP, and advanced risk models.

ProtectAI's scanner that detects malicious payloads hidden inside pickle, PyTorch, TF, and Keras model files.

spaCy-based NLP pipeline for English legal text: named entity recognition for cases, legislation, and provisions, plus text categorization.

Fast retrieval-augmented generation framework that fuses knowledge-graph structure with vector retrieval.

DeepMind's Python interface to the StarCraft II Learning Environment, exposing the game as an RL testbed for game-agent research.

Microsoft Azure's CLI for adversarial robustness testing of ML models: evasion, poisoning, extraction attacks.

Official MCP server exposing Grafana dashboards, datasource queries, alerts, and incidents to AI agents.

Fast, language-agnostic structural search, lint, and rewrite tool that runs codemods using AST patterns written like code.

A comprehensive Python toolkit of 60+ outlier-detection algorithms, widely applied to financial fraud and anomaly detection.

Interactive household simulation environment for embodied AI tasks including navigation and manipulation.

Official Notion MCP server to search, create, and edit Notion pages and databases in Markdown.

Self-hosted MIT-licensed SEO crawler and auditor: crawls websites, surfaces technical SEO issues, broken links, missing metadata, and duplicate content.

Google DeepMind's suite of 50+ multi-agent social RL scenarios testing cooperation, competition, and generalization.

Integrates LLMs as spaCy pipeline components for NER, classification, lemmatisation, and relation extraction with zero/few-shot prompting.

a16z's JavaScript/Next.js starter stack for AI apps: models, vector store, auth, and deploy.

Open NeurIPS benchmark for jailbreaking LLMs: balanced harmful/benign behaviors, reproducible attack artifacts, standardized judges, and a live leaderboard.

Stanford RegLab's 53K+ multiple-choice legal holdings dataset for training and evaluating legal NLP models.

Machine-readable database of U.S. legal reporters and their citation abbreviations, powering case-citation parsers like eyecite.

Neo4j Labs MCP servers for Cypher queries, knowledge-graph memory, and Aura instance management.

MIT-licensed AI content platform for SEO blog posts, social copy, YouTube scripts, and podcast outlines grounded in real web research and competitor data.

Pretrained PyTorch models that score text for toxicity, threats, insults, and identity attacks — a drop-in content-moderation guardrail.

Procedurally generated open-world survival benchmark that evaluates a broad range of RL and world-model agent abilities.

Prefect's Python library for building reliable AI functions, tasks, and workflow orchestration.

Read, search, and send your personal WhatsApp messages and media from an AI assistant.

A caching, scraping library that collects opinions, oral arguments, and PACER filings from hundreds of American court websites.

Extracts blocks, transactions, token transfers, receipts, and logs from Ethereum into CSV/JSON or warehouses for on-chain analytics.

Prompt-driven web scraping: describe the data you want and LLM graph pipelines extract clean structured JSON from any page.

Official ElevenLabs MCP server for text-to-speech, voice cloning, and audio transcription.

MCP server that lets agents run kubectl and Helm operations to inspect and manage Kubernetes clusters.

Self-hostable web app to tag arXiv papers and get recommendations of similar papers using SVMs over tf-idf abstract features.

Bridges AI assistants with the Unity Editor to manage assets, scenes, scripts, and tests.

Neovim AI plugin for GPT chat sessions, instructable text/code edits, and speech-to-text.

Privacy-focused, cookie-free open-source web analytics — a lightweight, self-hostable alternative to Google Analytics.

Unofficial Python client for the Semantic Scholar Academic Graph APIs: papers, authors, citations, and references.

OpenAI's 164-problem Python benchmark for evaluating code-generation correctness (pass@k).

Extracts and resolves legal citations (case law, statutes, law journals) from any block of text, built by the Free Law Project.

Large library of prompts, system prompts, and LLM instructions, including extracted product system prompts.

Fast open-source AI gateway that routes to 250+ LLMs through one API with load balancing, fallbacks, retries, and caching.

The Pythonic, event-driven algorithmic trading library that powered Quantopian, for backtesting and researching quantitative strategies.

Official ClickHouse MCP server — run read-safe SQL and explore databases and tables.

Lightweight, low-dependency unified Python API to run any cross-encoder, ColBERT, or LLM reranker to sharpen RAG retrieval.

An open-source expert system for guided interviews and automated assembly of legal documents, widely used in access-to-justice and legal-aid tools.

Brex's in-depth public guide to prompt engineering and working with GPT-4-class models.

Unified MCP access to biomedical literature, clinical trials, genes, variants, and drugs.

Connects AI assistants to Exa web search, code search, and company/deep research.

AI coding assistant for Neovim with chat, inline actions, and multi-provider LLM support.

MCP server giving agents safe PostgreSQL access plus index tuning, execution-plan analysis, and database health checks.

Official MCP server connecting agents to MongoDB databases and Atlas clusters for queries, aggregation, and admin.

Google's real-time 2D and 3D SLAM system that builds globally consistent maps across many sensor configurations.

Heterogeneous zero-shot information-retrieval benchmark bundling 15+ diverse IR datasets behind one evaluation API.

Curated collection of high-quality system prompts for ChatGPT, organized by role and use case.

Gives AI assistants terminal control, filesystem search, and diff-based file editing on your machine.

Semantic, symbol-level code retrieval, editing, and refactoring tools that turn your agent into an IDE.

MCP server for the Terraform Registry and HCP Terraform — providers, modules, and workspace automation.

MCP server for the Financial Datasets API — company financials, stock prices, and crypto data.

Gives AI coding agents structured Figma layout data to implement designs accurately in any framework.

Open-source RAG engine built on deep document understanding, grounding LLM answers with traceable citations.

Standardized framework for automated LLM red teaming: curated harmful behaviors plus 18+ attack methods scored by a common refusal-robustness metric.

Gives AI assistants deep knowledge of n8n nodes to build workflow automations for you.

A programming paradigm for steering LLMs — interleave generation, prompting, and control flow with constrained decoding and structured output.

Crawl a website from a single URL and generate one consolidated knowledge file to power a custom GPT or RAG assistant.

PyTorch library for loading, preprocessing, augmenting, and patch-sampling 3D medical images (MRI/CT) for deep learning.

Benchmark of 817 questions across 38 categories measuring whether LLMs avoid imitative falsehoods — a direct probe of factual hallucination.