VaxVoIP Call SIP Agent AI SDK
A SIP AI voice agent SDK that connects SIP servers and IP-PBX systems with OpenAI Realtime for multilingual voice automation.
原文
1
DEV TRENDS / CATEGORY
Agent 生态 · Agent 运行时
2026年10月26日 – 2026年11月1日 内首次发现的 15 个新项目，已跨 3 个来源去重。
2026年8月10日 – 2026年11月1日 内首次发现 238 个项目
DTDevTrends 归类原始项目或来源原始标签
15 个新项目3 个来源
Cartesia Managed Agents
Cartesia Managed Agents is an end-to-end voice agent platform for enterprise conversations. Cartesia co-designed its voice models and agent harness so listening, turn-taking, reasoning, tool calls and speech work as one system, with telephony, knowledge bases and outbound campaigns included. It ranks #1 on Artificial Analysis’ Speech Agent Arena. Launch pricing is $0.03 per minute, 50% off.
原文3
AgentQon
AgentQon is a free AI agent harness. A panel of AI agents plans, checks its own work, and finishes jobs. It is free forever: no paywall, no credits, no ads, no commissions. You bring your own model key, or run a free local model. 6,799 agents and 4,840 skills are built in, plus an optional 213-skill Extended Library you can add at setup. Install it with one command: npm install -g agentqon. There is also an Android app. The product page is the GitHub repo.
原文1
1
Agent-2
An autonomous AI agentic harness built to code anything, automate terminals, perform cybersecurity tasks, and execute complex real-world workflows with minimal human intervention. From writing and..
原文1
harness2
谷歌开源的智能体自我进化框架。这是一个让 AI 智能体在不改动模型权重的情况下，遇到陌生任务时自我改进的框架。它会针对当前任务提出修改方案，比如调整系统提示词、记忆、技能、子智能体和插件等，然后实际试跑对比效果，最后把经验沉淀下来，供后续任务使用。
—
Cognitum Metaharness
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Co...
原文3
1
10x faster, 3x cheaper ETL
For the past few months our team has been working on an agentic framework that takes large, expensive SQL workloads and compiles them to Rust, backed by a formal proof of correctness. This is the sort of work I used to do by hand as a systems performance engineer, but now it happens in hours instead of months. We first redid our internal pipelines with this technique and they're now 10x faster and 3x cheaper. Next, we went live with our Snowflake and Databricks SQL customers. They're seeing similar results with critical production workloads that originally cost 6-7 figures per year. We'll be publishing benchmarks and code samples over the coming weeks; for now, you can read a bit more (and watch our anime launch trailer) on the site. Happy to answer questions about how it all works.
原文
—
iGentrix
iGentrix is the AI agent platform that proves an agent works before it goes live. A built-in launch check runs about 30 realistic customer questions and about 20 attacks in a safe sandbox, then scores accuracy, security and coverage and shows how to fix each failure. Then one agent serves WhatsApp, web chat, email, Messenger, Instagram and Telegram, with a team inbox, lead capture and automations included.
原文2
A Lego-like composable Framework for RSI
GEAR: An Open General Evolutionary Architecture for Recursive Self-Improvement of LLM Agent Harness. An open framework for harness evolution, reproducible evaluation, and learning across tasks.
原文—
Sectr – Serverless backend platform for easy deployment of AI agents
Hey HN, I've been building Sectr, a backend-as-a-service for making it easy(ier) to develop and deploy AI agents. Deploying agents requires non-trivial systems design work. Consider a support agent: how do you stream messages to your frontend, how/where do you persist messages for frontend fetching later (or for auditing), and when the agent wants to issue a refund, do you spin-down the compute infra while it's waiting on human approval? Sectr aims to be the serverless abstraction and platform to provide these systems for you. No sign-up needed to try using the dev server: curl -fsSL https://sectr.dev/install.sh | sh # Install CLI sectr init my-agent && cd my-agent # Starter code sectr dev # Dev server, with UI to test chatting Sectr provides: - Streaming of every token, tool call and event, and persistence so they can be loaded fresh later. - Scaling up, and down to zero when the agent needs to wait, and resumption right to the suspended agent's state. - Human approved tools automatically use Sectr's suspension and resumption capabilities, no code needed from you. - AG-UI endpoint for any deployed agent so you can trivially hook up your frontend - Local dev server experience, so you can rapidly debug and iterate on your agent's behavior At the core, you can deploy any container image to Sectr as long as it implements a certain shaped HTTP endpoint. In practice, currently Sectr provides adapters to let you deploy your existing OpenAI Agents SDK, LangGraph, or Pydantic AI agents, with only 2 new lines of code: app = AgentApp(name="support") app.add_route("/chat", openai_agents(agent)) Certainly the hardest part of building Sectr was getting the resumption logic to be correct and invisible, across the Program State x Model Provider x Agent Framework matrix. For example, an earlier bug was when a model replied with text plus a tool call, Sectr would resume that as two separate messages, instead of one message with a text and tool part. This works, but breaks prompt caching (and might subtly change model behavior). Sectr is free during the beta (and can be tried locally without sign-up); I mainly want feedback, especially on dev & deployment experiences, any bugs, and what features would excite you. Introductory video: https://www.youtube.com/watch?v=H-y3wynkKc0 Docs: https://docs.sectr.dev
原文—
VoiceStride
VoiceStride is an AI voice agent platform for business conversations. It brings AI into phone interactions, giving businesses a new way to approach customer communication. From answering enquiries to supporting ongoing conversations, business calls serve different purposes across industries. VoiceStride focuses on AI voice agents for sectors including healthcare, banking and financial services, real estate, hospitality, and education.
原文1
Zuloo AI Voice Agent Platform
Deploy enterprise AI voice agents that answer phone calls, qualify leads, and schedule appointments 24/7. Sub-second latency with seamless human handoff.
原文1
JetAgents
AI agent platform that lets anyone create, deploy and automate AI agents connected to 100+ business apps — no code required.
原文1
没有找到相关项目
换一个关键词或分类试试。