#llm

Zero-config entity resolution feeding a durable identity layer: messy records from any source become stable golden entities, a Customer 360 with provenance, merge/split and audit. Fellegi-Sunter beats hand-tuned Splink. Arrow-native/Rust, 250M rows in 11.2 min. Python + edge TypeScript (WASM), SQL-native in Postgres & DuckDB, 97 MCP tools + REST.

The open-source hub to build & deploy GPT/LLM Agents ⚡️

OpenZIM MCP is a modern, secure, and high-performance MCP (Model Context Protocol) server that enables AI models to access and search ZIM format knowledge bases offline.

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code

Unified AI Gateway for 30+ LLMs (OpenAI, Anthropic, Bedrock, Azure etc) with Caching, Guardrails, A/B test & cost controls. Go-native Fastest & Scalable AI Gateway LiteLLM & Kong AI Gateway alternative.

A minimal, fast agent harness for the terminal. One ~12 MB native binary that runs anywhere, with an open, extensible architecture.

☁️ The fastest HTML to markdown convertor on GitHub. Optimized for LLMs and supports streaming.

Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

Run AI coding agents in sandboxed CI environments

An official Qase MCP server

A modular MCP server that provides commonly used developer tools for AI coding agents

Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.

🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.

Full-stack framework for building AI apps and agents with TypeScript and React. Works with Node.js, Deno, and Bun.

The complete toolkit for building AI agents in JavaScript. Lightweight core, React & Terminal UIs, autonomous runtime, tools, skills, memory, RAG and observability. Plug-and-play from chat UI to full agents.

Hundreds of models & providers. One command to find what runs on your hardware.

Real-time monitoring, slowlog analysis, and audit trails for Valkey and Redis

多平台模型接入，可扩展，多种输出格式，提供大语言模型聊天服务的插件 | A bot plugin for LLM chat with multi-model integration, extensibility, and various output formats

Fast, flexible LLM inference

Security-first, self-hosted AI agents - isolation you can prove, not just promise.

Zero-Config Code Flow for Claude code & Codex

Safe DOCX suite: docx-primitives, docx-comparison, safe-docx MCP server

A provider agnostic PHP AI client SDK to communicate with any generative AI models of various capabilities using a uniform API.

Open-source context retrieval layer for AI agents

Type-safe, real-time backend framework on your own Cloudflare account — Workers, Durable Objects, D1, R2, Queues. Convex-style DX, Vite-first.

The pretty much "official" DSPy framework for Typescript

The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

docx ↔ LLM translator. Projects .docx to Markdown for editing. Projects edits back to OOXML as tracked changes. Python and Node.js implementations.