Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat — with any LLM provider.

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

PipesHub is a fully extensible and explainable workplace AI platform for enterprise search and workflow automation

The best-benchmarked open-source AI memory system. And it's free.

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

RAG-Mail is a thread-aware email processing system that semantically indexes conversations and attachments for context-rich retrieval using RAG.

Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.

Browser extension for AnythingLLM Docker & Desktop application

AnythingLLM Embed widget submodule for the main AnythingLLM application

Documentation of AnythingLLM by Mintplex Labs Inc.

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.

LLM inference in C/C++

Simple API to get the "true" odds for a single bet or given set of events in a parlay.

[ARCHIVED 2026-04-20 — stampby retired; see bong-water-water-bong] no longer actively developed

Agno turns agents into production software. Build in any framework. Run as a service. Ship to real users.

17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.

Control Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks, Search & Drive with AI - Comprehensive Google Workspace / G Suite MCP Server & CLI Tool

CodeNomad: The command center that puts AI coding on steroids.

From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration with multi-model teams and parallel execution. Three runtime dependencies.

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.

FUSE filesystem over Google Drive

OneDrive Client for Linux

Open-source implementation of Google's TurboQuant (ICLR 2026) — KV cache compression to 2.5–4 bits with near-zero quality loss. 3.8–5.7x memory reduction on Mistral-7B, no training required.

ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal. China website is https:/…

"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"

Public repository for Agent Skills

Skills and channel integrations for nanotars

🦖 ClawBio — The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Built on OpenClaw.