#llm

Guardrails for coding agents: what's left on every AI plan, in-session nudges, and limits your agents respect. Local-first, ~90 providers.

The CLI-native orchestrator for AI agent workflows. Run Claude Code, Codex, Gemini CLI & Kimi Code from declarative YAML. Because the terminal is where real work happens.

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents

MCP server for Outlook email, calendar, and contacts — let your AI assistant manage your inbox directly from the conversation.

🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without native web access. Free, no signup, no API key. Ask the web or X, get structured JSON evidence. | 🥇 全网最强的 DeepSeek Harness 免费联网搜索插件，免费免注册免 API key。为不能联网的模型补上搜索，问网页或 X，拿回结构化 JSON 证据（搜索、抓取、引用）。

The open-source, local-first alternative to Claude Code & Claude Cowork. Run multi-agent AI workflows locally with total privacy and zero cloud lock-in.

Natural voice conversations with Claude Code

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

Autonomous AI agent for Home Assistant with multi-model routing, persistent memory, and an OpenAI-compatible API

Run AI models on Apple Silicon and Raspberry Pi

A Model Context Protocol (MCP) server that provides secure integration with Google Drive, Docs, Sheets, Slides and Calendar. It allows Claude Desktop and other MCP clients to manage files in Google Drive through a standardized interface.

Shared memory for AI agents

Official Node.js, Python, and Go SDKs plus the primitive CLI for Primitive — email infrastructure for AI agents. Generated from the OpenAPI spec.

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.

A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.

Unofficial Ruby SDK for Claude Agent

TypeScript / Node libraries

AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security governance, and team collaboration

Parse bank statements — CAMT/ISO 20022, PAIN.001, CSV (EN/DE/FR/ES), OFX/QFX, MT940, PDFs (digital + scanned) — into unified Transactions. Deterministic parsers, LLM/vision fallback, Golden Rule + multi-currency + continuity verification, page provenance, dedupe, review, accuracy evals, CLI + REST API. 100% test coverage.

Composable Pi coding agent with MCP, LSP, agent chains, prompt presets, and local eval telemetry

Foundational low latency web data collecting in Rust

One-stop shop for building AI-powered products and businesses with Stripe.

C# SDK for the Anthropic API -- Claude chat completions, tool calling, and vision

C# SDK for the Hugging Face API -- inference, embeddings, and model hub

C# SDK based on official OpenAI OpenAPI specification

Minimum viable chat components

Pipeline engine for multi-agent LLM workflows, with Dippin pipelines, parallel agents, and a terminal dashboard.

Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments.

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics