Loading...
Loading...
Cave Agent: Stateful runtime management for LLM agents—inject, manipulate, and retrieve Python objects across turns. 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 Cave Agent. This is an automatic list. We have not written a researched verdict for Cave Agent 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 RL Bridge for LLM-based Agent Applications.
AReaL is open source reinforcement learning infrastructure for training large language models and the agents built on them. It connects foundation model training with agent based applications, so teams can post train models on agentic tasks such as multi turn tool use and long horizon reasoning with reinforcement learn...
Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser
BrowserAI is an open source JavaScript library for running small language models locally inside a web browser. It uses WebGPU and WebAssembly to load and run models on the user's own device, so an application can generate text, hold a chat or process speech without calling a cloud API, holding API keys or maintaining s...
A blazingly fast, privacy first & OPEN AI Chat Interface
Faster Chat is an open source chat interface for large language models that runs on the user's own machine or server. Conversations are stored locally in the browser through IndexedDB, with optional SQLite sync, so chat history never has to leave the device. It connects to local inference servers such as Ollama or LM S...
An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.
MatrixHub is an open source, self hosted registry for AI models, built for enterprise inference at large scale. It is positioned as a drop in private replacement for Hugging Face, and the site compares its relationship to Hugging Face with the one between Harbor and Docker Hub. It is designed to speed up vLLM and SGLan...
An open coding agent for your terminal, built by a community collective rather than a company.
Nanocoder is an open coding agent for the terminal, built by the Nano Collective, a community group that develops AI tooling not for profit. It works with local models through Ollama, llama.cpp, LM Studio and similar servers, and with hosted providers such as OpenRouter, OpenAI, Anthropic Claude, Google Gemini, Mistral...
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
SkillsVote is a skills service for AI coding agents. It indexes a very large collection of agent skills and lets an agent, or the developer running it, search that collection and receive recommendations for the task at hand. It is built to work with clients such as Claude Code, Codex and Cursor. The core features foll...