A Python framework for building distributed video and stream processing pipelines that can run locally or on Kubernetes using NATS JetStream.

An auto-tuning tool for GPU kernels that benchmarks and optimizes parameters across multiple GPU programming languages to improve performance and and energy efficiency.

SeekStorm is an open‑source Rust search engine offering native lexical (BM25, faceting, typo‑tolerance) and vector (ANN, quantisation, hybrid) indexes. It can be used as an in‑process library or as a multi‑tenant REST server, with client SDKs for Rust, Python, TypeScript, C# and Java. Designed for sub‑millisecond latency on a single commodity machine, it supports real‑time incremental indexing, sharded billion‑scale indexes, and a web UI for ad‑hoc queries.

An open-source LLM function calling framework for building scalable, ultra-fast AI agents using a geo-distributed architecture to reduce latency.

A collection of Swift utilities for adopting language models, providing tokenization, Hugging Face Hub downloads, and CoreML integration.

A physics-informed neural network (PINN) for stable modeling and prognosis of lithium-ion battery degradation and State of Health (SOH).

A shared AI agent layer that enables geospatial Python packages and QGIS plugins to expose their tools to LLMs through a consistent interface.

A file-backed workflow and runtime for AI agents that replaces chat memory with repository-local artifacts to ensure continuity and consistency across sessions.

An MCP server that provides AI coding agents with structured, full-content web search results from technical sites like GitHub and StackOverflow to improve code generation quality.

A Julia compiler that transforms functions into MLIR and XLA to enable high-performance execution and automatic differentiation on CPUs, GPUs, and TPUs.

A Windows automation plugin that integrates window management, screen capture, OCR, and YOLO detection into a unified API for scripting and desktop automation.

An MLIR-based JavaScript analysis tool that enables high-level source-to-source transformation and low-level dataflow analysis for decompilation and deobfuscation.

A high-performance data profiling tool that discovers and validates complex patterns in datasets to improve data quality and feature engineering.

An open-source semantic layer for analytics that enables drag-and-drop data exploration and provides a typed API for AI agents to query data cubes without writing MDX.

An open-source framework for documenting problems and solutions linked to authoritative data, designed to accelerate human progress through shared, evidence-based knowledge.

A tool that uses LLMs to un-minify JavaScript by suggesting meaningful names for variables and functions while maintaining structural integrity via AST manipulation.

A browser extension for managing and quickly inserting preset AI prompts into any web input field using shortcuts and variables.

A local management interface for AI coding agents that organizes Claude Code and ChatGPT Codex sessions into a unified, scrollable browser-based terminal with cost tracking and workflow tools.

A Python library for building scripted agents and reinforcement learning bots for Pokemon Showdown.

A high-performance Go-based AI backend for ESP32 devices that enables low-latency, full-streaming voice interactions by integrating ASR, LLM, and TTS engines.

AI agent tooling for data engineering that extends AI coding agents with specialized skills and an MCP server for managing Apache Airflow and querying data warehouses.

A React Native Expo UI kit featuring 10 high-fidelity animated welcome and onboarding screens inspired by leading iOS apps, designed for educational study and integration via AI coding agents.

A Python library that repairs malformed JSON from LLMs and APIs by fixing syntax errors and completing missing structures to ensure valid parsing.

An open-source LLM load balancer and serving platform that enables self-hosted inference, deployment, and scaling of LLMs on private infrastructure.

A command-line interface for App Store Connect that automates builds, releases, TestFlight, and monetization, featuring structured JSON output for AI agent integration.

A macOS menu bar application that tracks Claude.ai session and weekly usage limits in real-time using session cookies.

A browser extension that adds timeline navigation, prompt libraries, and organization tools to AI chat interfaces like ChatGPT and Gemini to improve long-conversation management.

A tool for fetching X/Twitter tweets, timelines, and articles without API keys or logins, featuring automatic backend fallback and a unified JSON schema for AI agents.

A GPU-accelerated DataFrame library for tabular data processing that provides a pandas-compatible API and zero-code change acceleration for pandas, Polars, and Dask.

A lightweight Python library that estimates and tracks carbon emissions from local computing hardware (CPU, GPU, and RAM) to help developers reduce their environmental impact.

A Python library for building predictable AI workflows by turning typed functions into structured LLM calls with automatic validation and retries.

A self-hosted payload-analysis sandbox for red and blue teams to test samples against static, dynamic, and EDR analysis tools to determine their detection likelihood.

A macOS notch companion that provides real-time visual feedback, sentiment-based emotional reactions, and usage tracking for Claude Code and Codex activity.

A high-performance GPU-accelerated molecular dynamics package that supports empirical and neuroevolution machine-learned potentials for materials simulation.

A specialized AI skill that provides guidance and best practices for writing and maintaining Playwright tests in TypeScript across various testing modalities.

A physiologically-informed tool for parameterizing neural power spectra by separating aperiodic components from periodic oscillations in electrophysiological data.

An offline skill pack for AI programming assistants that provides comprehensive HarmonyOS NEXT documentation, API references, and automation tools for ArkTS and DevEco Studio.

A multi-language bug scanner designed as a quality guardrail for AI coding agents, flagging critical bugs and security vulnerabilities early using AST and taint analysis.

gh‑axi is a Node‑based wrapper around the official GitHub CLI, purpose‑built for autonomous AI agents. It delivers token‑efficient, structured output, robust error handling, and a full suite of GitHub commands (issues, PRs, stacks, workflows, projects, secrets, gists, raw API, etc.). Benchmarked to be the cheapest and most successful tool in the AXI suite, it can be installed as an AXI skill or via npm, and includes optional session hooks for agents like Claude Code.

A graph-first IDE for agentic coding that provides live codebase visualization and coordination tools to manage multiple AI agents working on one repository.

An open-source compiler framework based on MLIR that optimizes and compiles machine learning models for Tenstorrent's custom AI hardware accelerators.

A tool that manages multiple AI coding agents in parallel by isolating each in its own tmux pane and git worktree.

CLI WeChat Bridge is a Node.js tool that connects local AI‑code assistants (Codex, Claude Code, OpenCode, Pi) to personal or Enterprise WeChat. It lets you keep the terminal as the primary interface while using WeChat to send prompts, receive outputs, and control sessions via slash commands or emoji shortcuts. Supports one‑off commands and a persistent daemon for multi‑tool switching, with full file‑transfer handling and AGPL‑3.0 licensing.

A local-first knowledge management system that captures, indexes, and makes searchable all interactions with AI coding assistants across various IDEs and CLI tools.

k7 is an open‑source platform that lets you run isolated VM sandboxes (via Kata, Firecracker, QEMU, or Katakate’s own k7d runtime) on Kubernetes. It targets AI agents needing to execute untrusted code at scale, offering fast warm‑forks, Docker‑in‑VM support, snapshotting, and optional Cilium network policies. Install via APT, manage sandboxes with the `k7` CLI or Python SDK, and control everything through an automatically deployed HTTPS API.

An MCP server that gives AI agents free, keyless web search and anti-bot fetching capabilities, allowing them to bypass bot walls and crawl the web locally.

A compiler and runtime that provides AI agents with a single governed graph over databases, warehouses, files, and source code via GraphQL and MCP.

An AI-powered threat modeling tool that uses LLMs to generate STRIDE-based threat models, attack trees, and mitigations for traditional and AI-driven applications.