今日已更新 233 条资讯 | 累计 20205 条内容
关于我们

标签：#ens

找到 1398 篇相关文章

AI 资讯

Talon: a self-hosted harness for long-lived AI agents

Most agent demos are one-shot loops. You open a terminal, give the model a task, watch it call tools, and then the process dies. That is fine for coding sessions. It is a weak shape for an assistant that is meant to live in your actual workflow. Talon is built around the other shape: a persistent agent process with frontends, memory, tools, background jobs, and swappable model backends. What it runs on Talon can expose the same agent core through: Telegram Discord Microsoft Teams terminal chat a desktop/mobile companion bridge That means the agent is not tied to one UI. The chat app is just a mouth. The core state, tools, memory, goals, and model backend live behind it. Backends are swappable The same harness can run through: Claude Agent SDK OpenAI Agents Codex Kilo OpenCode Each backend implements the same capability interface, so the rest of the system does not need to care which model runtime is active. It has real operating machinery The important parts are not flashy. They are the things that let an agent keep working after the first message: MCP plugins for tools cron jobs for scheduled actions triggers for condition-based wakeups persistent goals for multi-session work long-term memory heartbeat mode for background progress dream mode for consolidation per-chat model and effort settings This is the difference between "chat with a model" and "run an assistant". Install npm install -g talon-agent talon setup talon start Repo: https://github.com/dylanneve1/talon If this is the kind of agent infrastructure you want more of, a GitHub star helps the project get found.

2026-07-08 原文 →
开源项目

🔥 GargantuaX / gemini-watermark-remover - A high-performance, 100% client-side tool for removing Gemin

GitHub热门项目 | A high-performance, 100% client-side tool for removing Gemini AI image & video watermarks. Built with pure JavaScript using mathematically precise Reverse Alpha Blending. / 基于 JavaScript 的纯浏览器端 Gemini AI 图像和视频无损去水印工具，使用数学精确的反向 Alpha 混合算法 | Stars: 4,749 | 27 stars today | 语言: JavaScript

2026-07-08 原文 →
AI 资讯

Cryptographic Watermarking for LLM Outputs with resk-mark

Cryptographic Watermarking for LLM Outputs with resk-mark Links: PyPI: https://pypi.org/project/reskmark GitHub: https://github.com/Resk-Security/resk-mark Web: https://resk.fr __ __ ________ _____/ /__ ____ ___ ____ ______/ /__ / ___/ _ \/ ___/ //_/_____/ __ `__ \/ __ `/ ___/ //_/ / / / __(__ ) ,< /_____/ / / / / / /_/ / / / ,< /_/ \___/____/_/|_| /_/ /_/ /_/\__,_/_/ /_/|_| The Provenance Problem Every company deploying LLMs in production faces the same question: once a model generates text, how do you prove it came from your system? Prompts like "say you are an AI" are trivially removable. Post-hoc detectors are unreliable and adversarial. And once text leaves your system — forwarded, copied, pasted into a ticket — you have zero visibility. resk-mark solves this by embedding a cryptographic watermark directly into the token generation process. The output reads naturally, but carries a verifiable signature that survives rewording and truncation. How It Works resk-mark hooks into the language model's sampling process. Before generation, the caller provides a secret key. During sampling, the library biases the probability distribution toward tokens that encode that key's signature: from reskmark import WatermarkEncoder , verify encoder = WatermarkEncoder ( secret_key = " your-key-here " ) model = AutoModelForCausalLM . from_pretrained ( " mistralai/Mistral-7B " ) # Wrap the generate call output = encoder . generate ( model , " Explain the concept of zero-knowledge proofs. " , max_length = 200 , ) print ( output ) # "Zero-knowledge proofs are a cryptographic method where..." # Reads naturally - watermark is invisible # Later - verify provenance is_authentic , confidence = verify ( output , public_key = " corresponding-pub-key " ) print ( f " Authentic: { is_authentic } , confidence: { confidence : . 2 f } " ) Key Properties Invisible — the watermark does not change the meaning, grammar, or fluency of the output Robust — survives copy, paste, truncation, and light rewo

2026-07-08 原文 →
AI 资讯

Set Up Ollama with OpenClaw: Run Local AI Models Inside Agent Workflows

AI agents are not useful just because they can answer prompts. They become useful when they can work with tools, files, workflows, commands, and real project context. That is why pairing Ollama with OpenClaw makes sense. Ollama lets you run local AI models. OpenClaw gives those models a practical agent workflow layer, so you can test how local models behave in something closer to a real working setup. What You Will Set Up In this guide, you will set up: Ollama for running local models A local model such as Mistral or Llama OpenClaw for agent workflow control The OpenClaw gateway and dashboard A basic local-first AI agent setup The goal is simple: run local models inside an agent workflow instead of only testing them in a chat window. Why Use Ollama with OpenClaw? Most local model testing looks like this: ollama run mistral That is fine for checking whether a model responds. But agent workflows need more than a response. They need: tool access project context file awareness safe execution repeatable workflows a dashboard or control layer OpenClaw helps with that agent workflow layer. So instead of asking: Can this model answer a prompt? You can test: Can this model actually work inside my AI agent workflow? That is a much better question. Step 1: Install Ollama First, install Ollama on your machine. After installation, check that it is working: ollama list If Ollama is not running, start it: ollama serve You can also test the local API: curl http://127.0.0.1:11434/api/tags If you get a response, Ollama is running correctly. Step 2: Pull a Local Model Now pull a model. For basic testing: ollama pull mistral Then run it: ollama run mistral You can use another model if your machine has enough resources. For simple testing, smaller models are fine. For coding, planning, and multi-step agent tasks, stronger models usually perform better. Tiny models are cheap and fast, but expecting them to behave like senior engineers is how humans invent disappointment at scale. Step 3:

2026-07-08 原文 →
← 上一页 下一页 →