Explore the directory

A framework that runs a second, more deliberative AI model alongside a primary coding agent to review its architecture, security, and performance decisions before code is written.

• Coding agents
• Code quality

A skill and CLI that lets one AI coding agent orchestrate several others in the background, assigning specific models or agents to specific parts of a task.

• Coding agents
• Agent skills

The official implementation of a speculative-decoding method that pairs a large language model with an adaptively trained diffusion drafter model to speed up inference.

• Inference
• Papers

A starter kit for building browser games with Vite, React, Three.js and TypeScript, built specifically to be driven by coding agents through predefined roles and skills.

• Web frameworks

A desktop app that turns a task backlog from tools such as Linear or HubSpot into work assigned to AI coding agents, which run locally and pause for approval before risky actions.

• Coding agents

A Claude Code skill that delegates coding subtasks to the cheaper Mistral Vibe agent, keeping Claude's own token usage to a small supervising role while it reviews the resulting diff.

• Agent skills

A Swift and Metal inference runtime for Apple Silicon that runs large mixture-of-experts language models by streaming only the active experts from disk instead of holding the whole model in memory.

• Inference

A purpose-built Rust database engine for AI agent memory, combining a write-ahead log, HNSW vector search, and a knowledge graph instead of wrapping an existing database.

• Agent memory
• Databases

A tool that turns scanned PDFs and images into searchable documents by reading them with a locally run vision language model instead of traditional OCR.

• RAG
• Inference

A journal of case studies documenting prompt-engineering experiments for the MiniMax H3 video model, recording what failed and which final prompts worked.

• Generative media
• Tutorials

A multi-agent forum simulator where several LLM-driven personas post, reply, and vote in a shared discussion, built to study emergent agent behavior and social dynamics.

• Agent frameworks

A worked tutorial that trains a multilayer perceptron neural network in PHP to classify movie review sentiment, using the Rubix ML library and 25,000 labeled IMDB reviews.

• Tutorials

An independent, audited fork of the ZCode AI coding client that removes all monitoring and telemetry and builds transparently from its own source.

• Coding agents
• Security

A headless daemon that runs autonomous coding agents against Linear tickets, moving them through a configurable workflow of agent stages and human review gates.

• Coding agents
• Workflow automation

An R package that fits Bayesian regression models with one or more change points between linear or generalized linear segments.

• Libraries

A research framework in which a meta-agent designs, evaluates, and verifies multi-agent system architectures for a task without labeled supervision or a validation set.

• Agent frameworks
• Papers

The official code and project write-up for an ICML 2026 paper showing that smaller language models compress their token embeddings into a narrow region, and proposing a dispersion loss to counteract it.

• Models
• Papers

A research framework that replaces a single central orchestrator with a shared, verified context so parallel agent threads can accumulate reusable progress on a coding benchmark.

• Agent frameworks
• Papers

A Datasette plugin that adds an LLM-powered chat assistant for exploring a Datasette instance's databases and tables, plus background agents that write exploration reports.

• Databases
• Data engineering

A session manager that runs fleets of Claude Code and Codex terminal sessions, adds a status sidebar, lets agents message each other, and links sessions across machines.

• Coding agents

A zero-dependency CLI and browser tool that converts and keeps in sync the rule files different AI coding agents read, such as AGENTS.md, CLAUDE.md, and .cursorrules.

• Agent skills
• CLI tools

A memory infrastructure library for long-running AI agents that keeps identity and facts consistent across model switches, crashes, and context limits.

• Agent memory

A neural vector compression method for large-scale similarity search that predicts each quantization step's codebook from a neural network instead of using a fixed one.

• RAG

A serving runtime for robotics vision-language-action models that runs custom fused kernels on NVIDIA Jetson Thor and desktop GPUs for faster real-time prediction.

• Inference