Open source used to cost maintainers their time. It still does — but a second bill arrived, paid in inference: the agents, the evals, the models these tools call every day. This is a living directory of 64 open-source projects that run on compute, and the people who quietly pay for it.
We list how to support each one — their own funding, first: GitHub Sponsors, Ko-fi, Open Collective, wherever they already are. TokenTip is our point of view — the way readers can fund a maintainer's compute directly — not the only road. Support them however you can.
★ Star it on GitHub — the directory is an open, CC0 awesome-list. Know a project that runs on compute and takes funding? Send a PR.
Serve or route model calls — the maintainers here pay for GPUs or upstream API credit directly.
AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.
AirLLM 70B inference with single 4GB GPU
Harness LLMs with Multi-Agent Programming
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
Stop juggling AI accounts. Quotio is a beautiful native macOS menu bar app that unifies your Claude, Gemini, OpenAI, Qwen, and Antigravity subscriptions – with real-time quota tracking and smart auto-failover for AI coding tools like Claude Code, OpenCode, and Droid.
A Unified MCP Server Management App (MCP Manager).
Orchestrate multi-step LLM calls — every run is inference the maintainer often foots during dev and CI.
Cross-CLI skill for Obsidian: turn your vault into a living AI-first second brain across Claude Code, Codex, Gemini, OpenCode, Antigravity, Hermes, and Pi. 45 commands - self-rewriting notes, hybrid semantic search, key-less web research, /obsidian-architect codebase docs, and scheduled agents that maintain the vault while you sleep.
The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. Also checkout AgenticSeek successor 3Toks! https://github.com/Fosowl/3toks
#1 Persistent memory for AI coding agents based on real-world benchmarks
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
Autonomous Hacking Agent for Red Team
Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.
The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that interact with your data and UI.
AI that writes, reviews, or drives your code — heavy per-invocation model spend.
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
Never stop coding. Free MIT AI gateway: one endpoint, 268+ providers (50+ free), 500+ models — Claude, GPT, Gemini, Kimi K3, GLM, DeepSeek. Works with Claude Code, Codex, Cursor, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, multimodal, Desktop/PWA. Built by 500+ contributors.
🚀 Beautiful highly customizable statusline for Claude Code CLI with powerline support, themes, and more.
A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
🦞 OpenClaw (Clawdbot/Moltbot) 汉化版 - 开源个人 AI 助手中文版 | Claude/ChatGPT LLM 接入 | WhatsApp/Telegram/Discord 多平台 | 每小时自动同步 | CLI + Dashboard 全中文 | 全流程搭建教程，以及排错指南！
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
Typescript/React Library for AI Chat💬🚀
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Embed, store, and retrieve for LLMs — embedding and query calls add up.
RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
Python scraper based on AI
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
A vector index built on TurboQuant, written in Rust with Python bindings
🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/
Neo4j graph construction from unstructured data using LLMs
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon Bedrock, Anthropic, HuggingFace, OpenAI, Meta, AI21, Cohere, Mistral) using AWS CDK on AWS
Tiny AI for tiny devices
Hypernetworks that update LLMs to remember factual information
Conversational UIs and assistants — user-facing inference at scale.
Fully customizable AI chatbot component for your website
🧠 Leon is your open-source personal assistant.
💬 Typebot is a powerful chatbot builder that you can self-host.
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
Venom is a high-performance system developed with JavaScript to create a bot for WhatsApp, support for creating any interaction, such as customer service, media sending, sentence recognition based on artificial intelligence and all types of design architecture for WhatsApp.
跨平台 Python 异步聊天机器人框架 / Asynchronous multi-platform chatbot framework written in Python
🍀 A cross-platform instant messaging desktop application with exceptional performance built on Rust + Vue3, compatible with Windows, macOS, Linux, Android, and iOS（一款基于Rust+Vue3极致性能的跨平台即时通讯桌面应用，兼容Windows、MacOS、Linux、Android、IOS）
A multi-function Discord bot
.NET Client for Telegram Bot API
💬 Telegram bot with ChatGPT & Claude Python-based, using OpenAI's API.
Test, trace, and monitor model behaviour — evals are themselves inference runs.
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
Bionic is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Useful open-source tools built on top of AI inference.
Access large language models from the command-line
Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.
The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme
structured outputs for llms
Desktop app to generate 3D models from images using local AI — runs entirely on your GPU
Bindu: The identity, communication, and payments layer for AI agents.
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visualization.
Dolt – Git for Data
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
Add the badge that funds it — a reader's tip becomes the inference your project runs on, every fee shown before anyone pays.
Claim your page Read the API