Loading...
Loading...
Mlx Serve: Native LLM inference server for Apple Silicon. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Mlx Serve. This is an automatic list. We have not written a researched verdict for Mlx Serve yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
The Rust SDK for building coding agents.
Cersei is a Rust SDK for building coding agents. It provides the building blocks of a production coding agent as composable library functions: tool execution, streaming from language model providers, subagent orchestration, persistent memory backed by an embedded graph database, skills and MCP integration. Developers c...
Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。
Cindy is an open source AI agent from XD Inc that brings several agent harnesses, models, tools, memory and skills into one desktop agent that finishes real work in a user's projects and apps. It currently supports Claude Code, Codex and Pi as harnesses, with a native harness in development, and every supported model r...
Token efficient Claude Code full Python rebuild.
ClawCodex is an open source coding agent for the terminal, written as a Python native rebuild of the Claude Code architecture that works with many model providers instead of Claude alone. It keeps a genuine tool calling loop, a streaming REPL, persistent sessions and markdown based skills, and puts one runtime in front...
AI Coding, Vim Style
CodeCompanion.nvim is an open source plugin that brings AI assisted coding into Neovim. It lets developers chat with large language models in a dedicated buffer, write model output directly into existing buffers through inline transformations, and drive command line coding agents without leaving the editor. The project...
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM.
Headroom is a context optimization layer for LLM applications and coding agents. It compresses what an agent reads, including tool outputs, database results, file reads, RAG retrievals and API responses, before the content reaches the model, so the model sees less noise, responds faster and costs less. It is for devel...
Local-first native macOS terminal with Vietnamese IME support and coding-agent observability
Herminal is a native macOS terminal built for developers who spend their day inside Claude Code and similar coding agents. It embeds libghostty, the terminal core written in Zig with a Metal renderer, inside a Swift and AppKit shell that adds features other terminals lack: a Vietnamese Telex input method, an agent dash...