Explore the directory

A Neovim plugin that connects the editor to large language models and coding agents for chat, inline code transformation, and tool-based workflows.

• Coding agents
• Editors

A self-hosted backup automation tool built on Restic that schedules, encrypts, and monitors backups of remote storage through a web interface.

• Hosting

A code generation and manipulation library that creates and changes Java classes at runtime without a compiler, usable as a library, a Java agent, or a build-time tool.

• Libraries

An AI coding workbench from Z.ai that provides a desktop application, a browser interface, and a terminal agent from one shared codebase.

• Coding agents

A persistent memory system for AI coding agents, packaged as a single agent-agnostic Go binary with a SQLite full-text search store behind it.

• Agent memory

A validated, security-scanned registry of packaged skills that extend coding agents such as Claude Code, Cursor, Copilot, and Antigravity with new workflows.

• Agent skills

A TypeScript library that extracts structured data from any web page by sending its content to a large language model against a defined schema.

• Browser automation

A self-hosted TypeScript agent runtime where consequential actions wait for durable, tamper-evident approval and every run leaves an offline-verifiable record.

• Agent frameworks

A C library implementing X.509 certificate handling and the TLS and DTLS protocols, with a small code footprint intended for embedded systems, plus a PSA Cryptography API implementation.

• Security
• Libraries

A three-part kit for the DeepSeek Harness runtime that adds a hot-reloading tool injector, task-aware model routing presets, and a staged task protocol.

• Coding agents

A Claude Code plugin and npm library that replaces context-compaction summaries with per-call keep-or-drop decisions from a model called Jev, keeping everything it retains verbatim.

• Agent skills
• Agent memory

A collection of Claude Code and Codex skills that package common engineering habits, such as planning, UI iteration, release review, and debugging, into runnable playbooks.

• Agent skills

An MCP integration that lets AI coding agents such as Cursor and Claude Code read and modify Figma designs programmatically through a Figma plugin.

• MCP servers
• Design tools

A microkernel AI agent that routes each turn to the cheapest capable model and runs the same loop across a CLI, web UI, and chat channels.

• Agent frameworks
• LLM gateways

A self-hosted codebase intelligence tool that indexes code, dependency graphs, git history, tests, and documentation to give agents and developers cited answers.

• Agent memory
• Code quality

A self-hosted, open-source ecosystem of AI agents that share long-term memory, work across many messaging apps, and can switch models mid-task.

• Agent frameworks
• Agent memory

An AI-native proxy server and data plane for agentic applications that centralizes LLM routing, agent orchestration, observability, and guardrails.

• LLM gateways
• AI evals

An enterprise job scheduling library for .NET, installed as a single package that includes dependency injection, hosting integration, a health check, and JSON serialization.

• Backend

An inference framework built on vLLM that extends serving to omni-modality models covering text, image, audio, and video generation and understanding.

• Inference

An AI search and serving platform for organizing and querying vectors, tensors, text, and structured data at scale, with sub-100-millisecond responses over large, continuously changing datasets.

• Databases

An open lakehouse file, table, and catalog format for multimodal AI data, built for fast random access and hybrid search on top of object storage.

• Databases

An open-source, cross-platform USB host and device stack for embedded systems, built for memory safety and real-time performance across more than fifty microcontroller families.

• Libraries

An open-source gateway that puts hosted, BYOK, and local language models behind one OpenAI-compatible API, with per-user spend limits and routing learned from production traffic.

• LLM gateways

A Python package for generating text with and fine-tuning large language models on Apple silicon using Apple's MLX framework.

• Models
• Inference