Search

Test local AI models like a scientist: ground-truth benchmarks for LM Studio + cloud LLMs. Vision/tools/reasoning/security, N=3 trials, SHA3-sealed evidence, live Rust+SSE dashboard. No marketing numbers — your hardware, your proof.

Nexus is an autonomous CLI coding agent powered by LangGraph and MCP. It plans complex tasks, persists context via SQLite, and securely orchestrates tools. Features specialized Architect/Code modes, real-time metrics, and human-in-the-loop safety for production workflows.

OpenClaw plugin that gives AI agents full Grafana access — 17 composable tools for PromQL/LogQL/TraceQL queries, dashboard creation, alerting, SRE investigation (multi-signal triage, anomaly detection, alert fatigue analysis), security monitoring (prompt

Unified web search + content extraction extension for pi with 12 backends (DuckDuckGo, Jina AI, Tavily, Brave, Exa, Serper, Firecrawl, Marginalia, LangSearch, WebSearchAPI, Perplexity Sonar, SearXNG). Auto-fallback, RRF combine mode, web_read tool, secure

From one prompt to a finished product — fully autonomous. NexGSD turns any AI coding tool into a complete project engine: auto-plans, remembers across sessions, builds end-to-end, audits security & performance, deploys to production. 18 agents + 39 workfl

A specialized tool designed for AI agents to securely move files from their private, isolated workspaces to their owners. It provides agents with a simple REST API to upload results and generates clean, public URLs for owners to download those files instantly via a premium web dashboard.

From one prompt to a finished product — fully autonomous. Auto-plans, remembers across sessions (persistent context), builds end-to-end, audits security & performance, deploys. 18 agents + 39 workflows for Claude Code, ChatGPT, Copilot, Codex, Cursor. Built by NexVar.

Agent Hub is an AI orchestration platform that transforms how developers and DevOps engineers interact with their toolchain. Built on the cutting-edge Model Context Protocol (MCP), it provides intelligent automation through specialized AI agents, seamlessly integrating with GitHub, Azure, security tools, and data processing

Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP keyboard control, and a confirm-before-act security model. BYOK across 8 LLM providers (Claude, GPT, Gemini, DeepSeek + 4 China-region).

A .NET 9 multi-agent platform where AI agents (Silicon Beings) self-evolve via Roslyn dynamic compilation. Features tick-driven time-sliced scheduling, executor-permission security, and zero-database file storage. Cross-platform, single-file deployable.

Plexir is a modular, keyboard-centric AI terminal workspace that combines multi-provider LLM orchestration, persistent Docker sandboxing, and advanced agentic tools into a professional TUI. Designed for developers who live in the CLI, it offers a resilient and secure environment for coding, information gathering, and system automation.

Fail-closed guard for AI agent tool calls — preflight contract changes before they execute. Security core frozen (agent-guard-api v1.0); v1.1 adds client-side enforcement: receipt→envelope binding, decision↔action reconciliation, safe_for_agent + degraded

Game Enterprise R&D AI Agent Control Plane — 25+ LLM providers, five-layer security, multi-tenant isolation, game-specific tools with hallucination detection | 面向游戏企业研发的 AI Agent 控制平面 — 25+ LLM 供应商、五层安全、多租户隔离、游戏专属工具 + 幻觉检测

Stateful Telegram AI Assistant powered by Gemini 2.5 Flash & LangChain. Securely manages Google Calendar (CRUD) via custom tools. Features SQL-backed conversational memory for dynamic chats, zero-downtime error handling, strict access control, and cloud-ready architecture.

Salesforce AI Assistant — An intelligent, LLM-powered assistant that enables natural language interaction with Salesforce metadata and data. Built with LangGraph for agent workflows, Weaviate for semantic search, MongoDB for short-term memory, and high-quality embedding models. Supports SOQL generation, metadata exploration, and secure multi-org

Agent orchestration platform & operating-system-workspace. It powers Agents, mini apps, documents, CRM, CMS, chat, workflows, tools, and secure browser access across desktop, mobile, and web using skills and MCP. Built on Aurora Cloud, it comes bundled with production ready agents, agentic runtime, MCP + MORE.

Minimal, secure Google Workspace MCP server — 43 tools across 10 services (Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Tasks, Chat, Meet). Only official Google libraries, zero third-party wrappers, fully auditable. Works with Claude Code, Kiro, Cursor, Windsurf, Codex.

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.

Aegis Agent Framework is an engineering-grade AI agent runtime built on Python 3.11+ and pydantic v2. Designed with an "offline-first" and secure-isolation philosophy, it features rigorous architectural boundaries and a 5-slot context engineering model. With out-of-the-box support for 11 model adapters and native integration with MCP and A2A protoc