AI 资讯
Enterprise MCP Gateway Solutions: Providers, Alternatives, and Cost 💎
Your company uses six different AI providers. OpenAI for ChatGPT, Anthropic for Claude and Groq for speed critical inference. Each one has different API formats. Different authentication models. Different rate limits and costs. Different failure modes. Your application code has to know about all of them. Your security team has to audit requests across all of them. Your finance team has to track costs across all of them. Your compliance team has to ensure governance across all of them. Bifrost Gateway solves this by doing what HTTP gateways have done for decades: centralizing control . But for AI. 👀 What is an MCP gateway? Model Context Protocol (MCP) is an open standard that lets AI models discover and execute external tools at runtime filesystems, web search, databases, ticketing systems, and custom business logic instead of being limited to text generation. An MCP gateway sits between your applications (or external MCP clients like Claude Desktop and Cursor) and the upstream MCP servers. Instead of each client maintaining its own connections, credentials, and tool lists, the gateway: Aggregates tools from multiple MCP servers into one registry Applies governance : authentication, tool filtering, budgets, and rate limits Exposes a single endpoint that external MCP clients can connect to In Bifrost, this pattern is implemented in two complementary roles: Role What it does MCP Client Connects to external MCP servers via STDIO, HTTP, or SSE MCP Server (Gateway) Exposes aggregated tools at /mcp for Claude Desktop, Cursor, and other MCP-compatible clients Bifrost is both an AI gateway (routing LLM traffic to 20+ providers) and an MCP gateway (connecting to and exposing tool servers). The open-source gateway covers virtual keys, budgets, rate limits, routing, and MCP tool filtering. Bifrost Enterprise adds RBAC, SSO, audit logs, MCP Tool Groups, guardrails, clustering, and in-VPC deployment options. ⚙️ How does an MCP gateway work? Connection layer Each upstream MCP serv
AI 资讯
IEC 104 Before the Wire: Understanding Its Architecture, Framing, and Security Boundaries
By RUGERO Tesla ( @404Saint ). IEC 60870-5-104 (IEC 104) is the TCP/IP-based member of the IEC 60870-5 telecontrol family. It was designed to carry SCADA telemetry and control information across packet-switched networks, particularly within electrical power systems. Before getting into raw packets, it is worth understanding how IEC 104 is structured, how its communication state is maintained, and where its security boundaries actually exist. This is the map before we meet the protocol on the wire. Protocol Stack IEC 104 operates over TCP, commonly using port 2404 . Two protocol components are particularly important: APCI : Application Protocol Control Information ASDU : Application Service Data Unit The APCI handles framing, sequencing, acknowledgments, and connection control. The ASDU carries the actual telecontrol information. +-------------------------------------------------------------+ | ASDU | | Type ID | VSQ | COT | CA | IOA | Information Objects | +-------------------------------------------------------------+ | APCI | | 0x68 | Length | Control 1 | Control 2 | Control 3 | Ctrl 4 | +-------------------------------------------------------------+ | TCP / IP | +-------------------------------------------------------------+ Every APDU begins with the 0x68 start byte, followed by a length field and four control bytes. The length represents the bytes following the length field, including the four control bytes and, when present, the ASDU. That fixed structure is the starting point for understanding IEC 104 traffic. I, S, and U Formats IEC 104 defines three APDU formats. I-Format: → I-format frames carry application information and therefore contain an ASDU. They also carry two sequence numbers: N(S) : send sequence number N(R) : receive sequence number These allow communicating stations to maintain ordered transmission and acknowledgment state. S-Format: → S-format frames are supervisory frames. They do not carry an ASDU. Their purpose is to communicate receive ac
AI 资讯
It’s Greg Brockman’s OpenAI now
OpenAI has had a hell of a year. The company spent months battling former co-founder Elon Musk in a sensational jury trial, was hit with a high-profile trade secrets lawsuit from Apple, and faced widespread scrutiny after an unreleased model hacked another AI company. As it prepares for an IPO, a steady string of executives […]
AI 资讯
Welcome to the AI crisis in math
Today on Decoder, I’m talking with Robert Hart, The Verge’s London-based AI reporter, about what AI is doing to the field of mathematics and the existential crisis many lead mathematicians are having about it. OpenAI just published a set of solutions to longstanding problems in math that went off like a bombshell in the field. […]
开源项目
🔥 anomalyco / models.dev - An open-source database of AI models.
GitHub热门项目 | An open-source database of AI models. | Stars: 6,498 | 139 stars this week | 语言: TypeScript
开源项目
🔥 firecracker-microvm / firecracker - Secure and fast microVMs for serverless computing.
GitHub热门项目 | Secure and fast microVMs for serverless computing. | Stars: 36,167 | 31 stars today | 语言: Rust
开源项目
🔥 WecomTeam / wecom-cli - 企业微信开放平台命令行工具 — 让人类和 AI Agent 都能在终端中操作企业微信
GitHub热门项目 | 企业微信开放平台命令行工具 — 让人类和 AI Agent 都能在终端中操作企业微信 | Stars: 2,898 | 34 stars today | 语言: Rust
开源项目
🔥 cline / cline - Autonomous coding agent as an SDK, IDE extension, or CLI ass
GitHub热门项目 | Autonomous coding agent as an SDK, IDE extension, or CLI assistant. | Stars: 66,533 | 79 stars today | 语言: TypeScript
开源项目
🔥 AdguardTeam / AdGuardHome - Network-wide ads & trackers blocking DNS server
GitHub热门项目 | Network-wide ads & trackers blocking DNS server | Stars: 36,246 | 30 stars today | 语言: TypeScript
开源项目
🔥 apache / maka - Apache Maka (Incubating) is a local-first AI agent workspace
GitHub热门项目 | Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log. | Stars: 1,781 | 364 stars today | 语言: TypeScript
开源项目
🔥 magnitudedev / magnitude - Open source agent with local models built in. Fully private
GitHub热门项目 | Open source agent with local models built in. Fully private and offline. Works out of the box on any hardware. | Stars: 1,430 | 134 stars today | 语言: TypeScript
开源项目
🔥 chuspeeism / dashi-ppt-skill - An AI-agent skill that generates browser-editable presentati
GitHub热门项目 | An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX. | Stars: 5,764 | 298 stars today | 语言: JavaScript
开源项目
🔥 docling-project / docling - Get your documents ready for gen AI
GitHub热门项目 | Get your documents ready for gen AI | Stars: 65,286 | 145 stars today | 语言: Python
开源项目
🔥 ATH-MaaS / Pixelle-Video - 🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
GitHub热门项目 | 🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine | Stars: 27,091 | 125 stars today | 语言: Python
开源项目
🔥 Osmantic / ODS - Turn your PC, Mac, or Linux box into an AI server. LLM infer
GitHub热门项目 | Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. | Stars: 4,561 | 168 stars today | 语言: Python
开源项目
🔥 Tencent / AI-Infra-Guard - A full-stack AI Red Teaming platform securing AI ecosystems
GitHub热门项目 | A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation. | Stars: 4,773 | 28 stars today | 语言: Python
开源项目
🔥 agent-substrate / substrate - Agent Substrate: the core system
GitHub热门项目 | Agent Substrate: the core system | Stars: 1,292 | 26 stars today | 语言: Go
开源项目
🔥 modular / modular - The Modular Platform (includes MAX & Mojo)
GitHub热门项目 | The Modular Platform (includes MAX & Mojo) | Stars: 27,537 | 340 stars today | 语言: Mojo
AI 资讯
Pi4J LED Playground: A Community Resource for Learning Hardware Programming with Java
One of the best moments when learning electronics is seeing your first LED blink. It's a simple experiment, but it represents the bridge between software and the physical world. With Java and Pi4J, that first step is already well documented. But what happens after the first LED? How do you experiment with different animations, colours, brightness levels, or GPIO configurations without repeatedly rewriting the same code? That question led to the creation of the Pi4J LED Playground . 👉 https://igfasouza.github.io/pi4j-led-playground/ Why another example? Pi4J already provides excellent examples and documentation for getting started with Raspberry Pi hardware. The project itself encourages community-driven examples and implementations, recognising that the ecosystem grows through shared contributions. The goal of the LED Playground is not to replace those examples. Instead, it provides an interactive environment where developers can quickly experiment with LED behaviours while learning how Pi4J works. Think of it as a sandbox where changing a few lines of code immediately produces visible results. Built by the community, for the community This project started as a personal experiment while exploring Pi4J. Very quickly it became clear that the playground could be useful for others who are starting their journey with Java on Raspberry Pi. Instead of keeping it as a private repository, it was published as an open community resource where anyone can: 1. learn from the source code; 2. suggest improvements; 3. report issues; 4. contribute new LED effects; 5. help improve the documentation; Open source projects become stronger when many people contribute different ideas, and Pi4J itself has grown thanks to this collaborative model. What can you do? The playground demonstrates common LED operations such as: turning LEDs on and off; blinking patterns; brightness control (where supported); experimenting with different GPIO configurations; creating reusable animations; Because th
开发者
I built flutter_auditor — a zero-config CLI tool to audit Flutter apps for permissions, dead assets, security risks, and package hygiene
Shipping a Flutter app without auditing native permissions, release keystores, or asset bloat? To help Flutter developers catch hidden production risks before App Store/Play Store review, I built flutter_auditor — an open-source, zero-config CLI health and security inspector for Flutter & Dart. In just one terminal command (dart run flutter_auditor), it scans your project for: 🔒 17+ Automated Audits: Hardcoded API secrets & exposed .jks keystores Missing iOS Info.plist privacy description strings Unused heavy assets & broken 2.0x/3.0x image variant paths Dangerous manifest flags (android:debuggable="true", allowed cleartext traffic) Unused & transitive package dependencies Give it a try locally on your project and let me know what audits you'd like to see next! 👇 pub.dev: https://pub.dev/packages/flutter_auditor GitHub: https://github.com/thakaredipali/flutter_auditor