Explore the directory

A cross-platform AI chat client for macOS, Windows, Linux, iOS, Android and the web that connects to Model Context Protocol servers, with local-network data sync between devices.

• MCP servers
• Inference

A reliability layer that makes self-hosted LLM tool-calling more dependable, sitting inside an existing agent loop or coding harness as a proxy, a workflow runner, or middleware that validates responses and rescues malformed tool calls.

• Agent frameworks

A Rust ecosystem of crates for running local and remote pre-trained language, audio and image models, with structured generation that constrains model output to a Rust type, regex or custom grammar.

• Inference
• Libraries

A Kubernetes-native platform for distributed AI model training and large language model fine-tuning, orchestrating multi-node, multi-GPU jobs across frameworks such as PyTorch, JAX, HuggingFace and Megatron-LM.

• Models
• Containers

A curated, multi-language collection of prompt examples for OpenAI's GPT Image 2 and 2.5 models, organized by category such as photorealism, UI design, typography and character consistency.

• Generative media
• Curated lists

An archived Microsoft research project demonstrating a multi-modal memory service for LLM applications, indexing documents into embeddings for retrieval-augmented generation with citations.

• Agent memory
• RAG

A native control plane for local coding agents such as Claude Code, Codex, Cursor and Devin, running local-first by default with optional multi-device sync so a session can be followed or driven from another machine.

• Coding agents

A curated list of open-source AI agent projects that ranks entries by how quickly their GitHub popularity is growing, tracked over daily, weekly and monthly windows across the agentic AI ecosystem.

• Agent frameworks
• Curated lists

A daily-updated, curated collection of papers, prompt-engineering techniques, and getting-started guides for in-context learning and prompting large language models such as ChatGPT.

• Curated lists
• Papers

A Claude Code plugin toolkit for enterprise architects that turns architecture governance into structured, AI-assisted workflows for strategy, risk, business cases, requirements, data modeling and vendor selection.

• Agent skills

An open-source Computer Use service, exposed as an MCP server, that lets any AI agent or MCP client run GUI automation on macOS, Linux and Windows through the accessibility API.

• MCP servers
• Agent skills

A conversational data-analysis system that turns natural-language questions into validated SQL, runs them against a database, and renders the results as charts, using retrieval-augmented generation and a multi-agent pipeline.

• RAG
• Data engineering

An agentic research tool that turns a company name into a structured, source-backed briefing, coordinating web search, relevance scoring and multi-model synthesis behind a FastAPI backend and a React interface.

• Agent frameworks

A lightweight, memory-efficient terminal for Mac built with SwiftUI and libghostty, with project groups, git worktree support, split panes and an extensible API.

• Terminals

An HTTP credential proxy and vault that sits between AI agents and the APIs they call, so agents route requests through it instead of holding API keys directly, reducing the risk of credentials leaking through prompt injection.

• Security

A terminal-based AI coding assistant tuned specifically for the DeepSeek-v4 model family, with thinking-mode and reasoning-effort controls, Agent Skills, and MCP integration.

• Coding agents

A small CLI wrapper that runs Claude Code's agent loop against DeepSeek V4 Pro, OpenRouter, or any other Anthropic-compatible API, by setting environment variables for the session and restoring the prior configuration on exit.

• Coding agents

A no-code orchestration platform that assembles a team of AI expert roles from a single sentence, runs them through YAML-defined workflows with acceptance checks, and delivers finished documents, images or video.

• Workflow automation

A multi-agent orchestration framework that mechanically enforces engineering rules on AI coding assistants, gating every code-changing turn on checks that reviewers ran, memory updated, and shipped files are supply-chain intact.

• Agent frameworks
• Code quality

A unified control plane for provisioning and orchestrating GPU compute across clouds, Kubernetes, VMs and bare-metal clusters, used to run AI training and inference on NVIDIA, AMD, Google TPU or Tenstorrent hardware.

• Hosting

A production-oriented multi-agent orchestration framework that runs agents as Temporal workflows with token budgets, WASI sandboxing, policy-based access control, and replayable, step-by-step execution history.

• Agent frameworks

A curated, continuously updated list of academic papers on large language model systems, tracking work on training, serving, agent systems and hardware co-design from 2024 through 2026.

• Papers

A collection of 50 specialized Claude Code subagents that turn Claude into an offensive security research assistant for authorized penetration testing, covering reconnaissance, web, cloud, mobile, exploit development and reporting.

• Security

An AutoML library in Scala that runs on Apache Spark, automating feature engineering and model selection to build strongly typed, production machine learning pipelines with close to hand-tuned accuracy.

• Models
• Data engineering