Explore the directory

A reference collection of runnable, checked Python implementations of agent design patterns such as prompt chaining, routing, parallelization and multi-window autonomous agents.

• Tutorials

A local, offline memory engine for AI agents and robots, written as a single Rust binary that stores and recalls facts without calling any language model.

• Agent memory

A desktop control room for running several coding-agent sessions in parallel, each in its own Git worktree, tracked on a Kanban board alongside diffs and pull requests.

• Coding agents

A policy engine that intercepts an AI agent's destructive or expensive tool calls, routes them to a human for remote approval, and records every decision in a signed ledger.

• AI evals
• Security

An orchestration platform for AI coding agents that lets a developer define tasks and review results while agents such as Claude Code or Codex implement the work in the background.

• Coding agents

Neo4j's official MCP server, giving an AI assistant such as Claude, Cursor or VS Code direct, structured access to explore a Neo4j graph's schema and run Cypher queries against it.

• MCP servers
• Databases

A retired Laravel package for building autonomous AI agents with tools, sub-agent delegation and persistent memory; the final release still works but gets no further updates, and the project has moved to a separate evaluation tool instead.

• Agent frameworks

A small Transformer language model and pure C inference engine for personal experimentation, running pretrained and fine-tuned models from a browser down to microcontrollers, single-board computers and routers.

• Models
• Inference

A local LLM chat UI for the web and Chrome, connecting to Ollama, LM Studio, AUTOMATIC1111 or Chrome's on-device Gemini Nano with no external API calls, so chats and image generations stay fully private.

• Inference

An MCP server that connects Charles Proxy to AI agents, letting them read live and historical HTTP traffic captures as structured, summary-first data instead of raw packet dumps, plus tools for reverse-engineering auth and replay.

• MCP servers
• Debugging

An open-source visual AI agent builder and runtime, with a drag-and-drop workspace for building agent workflows without code, extendable with custom code and deployable locally, in the cloud or at the edge.

• Agent frameworks
• Workflow automation

A lightweight AI agent construction platform with configurable, hosted agents and MCP services, letting a user turn any HTTP endpoint into an MCP tool and have agents communicate with each other over A2A.

• Agent frameworks

A deprecated community MCP server for Snowflake, providing Cortex AI search, analyst and agent tools, object management, SQL execution and semantic view querying; its own README tells users to migrate to Snowflake's official MCP server.

• MCP servers
• Databases

Hugging Face's official MCP server, connecting an LLM client such as Claude, Gemini CLI, VS Code or Cursor to the Hugging Face Hub and thousands of Gradio AI applications.

• MCP servers

A Rust-native, stateful API gateway that sits in front of vLLM and implements an OpenAI-compatible Responses API server-side, so a client makes one call and the server manages conversation state, tool execution and streaming.

• LLM gateways

Forsaken-Mail is a self-hosted disposable email service: it receives mail for any address at your configured domain and discards it after reading, for throwaway or test addresses.

• Backend

A graph foundation model-powered retrieval-augmented generation pipeline that uses a pre-trained graph neural network to reason over a knowledge graph built from a user's documents and retrieve passages for question answering.

• RAG

An open, provider-agnostic pub/sub standard and CLI for coordinating AI agents in any topology, a flat team of peers, a manager with workers, a chain of command or any mix, across machines.

• Agent frameworks

A minimal C++/GGML inference engine for OpenAI's privacy-filter PII/NER model family, detecting personal-data entity spans with exact byte offsets much faster and with far less memory than Hugging Face Transformers.

• Inference

An MCP server, official from Postman, that connects AI coding agents such as Claude Code, Cursor and VS Code Copilot to a user's Postman workspaces, collections, API specifications and environments.

• MCP servers
• APIs

A Rust, UEFI-resident LLM runtime that boots a PC or Raspberry Pi 5 directly into a local chat prompt from a USB stick or SD card, with no operating system underneath.

• Inference

A local-first, single-binary MCP server that gives multiple AI coding agents a shared task board, memory and context, so agents in different editors can claim work with atomic locks and hand off cleanly.

• MCP servers
• Agent memory

A platform for building personal AI agents that scales into team and enterprise agent workforces, letting a user describe an outcome rather than write a workflow.

• Agent frameworks

A Chrome browser-automation agent, forked from Nanobrowser, that runs its model on-device inside the extension by default, so a task in plain language runs with no API key, no cloud call and no page content leaving the browser.

• Browser automation