Explore the directory

A native macOS menu bar and desktop app that monitors Inco AI's Splash local inference engine, showing live token throughput, memory use, and installed models, and offering one-click model installation and server control.

• Inference
• Desktop utilities

A memory engine for AI agents written in Java, storing working, episodic, semantic, and procedural memories with decay and consolidation, and retrieving them through fused semantic and SIMD-accelerated hybrid search.

• MCP servers
• Agent memory

A C# library that implements neural network inference and training as GPU compute kernels for .NET, running the same code on WebGPU, CUDA, OpenCL, WebGL, WebAssembly, and CPU, including inside a browser via Blazor WebAssembly.

• Inference
• Libraries

A Python library that enforces spend limits on AI agents by monkey-patching LLM provider calls, stopping runs, warning, or downgrading models before a budget is exceeded.

• AI evals

A role-aware retrieval-augmented generation platform for enterprise knowledge bases that filters search results by the requesting user's role and document permissions.

• RAG

A research implementation of a retrieval-augmented framework that gives a vision-language model spatial awareness for object-centric robot manipulation.

• RAG

A peer-to-peer semantic-matching layer for on-device AI agents that routes content by meaning instead of through a server-owned index, built for an on-device AI hackathon.

• Agent frameworks

A self-hosted, memory-native AI agent framework with a cross-platform app GUI, designed to run continuously and build up its own long-term memory over time.

• Agent frameworks
• Agent memory

A command-line tool that tells you which local LLMs fit an Apple Silicon Mac, how fast they will run, and how to launch them, in one command.

• Inference

An open-source control plane that sits on top of an AI agent's own logic, deciding whether each action is allowed, pausing it for human approval, and logging proof.

• Agent frameworks
• AI evals

A small, growing collection of filter, pipeline and tool extensions for Open WebUI that fill everyday usability gaps in local and cloud LLM chat workflows.

• Inference

An MCP-based infrastructure layer for coordinating AI agent swarms across a fleet of servers, combining remote-control tools, agent messaging, a mesh VPN and a browser.

• Agent frameworks
• Networking

A context provider for data agents that keeps metric definitions, verified example queries and interpretation notes in one knowledge base, served over MCP, REST and CLI.

• MCP servers
• Data engineering

A local-first agentic retrieval-augmented generation engine that combines hybrid search, a knowledge graph and a multi-agent runtime, running entirely on Ollama.

• RAG

A fully open-source personal AI agent for Android that runs entirely on the phone, keeps working while the app is closed, and can also drive a paired desktop from the phone.

• Agent frameworks
• Mobile

A pip-installable benchmark toolkit that measures routing entropy, expert utilization and collapse in sparse Mixture-of-Experts language models.

• AI evals

An SDK for building MCP servers, tools, prompts, resources and interactive widgets, that stays close to the official MCP SDK while removing repetitive setup code.

• MCP servers

A desktop app for manually testing MCP servers: connect, browse the tools, resources and prompts they expose, invoke them with real input, and inspect the response.

• MCP servers
• Testing

An open-source, local-capable pipeline where a team of planner, executor and reviewer agents builds a working MVP from a plain-English description, phase by phase.

• Coding agents

A local MCP server giving one MCP client session-aware control over several AI coding-agent CLIs, while keeping each tool's native sessions and local credentials.

• Coding agents
• MCP servers

A collection of self-contained example applications that show how to deploy AI models at scale with Lightning AI's LitServe model-serving engine.

• Inference
• Tutorials

An unmanaged, zero-allocation native AI inference runtime for Java 22 and newer that consolidates vision, speech and LLM pipelines behind one native memory boundary.

• Inference

A tool that generates and validates OpenTofu infrastructure code with an LLM across several clouds, checking each attempt against deterministic mock servers first.

• Agent frameworks
• Hosting

A zero-dependency coding-agent harness for local, open-weight models, pointed at llama.cpp, llama-swap, vLLM or any OpenAI-compatible endpoint on the user's own hardware.

• Coding agents