Explore the directory

A low-code RAG development framework built on the Model Context Protocol, letting a developer assemble retrieval-augmented-generation pipelines from independent MCP servers and orchestrate them with YAML.

• MCP servers
• RAG

An open-source edition of a developer platform for the full lifecycle of AI agents, covering prompt development, evaluation and observability.

• Agent frameworks
• AI evals

An independent, curated directory of skills, plugins, memory providers, and surfaces for Hermes Agent, the open-source self-improving agent from Nous Research.

• Agent skills
• Curated lists

A JAX library for using and fine-tuning Gemma, Google DeepMind's family of open-weight large language models built on Gemini research.

• Models

A command-line PNG compressor that converts images to an efficient 8-bit palette format with alpha channel, typically shrinking files 60 to 80 percent, also available as an embeddable library.

• CLI tools
• Libraries

A self-hostable, open-source alternative to Vapi and Retell for building voice AI agents with a visual workflow builder, letting a team bring their own LLM, speech-to-text and text-to-speech providers.

• Speech

A model-swapping proxy that runs multiple local AI models and hot-swaps between them on demand, working with any OpenAI or Anthropic API compatible server.

• Inference

An open-source GPU cluster manager that configures and orchestrates inference engines such as vLLM and SGLang, and lets a team launch SSH-accessible GPU instances on demand.

• Inference
• Hosting

A high-performance data engine for AI and multimodal workloads that processes images, audio, video and structured data at scale, with built-in operations for running LLM prompts and generating embeddings.

• Data engineering

A local AI server that runs large language, speech and image-generation models on a user's own GPU or NPU, exposing OpenAI, Anthropic and Ollama-compatible APIs at no cost.

• Inference

A visual playground for building and iterating on agentic workflows, letting an AI engineer define test cases, build an agent in Python code or a UI, and deploy it as an API.

• Agent frameworks

A production-ready Java framework for building distributed, enterprise-grade AI agents, with an event system, tool-call permission gating, middleware, sandboxed workspaces and multi-agent orchestration.

• Agent frameworks

An MCP integration platform offering prebuilt connectors, a context-optimizing tool router, and sandboxed MCP environments, so AI agents can use external tools reliably at scale.

• MCP servers

A research report on AI agent source code, distributed as downloadable PDFs, alongside a small teaching project that demonstrates how a minimal Python agent's core loop, tool skills and CLI fit together.

• Tutorials
• Books

A local-first workspace that turns coding agents such as Claude Code, Codex, OpenCode, Cursor or Google Antigravity into research agents that review literature, develop hypotheses, run experiments and produce research artifacts.

• Coding agents

An open-source framework for training language agents with reinforcement learning, letting a developer bring any agent harness and sandbox and switch training backends with one flag.

• Agent frameworks
• Models

An observability and devtool platform for AI agents, giving Python developers session replay, LLM cost tracking, and integrations with agent frameworks such as CrewAI, AutoGen and LangGraph.

• AI evals

A hands-on workshop that teaches developers to build a coding agent in Go, one step at a time, starting from a basic chatbot and adding file reading, command execution and code search.

• Tutorials

A desktop app for running multiple AI coding agents in parallel, each in its own Git worktree, so a developer can compare diffs across agents and merge the result that works.

• Coding agents

A zero-code platform for building production-grade AI agents that unifies tools, skills, memory and orchestration with built-in constraints and feedback loops, described in plain language rather than assembled with drag-and-drop.

• Agent frameworks

An open-source connector gateway that lets AI agents and applications reach more than a thousand SaaS providers and prebuilt actions through an SDK, CLI, MCP, HTTP or OpenAPI.

• MCP servers
• Workflow automation

A single-binary, OpenAI-API-compatible local inference server for GGUF models, built entirely in Rust on the project's own WebGPU transformer engine, Airframe.

• Inference

A modular desktop workspace where AI coding agents, models, plugins and workflows live together, so a developer can extend it with panels, tools, MCP servers and background services.

• Coding agents

A family of pretrained time series forecasting models offering zero-shot univariate, multivariate, and covariate-informed forecasting, deployable through AWS SageMaker or AutoGluon.

• Models