60 skills found · Page 1 of 2
Atmosphere / AtmosphereReal-time transport layer for Java AI agents. Build once with @Agent — deliver over WebSocket, SSE, gRPC, MCP, A2A, AG-UI, or any transport. Works with Spring AI, LangChain4j, Google ADK, Embabel, Koog or the built-in OpenAI-compatible client.
Exim / EximExim Mail Transport Agent - source, testsuite and documentation
matsim-org / Matsim LibsMulti-Agent Transport Simulation
corecode / DmaThe DragonFly Mail Agent, a small Mail Transport Agent (MTA), designed for home and office use.
eqasim-org / Eqasim FranceAn open synthetic population of Île-de-France for agent-based transport simulation
narrative-first / Narrative Context ProtocolA standardized, application-agnostic narrative structure schema designed for reliably transporting authorial intent across multi-agentic narrative systems.
wingify / AgentredrabbitTransport agent that moves data from Redis to RabbitMQ
telefonicaid / Iotagent JsonIoT Agent for a JSON and NGSIv2 based protocols with HTTP, MQTT and AMQP transports
firnsan / Shell AgentAgent program installed on remote host, help you to execute shell command on the remote host via HTTP. Also help to transport file to/from remote host.
yoloshii / MCP Code Execution EnhancedEnhanced MCP code execution. Agent framework-agnostic (optimized for Claude Code). Skills framework (99.6% token reduction), multi-transport, sandboxing
telefonicaid / Iotagent UlIoT Agent for a UltraLight 2.0 based protocol (with HTTP, MQTT and AMQP transports)
vuquangchien2208 / VQC# Loon全局配置 by nzw9314 # YouTube去广告请删除hostname 后的.bak # GitHub主页(https://github.com/nzw9314) # TG通知频道 (https://t.me/nzw9314News) [General] ipv6 = false skip-proxy = 10.0.0.0/8,127.0.0.0/8,169.254.0.0/16,192.0.2.0/24,192.168.0.0/16,198.51.100.0/24,224.0.0.0/4,*.local,localhostlocal bypass-tun = 10.0.0.0/8,127.0.0.0/8,169.254.0.0/16,192.0.2.0/24,192.168.0.0/16,198.51.100.0/24,224.0.0.0/4 # [DNS] => DNS 服务器 dns-server = system,1.2.4.8,119.29.29.29,223.5.5.5 allow-udp-proxy = true host = 127.0.0.1 [Remote Proxy] # 订阅节点 # 别名 = 订阅URL ✈️机场1 = https://example/server-complete.txt ✈️机场2 = https://example2/server-complete.txt [Remote Filter] # 筛选订阅节点,筛选后的结果可加入到策略组中,目前支持三种筛选方式 # NodeSelect: 使用在UI上选择的节点。 # NameKeyword: 根据提供的关键词对订阅中所有节点的名称进行筛选,使用筛选后的节点。 # NameRegex: 根据提供的正则表达式对订阅中所有节点的名称进行筛选,使用筛选后的节点。 𝐏𝐚𝐲𝐏𝐚𝐥 = NodeSelect,✈️机场1,✈️机场2 𝐍𝐞𝐭𝐟𝐥𝐢𝐱 = NameKeyword,✈️机场1,✈️机场2, FilterKey = Netflix 🇭🇰香港 = NameRegex,✈️机场1,✈️机场2, FilterKey = 香港|HK 🇯🇵日本 = NameRegex,✈️机场1,✈️机场2, FilterKey = 日本|JP 🇰🇷韩国 = NameRegex,✈️机场1,✈️机场2, FilterKey = 韩国|KR 🇺🇸美国 = NameRegex,✈️机场1,✈️机场2, FilterKey = 美国|US Other = NameRegex,✈️机场1,✈️机场2, FilterKey = ^(?!.*(HK|JP|US|KR|香港|日本|韩国|美国)).*$ [Proxy] # 本地节点 # 内置 DIRECT、REJECT 策略 # 节点名称 = 协议,服务器地址,服务器端口,加密协议,密码, 1 = Shadowsocks,1.2.3.4,443,aes-128-gcm,"”password“" 2 = Shadowsocks,1.2.3.4,443,aes-128-gcm,"”password“" 3 = ShadowsocksR,1.2.3.4,443,aes-256-cfb,"”password“",auth_aes128_md5,{},tls1.2_ticket_auth,{} 4 = ShadowsocksR,1.2.3.4,10076,aes-128-cfb,"”password“",auth_aes128_md5,{},tls1.2_ticket_auth,{} # vmess # 节点名称 = 协议,服务器地址,端口,加密方式,UUID,传输方式:(tcp/ws),path:websocket握手header中的path,host:websocket握手header中的path,over-tls:是否tls,tls-name:远端w服务器域名,skip-cert-verify:是否跳过证书校验(默认否) #5 = vmess, 1.2.3.4, 10086, aes-128-gcm,”uuid“,transport:ws,path:/,host:icloud.com,over-tls:true,tls-name:youtTlsServerName.com,skip-cert-verify:false # 解锁网易云音乐灰色歌曲 🎧 = http,106.52.127.72,19951 [Proxy Group] # 策略组 # 节点选项 🕹𝐅𝐢𝐧𝐚𝐥 = select,🔰𝐏𝐫𝐨𝐱𝐲,🎯𝐃𝐢𝐫𝐞𝐜𝐭 🔰𝐏𝐫𝐨𝐱𝐲 = select,♻️𝐀𝐮𝐭𝐨,🌀𝐒𝐞𝐥𝐞𝐜𝐭,🔴𝐅𝐚𝐥𝐥𝐛𝐚𝐜𝐤 # url-test模式,给提供的url发出http header请求,根据返回结果,选择测速最快的节点,默认间隔600s,测速超时时间5s,为了避免资源浪费,建议节点数不要过多,只支持单个节点和远端节点,其他会被忽略 ♻️𝐀𝐮𝐭𝐨 = url-test,🇭🇰香港,🇯🇵日本,🇰🇷韩国,🇺🇸美国,url = http://bing.com/,interval = 600 # select模式,手动选择模式 🌀𝐒𝐞𝐥𝐞𝐜𝐭 = select,🇭🇰香港,🇯🇵日本,🇰🇷韩国,🇺🇸美国 # fallback模式,和url-test类似,不同的是会根据顺序返回第一个可用的节点,为了避免资源浪费,建议节点数不要过多,只支持单个节点和远端节点,其他会被忽略 🔴𝐅𝐚𝐥𝐥𝐛𝐚𝐜𝐤 = fallback,🇭🇰香港,🇯🇵日本,🇰🇷韩国,🇺🇸美国,REJECT,url = http://bing.com/,interval = 600 🎵𝐓𝐢𝐤𝐓𝐨𝐤 = select,🔰𝐏𝐫𝐨𝐱𝐲,🎯𝐃𝐢𝐫𝐞𝐜𝐭 🖥𝐍𝐞𝐭𝐟𝐥𝐢𝐱 = select,𝐍𝐞𝐭𝐟𝐥𝐢𝐱,🎯𝐃𝐢𝐫𝐞𝐜𝐭 💳𝐏𝐚𝐲𝐏𝐚𝐥 = select,𝐏𝐚𝐲𝐏𝐚𝐥,🎯𝐃𝐢𝐫𝐞𝐜𝐭 📱𝐓𝐞𝐥𝐞𝐠𝐫𝐚𝐦 = select,🔰𝐏𝐫𝐨𝐱𝐲,🎯𝐃𝐢𝐫𝐞𝐜𝐭 🎬𝐘𝐨𝐮𝐓𝐮𝐛𝐞 = select,🔰𝐏𝐫𝐨𝐱𝐲,🎯𝐃𝐢𝐫𝐞𝐜𝐭 🔞𝐏𝐨𝐫𝐧𝐇𝐮𝐛 = select,🔰𝐏𝐫𝐨𝐱𝐲,🎯𝐃𝐢𝐫𝐞𝐜𝐭 # 🔓网易云音乐灰色歌曲,需要节点支持解锁 🎧𝐍𝐞𝐭𝐞𝐚𝐬𝐞𝐌𝐮𝐬𝐢𝐜 = select,🎯𝐃𝐢𝐫𝐞𝐜𝐭,🎧,🔰𝐏𝐫𝐨𝐱𝐲 # 网络测速 🚀𝐒𝐩𝐞𝐞𝐝𝐓𝐞𝐬𝐭 = select,🔰𝐏𝐫𝐨𝐱𝐲,🎯𝐃𝐢𝐫𝐞𝐜𝐭 # 苹果服务 🍎𝐀𝐩𝐩𝐥𝐞 = select,🎯𝐃𝐢𝐫𝐞𝐜𝐭,🔰𝐏𝐫𝐨𝐱𝐲 # 白名单模式 PROXY,黑名单模式 DIRECT # 广告拦截 🚫𝐀𝐝 𝐁𝐥𝐨𝐜𝐤 = select,⛔️𝐑𝐞𝐣𝐞𝐜𝐭,🎯𝐃𝐢𝐫𝐞𝐜𝐭 # 直接连接 🎯𝐃𝐢𝐫𝐞𝐜𝐭 = select,DIRECT # 拦截 ⛔️𝐑𝐞𝐣𝐞𝐜𝐭 = select,REJECT # SSID # 别名 = ssid,默认 = 策略, 蜂窝 = 策略, ssid名称 = 策略 #SSID = ssid, default = PROXY, cellular = DIRECT, ”DivineEngine“ = PROXY [Rule] # 本地规则 # Type:DOMAIN-SUFFIX,DOMAIN,DOMAIN-KEYWORD,USER-AGENT,URL-REGEX,IP-CIDR # Strategy:DIRECT,Proxy,REJECT # Options:force-remote-dns(Default:false),no-resolve # 𝐍𝐞𝐭𝐞𝐚𝐬𝐞𝐌𝐮𝐬𝐢𝐜 DOMAIN-SUFFIX,music.126.net,DIRECT # GeoIP China GEOIP,CN,🎯𝐃𝐢𝐫𝐞𝐜𝐭 FINAL, 🕹𝐅𝐢𝐧𝐚𝐥 [Remote Rule] # 订阅规则 https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Liby.list,🚫𝐀𝐝 𝐁𝐥𝐨𝐜𝐤 # BlockOTA https://raw.githubusercontent.com/nzw9314/Surge/master/Ruleset/BlockOTA.list,🚫𝐀𝐝 𝐁𝐥𝐨𝐜𝐤 # Antirevoke https://raw.githubusercontent.com/nzw9314/Surge/master/Ruleset/Antirevoke.list,🚫𝐀𝐝 𝐁𝐥𝐨𝐜𝐤 # > TikTok https://raw.githubusercontent.com/nzw9314/Surge/master/Ruleset/TikTok.list,🎵𝐓𝐢𝐤𝐓𝐨𝐤 # > Youtube https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Sub/YouTube.list,🎬𝐘𝐨𝐮𝐓𝐮𝐛𝐞 # > Netflix https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Sub/Netflix.list,🖥𝐍𝐞𝐭𝐟𝐥𝐢𝐱 # > PronHub https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Sub/Pornhub.list,🔞𝐏𝐨𝐫𝐧𝐇𝐮𝐛 # Telegram https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Sub/Telegram.list,📱𝐓𝐞𝐥𝐞𝐠𝐫𝐚𝐦 # > PayPal https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Sub/PayPal.list,💳𝐏𝐚𝐲𝐏𝐚𝐥 # > Outlook、Gmail https://raw.githubusercontent.com/nzw9314/Surge/master/Ruleset/Mail.list,🔰𝐏𝐫𝐨𝐱𝐲 # > GoogleDrive https://raw.githubusercontent.com/nzw9314/Surge/master/Ruleset/GoogleDrive.list,🔰𝐏𝐫𝐨𝐱𝐲 # Speedtest https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Sub/Speedtest.list,🚀𝐒𝐩𝐞𝐞𝐝𝐓𝐞𝐬𝐭 # >Unlock NeteaseMusic https://raw.githubusercontent.com/nzw9314/Surge/master/Ruleset/UnlockNeteaseMusic.list,🎧𝐍𝐞𝐭𝐞𝐚𝐬𝐞𝐌𝐮𝐬𝐢𝐜 https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Apple_CDN.list,🍎𝐀𝐩𝐩𝐥𝐞 https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Apple_API.list,🍎𝐀𝐩𝐩𝐥𝐞 https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/AsianMedia.list,🎯𝐃𝐢𝐫𝐞𝐜𝐭 https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/GlobalMedia.list,🔰𝐏𝐫𝐨𝐱𝐲 https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Domestic.list,🎯𝐃𝐢𝐫𝐞𝐜𝐭 https://raw.githubusercontent.com/eHpo1/Rules/master/Surge4/Ruleset/Global.list,🔰𝐏𝐫𝐨𝐱𝐲 [URL Rewrite] # 本地重写 # > TikTok Unlock (By Choler) # 区域请修改下方国家代码,默认为日本 JP (?<=_region=)CN(?=&) JP 307 (?<=&app_version=)16..(?=.?.?&) 1 307 (?<=\?version_code=)16..(?=.?.?&) 1 307 # > 抖音 去广告&水印 # 需配合脚本使用 ^https?:\/\/[\w-]+\.amemv\.com\/aweme\/v\d\/feed\/ https://aweme.snssdk.com/aweme/v1/feed/ header ^https?:\/\/[\w-]+\.amemv\.com\/aweme\/v\d\/aweme\/post\/ https://aweme.snssdk.com/aweme/v1/aweme/post/ header ^https?:\/\/[\w-]+\.amemv\.com\/aweme\/v\d\/follow\/feed\/ https://aweme.snssdk.com/aweme/v1/follow/feed/ header ^https?:\/\/[\w-]+\.amemv\.com\/aweme\/v\d\/nearby\/feed\/ https://aweme.snssdk.com/aweme/v1/nearby/feed/ header ^https?:\/\/[\w-]+\.amemv\.com\/aweme\/v\d\/search\/item\/ https://aweme.snssdk.com/aweme/v1/search/item/ header ^https?:\/\/[\w-]+\.amemv\.com\/aweme\/v\d\/general\/search\/single\/ https://aweme.snssdk.com/aweme/v1/general/search/single/ header ^https?:\/\/[\w-]+\.amemv\.com\/aweme\/v\d\/hot/search\/video\/list\/ https://aweme.snssdk.com/aweme/v1/hot/search/video/list/ header enable = true [Remote Rewrite] #订阅重写 去广告 by eHpo # 格式:订阅url,别名(可选) https://raw.githubusercontent.com/eHpo1/Rules/master/Loon/Rewrite.conf,eHpo https://raw.githubusercontent.com/nzw9314/Loon/master/Q-Search_All_in_one.conf,Q-Search_All_in_one [Script] # 本地脚本 enable = true [Remote Script] # 远程脚本 https://raw.githubusercontent.com/nzw9314/Loon/master/Task.conf,签到 https://raw.githubusercontent.com/nzw9314/Loon/master/Script.conf,脚本 https://raw.githubusercontent.com/nzw9314/Loon/master/Cookie.conf,Cookie [MITM] enable = true hostname = *.googlevideo.com.bak skip-server-cert-verify = true ca-p12 = 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 ca-passphrase = eHpoj
eqasim-org / Eqasim JavaThe eqasim framework features an integrated transport simulation environment. It is based on the agent-based transport simulation framework MATSim with added components for simulation of discrete choice models.
qiliuchn / GatsimGATSim: Generative-Agent Transport Simulation
splunk / Splunk MCP Server2Unofficial. Splunk MCP server. Implemented in Python and TypeScript/JS. Runs searches, queries Splunk, and outputs data as JSON, CSV, or Markdown for agentic LLM workflows. Includes guardrails for input SPL validation and output sanitization. SSE/stdio transport support. Deployment options: Stdio, local HTTP (SSE), or Docker.
Lisovate / Agent WsWebSocket bridge for CLI AI agents. Stream responses from Claude Code and Codex CLI over WebSocket. A dumb pipe: no prompt engineering, no credential handling, just transport.
SudiptaSingh / Q Learning Based Smart CabProblem Statement A smart city needs smart mobility, and to achieve this objective, the travel should be made convenient through sustainable transport solutions. Transportation system all over the world is facing unprecedented challenges in the current scenario of increased population, urbanization and motorization. Farewell to all difficulties as reinforcement learning along with deep learning can now make it simpler for consumers. In this paper we have applied reinforcement learning techniques for a self-driving agent in a simplified world to aid it in effectively reaching its destinations in the allotted time. We have first investigated the environment, the agent operates in, by constructing a very basic driving implementation. Once the agent is successful at operating within the environment, we can then identify each possible state the agent can be in when considering such things as traffic lights and oncoming traffic at each intersection. With states identified, we can implement a Q-Learning algorithm for the self-driving agent to guide the agent towards its destination within the allotted time. Finally, we can improve upon the Q-Learning algorithm to find the best configuration of learning and exploration factors to ensure the self-driving agent is reaching its destinations with consistently positive results. Our aim is also to find optimum values of parameters of the fitting function alpha, gamma and epsilon, so that the agent can work in an optimized way with the most optimum parameter values. Hence, a comparative analysis has also been conducted. Methodology used The solution to the smart cab objective is deep reinforcement learning in a simulated environment. The smart cab operates in an ideal, grid-like city (similar to New York City), with roads going in the North-South and East-West directions. Other vehicles will certainly be present on the road, but there will be no pedestrians to be concerned with. At each intersection there is a traffic light that either allows traffic in the North-South direction or the East-West direction. We have assumed that the smart cab is assigned a route plan based on the passengers' starting location and destination. The route is split at each intersection into waypoints, and the smart cab, at any instant, is at some intersection in the world. Therefore, the next waypoint to the destination, assuming the destination has not already been reached, is one intersection away in one direction (North, South, East, or West). The smart cab has only an egocentric view of the intersection it is at: It can determine the state of the traffic light for its direction of movement, and whether there is a vehicle at the intersection for each of the oncoming directions. For each action, the smart cab may either stay idle at the intersection, or drive to the next intersection to the left, right, or ahead of it. Finally, each trip has a time to reach the destination which decreases for each action taken (the passengers want to get there quickly). If the allotted time becomes zero before reaching the destination, the trip has failed. The smart cab will receive positive or negative rewards based on the action it has taken. Expectedly, the smart cab will receive a small positive reward when making a good action, and a varying amount of negative reward dependent on the severity of the traffic violation it would have committed. Based on the rewards and penalties the smart cab receives, the self-driving agent implementation should learn an optimal policy for driving on the city roads while obeying traffic rules, avoiding accidents, and reaching passengers' destinations in the allotted time. Environment: The smartcab operates in an ideal, grid-like city (similar to New York City), with roads going in the North-South and East-West directions. Other vehicles will certainly be present on the road, but there will be no pedestrians to be concerned with. At each intersection there is a traffic light that either allows traffic in the North-South direction or the East-West direction. U.S. Right-of-Way rules apply: On a green light, a left turn is permitted if there is no oncoming traffic making a right turn or coming straight through the intersection. On a red light, a right turn is permitted if no oncoming traffic is approaching from your left through the intersection. To understand how to correctly yield to oncoming traffic when turning left.
Dicklesworthstone / Franken WhisperAgent-first Rust ASR orchestration stack: Bayesian backend routing across whisper.cpp/insanely-fast-whisper/whisper-diarization, real-time NDJSON streaming, SQLite persistence, TTY audio transport, conformance harness. 107K lines, 2000+ tests, zero unsafe code.
manthanghasadiya / McpsecAn AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.
lrq3000 / Netlogo Mas DronesA 3D NetLogo 5 multi-agents system simulating a civil UAV drones mission, where they have to escort and protect a humanitarian convoy transporting a critical cargo