Free AI Tools for LLM

Self-hosted AI notification filter for Telegram that uses LLMs to prioritize messages and send only important alerts via ntfy.

A specialized local inference engine for large language models, optimized for Apple Silicon and SSD streaming on memory-constrained systems.

Unified AI API gateway providing access to top-tier LLMs, image, video, and coding models at affordable prices.

An open-source, OpenAI-compatible LLM gateway you run yourself, providing a single endpoint for 40+ providers with virtual keys, budgets, and usage tracking.

Run any LLM locally on your Mac faster than LM Studio or Ollama, with chat, coding agents, images, video, and voice, all fully offline and open source.

A unified Python library that combines MCP servers, agent skills, custom functions, and HTTP endpoints into a single tool set for building AI agents with any LLM.

Lightning Rod trains small AI models on messy real-world data to predict outcomes in sports, politics, finance, and more, offering a cost-effective alternative to frontier models.

A secure, portable Bash-first CLI wrapper for Groq's OpenAI-compatible API to interact with large language models from the terminal.

A reference implementation using Linux Pressure Stall Information to trim LLM KV cache under memory pressure.

Beautiful, AI-native markdown editor and LLM Wiki for creating and managing knowledge bases with AI assistance.

Self-hosted AI notification filter for Telegram that uses LLMs to prioritize messages and send only important alerts via ntfy.

A specialized local inference engine for large language models, optimized for Apple Silicon and SSD streaming on memory-constrained systems.

Unified AI API gateway providing access to top-tier LLMs, image, video, and coding models at affordable prices.

An open-source, OpenAI-compatible LLM gateway you run yourself, providing a single endpoint for 40+ providers with virtual keys, budgets, and usage tracking.

Run any LLM locally on your Mac faster than LM Studio or Ollama, with chat, coding agents, images, video, and voice, all fully offline and open source.

A unified Python library that combines MCP servers, agent skills, custom functions, and HTTP endpoints into a single tool set for building AI agents with any LLM.

Lightning Rod trains small AI models on messy real-world data to predict outcomes in sports, politics, finance, and more, offering a cost-effective alternative to frontier models.

A secure, portable Bash-first CLI wrapper for Groq's OpenAI-compatible API to interact with large language models from the terminal.

A reference implementation using Linux Pressure Stall Information to trim LLM KV cache under memory pressure.

Beautiful, AI-native markdown editor and LLM Wiki for creating and managing knowledge bases with AI assistance.

A CLI tool that converts web pages into compact text accessibility trees for LLMs to automate browser interactions efficiently.

Graphsignal is a production-scale inference profiling platform that helps engineers optimize AI performance across models, engines, GPUs, and other accelerators.

Claw Patrol is an open-source security firewall for AI agents that guards credentials, gates actions, and logs all traffic.

ctx is a context-aware recommendation engine that dynamically selects the best skills, agents, and MCPs for your current coding task using a massive knowledge graph.

Powabase is an all-in-one development platform for AI apps with built-in Postgres, RAG, agents, and drag-and-drop workflows, optimized for AI coding agents.

Meta's AI hub for Meta AI products, Vibes, AI Studio, and research on models, tools, and superintelligence.

Kie.ai is a unified AI API platform for accessing video, image, audio, and LLM models through one integration with transparent pricing.

ApX Machine Learning is an educational platform for learning machine learning, LLMs, and practical AI engineering through courses, guides, tools, and model rankings.

Jan is an open-source, local-first AI chat app that works as a private ChatGPT replacement.

Aider is a terminal-based AI pair programming tool that helps you build and edit code with LLMs.

Atlas Cloud is a full-modal AI inference platform offering one API for chat, image, video, and audio models.

A browser-based tool that estimates which local AI models your machine can run based on device capabilities.

Anthropic is an AI company offering Claude models, developer tools, and safety-focused research and products.