#llm

Portable, provider-neutral model invocation contracts, adapters, and conformance tools

A schema-first GraphQL MCP server that avoids the 1MB introspection limit via typeNames/typeDepth scoping — built for federated topologies.

AI Agent SDK designed for Go developers

A minimal, extensible agent library for Python.

Pi extension for SpaceXAI Grok/X.com Subscriptions

No repository description published.

A minimalist, LLM-powered AI translation & dictionary CLI tool for developers.

No repository description published.

Context as a Service. One context for every AI tool. Self-hosted, vendor-neutral, RBAC-ready. 1-minute install.

A Go engine for talking to LLMs that doesn't give a shit which one. Streaming, tool loops, history that actually fits the context window, retries that don't repeat themselves, and typed structured output. Swap OpenAI for Anthropic by changing one line. Library, not a framework: you own the loop.

Model-agnostic multi-modality generation server with plugin discovery: OpenAI-compatible TTS, embeddings, and image generation. Drop a Python file in ~/.muse/models/ to add a backend.

Pi slash command for inspecting and changing session and default thinking effort

An operating system for AI agents — Unix philosophy: process, VFS, syscalls. Go 1.26.

AI SDK provider for Mixlayer — the fully oxidized inference API

A verifiable memory layer for language models — facts in a graph, every claim with its source.

A self-hosted authenticating inference relay that fronts agent CLIs

A SQLite mailbox for local LLM agents — one HTTP API, an ActivityStreams messaging model, and a local stdio MCP server so AI coding agents can message each other. No external services.

Controls for .NET MAUI & Blazor

A Model Context Protocol (MCP) server that lets LLMs and AI assistants send push notifications to a Gotify server.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

A high-performance, enterprise-grade large model gateway dedicated console designed for the power ecology of large models (LLM) with rich traffic governance strategies.

🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.

No repository description published.

all the crons in the world

AI security gateway that inspects every prompt and response through a multi-layer detection pipeline - enforcing ALLOW, BLOCK, or SANITIZE before anything reaches the model.

Official Go SDK for the Webclaw web extraction API

MCP server for managing your Ace Data Cloud account — services, pricing, APIs, docs, balance, usage, API keys, orders and announcements.

Your personal AI partner on Windows & Linux — track and complete your goals through research, design, code, and action. Local continuity under ~/.remedy, your own model. Chat, code, computer use, browser rail. · PyPI remedy-ai.

AI knowledge workbench for Neovim.

Open-source Vibe Testing suite: an MCP server for the coding agent you already run, a VS Code review cockpit, and CI. Your agent explores your app and crystallizes each flow into a plain @playwright/test spec you own — record == replay, runs in CI with zero AI.