Explore the directory

A research paper and accompanying code that stores a user's facts as a few rows in a content-addressed edit to a language model's parameters, instead of a separate retrieval index or per-user LoRA.

• Agent memory
• Papers

A Python package that compresses KV-cache and vector payloads for existing agent runtimes and retrieval pipelines, adding reranking and benchmarking without requiring a new framework.

• RAG
• Inference

Field notes recording how to cross-compile and deploy llama.cpp GPU inference on an NVIDIA DRIVE Thor automotive domain controller, including a troubleshooting guide and measured throughput at each optimization step.

• Inference
• Tutorials

A local, API-free Claude Code plugin that gives the agent four layers of long-term memory — conversation, atom, scene and persona — built on local full-text and vector search.

• Agent memory

A cloud-native control plane that runs long-lived autonomous agents in production, with durable execution, declarative YAML configuration and a browser-based fleet view.

• Agent frameworks

A continuously updated survey that collects and verifies public demonstrations of frontier multimodal models doing 3D modeling, computational design and robotics work, assessing what they can reliably do today.

• Papers

A PyTorch framework for fine-tuning the Suiren family of pre-trained molecular encoder models on custom regression or classification property-prediction tasks.

• Models

A command-line search engine that indexes over 2700 OpenClaw skills and returns the closest matches to a natural-language query, in Chinese or English.

• Agent skills

A library that logs the actions AI agents take in production as a tamper-evident, cryptographically hash-chained record, so teams can prove what an agent did and detect if a log was altered afterward.

• AI evals

A pair of Colab notebooks demonstrating a retrieval-augmented generation workflow for extracting structured datasets from scientific paper abstracts, applied here to hydrogen-storage properties of metal alloys and hydrides.

• RAG
• Data engineering

A free ebook that teaches .NET developers to build production AI-powered applications in C#, pairing each chapter's markdown lesson with a runnable .NET project and unit tests, without Python or notebooks.

• Tutorials
• Books

An OpenClaw plugin that connects any MCP server to an OpenClaw agent, registering its tools automatically and offering either individual per-tool registration or a single router tool that saves most of the token cost of many servers.

• MCP servers

A macOS desktop app that combines chat, a multi-agent orchestrator, a code agent and a design tool in one sidebar, sharing memory, project context and a single local LLM proxy across Anthropic, OpenAI, OpenRouter, Ollama, Gemini and other OpenAI-compatible providers.

• Coding agents
• Agent frameworks

A CLI-first, local-first observability tool for LLM applications that traces and stores LLM calls, vector-store queries and LangChain steps in SQLite, then uses an LLM of your choice to help investigate the root cause of failures.

• AI evals
• Monitoring

A Nix flake and home-manager module that declares an entire AI coding toolkit, Claude Code, Gemini, GitHub Copilot, OpenAI Codex, Cursor CLI, Qwen Code and a shared catalog of MCP servers, as reproducible configuration, rebuilding it identically on any supported machine.

• Agent skills
• Hosting

A starter repository for a Knight Center course on advanced prompt engineering for journalists, giving students a working Claude Code workspace with worked examples of context files, memory, skills, commands, hooks and a staged pipeline.

• Tutorials

A dependency-free Rust runtime for Apple's MLX framework that loads Hugging Face model checkpoints straight onto Apple Silicon GPUs for fast local inference, shipped as both a native Rust crate and a Node.js package.

• Inference

A local-first C# library for building long-term memory into .NET AI agents, assistants, simulations and robots, combining semantic retrieval, an auditable temporal history and spatial memory of timestamped 3D observations.

• Agent memory

An open-source security gateway that sits between an MCP client and server, screening every tool call through a multi-stage pipeline of rate limiting, injection detection, SSRF and egress control, policy enforcement and dangerous-chain detection.

• MCP servers
• Security

A retrieval-augmented generation engine built with LlamaIndex for querying past MCM/ICM mathematical-modeling competition papers, chunking each paper by its heading structure into whole-section nodes tagged by year, problem and section for precise, filtered retrieval.

• RAG

A fullstack TypeScript framework where a single component definition is projected three ways: a live UI for people, and typed MCP tools and resources for AI agents, so the human interface and the agent-facing tools cannot drift apart.

• MCP servers
• Web frameworks

A self-hostable platform for internal enterprise AI agents that keeps a team's knowledge, instructions, skills and tools in a versionable folder and reuses that shared context through chat, scheduled workflows, or a personal assistant connected over MCP.

• Agent frameworks

An experimental project for running small transformer checkpoints such as SmolLM 135M and Qwen2.5 0.5B directly on the first-generation AMD XDNA NPU in Ryzen AI processors, using MLIR-AIE kernels, a patched Ollama build and a native Colibri backend.

• Inference

A package manager for AI-agent configuration that installs skills, rules, agents and MCP servers into Claude Code, Copilot, Cursor, Codex, Gemini, Zed, Amp, Kiro, Junie and opencode, storing packages on any OCI registry with no separate service to run.

• Agent skills
• CLI tools