04-17 00:02 · AI基础设施,推理优化,边缘计算,平台服务,代理智能
Cloudflare's AI Platform: an inference layer designed for agents
AI models are changing quickly: the best model to use for agentic coding today might in three months be a completely different model from a different provider. On top of this, real-world use cases often require calling more than one model. Your customer support agent might use a fast, cheap model to classify a user's message; a large, reasoning model to plan its actions; and a lightweight model to execute individual tasks.
This means you need access to all the models, without tying yourself financially and operationally to a single provider. You also need the right systems in place to monitor costs across providers, ensure reliability when one of them has an outage, and manage latency no matter where your users are.
These challenges are present whenever you’re building with AI, but they get even more pressing when you’re building agents. A simple chatbot might make one inference call per user prompt. An agent might chain ten calls together to complete a single task and suddenly, a single slow provider doesn't add 50ms, it adds 500ms. One failed request isn't a retry, but suddenly a cascade of downstream failures.
Since launching AI Gateway and Workers AI, we’ve seen incredible adoption from developers building AI-powered applications on Cloudflare and we’ve been shipping fast to keep up! In just the past few months, we've refreshed the dashboard, added zero-setup default gateways, automatic retries on upstream failures, and more granular logging controls. Today, we’re making Cloudflare into a unified inference layer: one API to access any AI model from any provider, built to be fast and reliable.
One catalog, one unified endpoint
Starting today, you can call third-party models using the same AI.run() binding you already use for Workers AI. If you’re using Workers, switching from a Cloudflare-hosted model to one from OpenAI, Anthropic, or any other provider is a one-line change.
const response = await env.AI.run('anthropic/claude-opus-4-6',{
input: 'What is Cloudflare?',
}, {
gateway: { id: "default" },
});
For those who don’t use Workers, we’ll be releasing REST API support in the coming weeks, so you can access the full model catalog from any environment.
We’re also excited to share that you'll now have access to 70+ models across 12+ providers — all through one API, one line of code to switch between them, and one set of credits to pay for them. And we’re quickly expanding this as we go.
You can browse through our model catalog to find the best model for your use case, from open-source models hosted on Cloudflare Workers AI to proprietary models from the major model providers. We’re excited to be expanding access to models from Alibaba Cloud, AssemblyAI, Bytedance, Google, InWorld, MiniMax, OpenAI, Pixverse, Recraft, Runway, and Vidu — who will provide their models through AI Gateway. Notably, we’re expanding our model offerings to include image, video, and speech models so that you can build multimodal applications
Accessing all your models through one API also means you can manage all your AI spend in one place. Most companies today are calling an average of 3.5 models across multiple providers, which means no one provider is able to give you a holistic view of your AI usage. With AI Gateway, you’ll get one centralized place to monitor and manage AI spend.
By including custom metadata with your requests, you can get a breakdown of your costs on the attributes that you care about most, like spend by free vs. paid users, by individual customers, or by specific workflows in your app.
const response = await env.AI.run('@cf/moonshotai/kimi-k2.5',
{
prompt: 'What is AI Gateway?'
},
{
metadata: { "teamId": "AI", "userId": 12345 }
}
);
Bring your own model
AI Gateway gives you access to models from all the providers through one API. But sometimes you need to run a model you've fine-tuned on your own data or one optimized for your specific use case. For that, we are working on letting users bring their own model to Workers AI.
The overwhelming majority of our traffic comes from dedicated instances for Enterprise customers who are running custom models on our platform, and we want to bring this to more customers. To do this, we leverage Replicate’s Cog technology to help you containerize machine learning models.
Cog is designed to be quite simple: all you need to do is write down dependencies in a cog.yaml file, and your inference code in a Python file. Cog abstracts away all the hard things about packaging ML models, such as CUDA dependencies, Python versions, weight loading, etc.
Example of a cog.yaml
file:
build:
python_version: "3.13"
python_requirements: requirements.txt
predict: "predict.py:Predictor"
Example of a predict.py
file, which has a function to set up the model and a function that runs when you receive an inference request (a prediction):
from cog import BasePredictor, Path, Input
import torch
class Predictor(BasePredictor):
def setup(self):
"""Load the model into memory to make running multiple p
▸ 展开全文
04-17 00:02 · 平台监管,反垄断,法律风险,市场合规,电商生态
New unsealed records reveal Amazon's price-fixing tactics, California AG claims
Hundreds of previously redacted records reveal how Amazon has put pressure on independent sellers using its platform into raising their prices on the sites of competitors such as Walmart and Target, so that Amazon can appear to have lower prices, California authorities allege.
The global conglomerate became concerned even if a competitor was selling an item for as little as a penny less, according to one segment of the newly unredacted evidence.
The documents – which have never previously been reported on – include internal emails, deposition testimony and confidential corporate presentations that the California attorney general, Rob Bonta, obtained as part of a civil case his office launched in 2022 accusing Amazon of large-scale price-fixing.
The Guardian obtained and reviewed the cache of evidence, which has been filed in San Francisco county superior court but has not yet become publicly available. Within the documents, lawyers for the state of California have unmasked key details, paragraphs and sometimes whole pages that had previously been blacked out. A judge permitted some redactions to remain at Amazon’s request.
In a statement, Bonta said the newly unveiled evidence reinforced his office’s claims that Amazon’s actions “unlawfully punishes sellers whose products are sold at lower prices by other online retailers”.
“Especially while consumers face an affordability crisis, there is no room for illegal practices that impede competition and raise prices,” Bonta said. “California looks forward to our trial in January 2027.”
Amazon has called the claims in the lawsuit “entirely false and misguided”.
“Amazon is consistently identified as America’s lowest-priced online retailer, and it is ironic that the attorney general seeks to have us feature higher prices in ways that would harm consumers and competition,” the company said in a statement.
For years, the state alleges, Amazon has used automated tools to track how independent vendors on its platform price their goods on competitor sites, then leveraged its dominant position in e-commerce to ensure that those prices do not fall below those on Amazon, even though Amazon often charges vendors far more in fees.
The state’s lawsuit claims that Amazon punishes vendors that dare to offer discounts on their own sites or competitor sites like Walmart, suppressing their sales on Amazon by taking away the vendors’ access to critical features, such as its site’s “Buy Box” – the panel on the right side of the site where customers see buttons like “Add to cart” and “Buy Now”.
In one previously redacted deposition, marked “highly confidential”, Mayer Handler, owner of a clothing company called Leveret, testified that he received an email in October 2022 from Amazon notifying him that one of his products was “no longer eligible to be a featured offer” through Amazon’s Buy Box.
The tech giant, he testified, had suppressed the item, a tiger-themed, toddler’s pajama set, because his company was selling it for $19.99 on Amazon, a single cent higher than what his company was offering it for on Walmart.
A. That Amazon -- the price on Amazon was higher than the price was on Walmart.
Q. And how much higher?
A. One penny.
Afterwards, Handler testified, his company “changed pricing on Walmart to match or exceed Amazon’s price” or changed the item’s product code to try to throw off Amazon’s price tracking system.
We changed pricing on Walmart to match or exceed Amazon’s price. Or we changed the code.
In response to a question from the Guardian, Handler criticized Amazon for tracking prices across the internet and “shadow” blocking his company’s products – tactics which he said were depriving consumers of “lower prices”.
“Maybe that’s capitalism,” he wrote. “Or that’s a monopoly causing price hikes on the consumer.”
In another unsealed deposition, Terry Esbenshade, a Pennsylvania garden store supplier, testified in October 2024 that whenever his products lost Amazon’s Buy Box because of lower prices elsewhere on the internet, his sales on Amazon would plummet by about 80%. This financial reality forced him to try to raise his products’ prices with other retailers elsewhere, he said.
In one instance, Esbenshade testified, he discovered that one of his company’s better-selling patio tables had “become suppressed” on Amazon.
Esbenshade wasn’t sure why, he recalled, until someone at Amazon suggested he look at Wayfair, another online retailer that happened to be selling his patio table below Amazon’s price.
The businessman went online and set up a new minimum advertised price for the table on Wayfair to ensure it was higher than Amazon’s.
“So that raised the price up, and, voila, my product came back” on Amazon, he said, thanks to the reinstatement of the Buy Box.
Amazon has argued that its practices actually promote, incentivize and reward competition. The company said it works “to ensure its customers see offers with low, competitive prices” and provide “the best possible” customer
▸ 展开全文
04-17 00:02 · 开源,硬件原型,AI集成,自动化,低成本创新
Guy builds AI driven hardware hacker arm from duct tape, old cam and CNC machine
AutoProber is the hardware hacker's flying probe automation stack for giving your agent everything it needs to go from "there's a new target on the plate" to probing individual pins in a safe way.
Demo video: https://gainsec.com/autoprober-demo-mp4/
- Tell the agent to ingest the project.
- Connect all the hardware.
- Tell the agent to confirm that all parts are functioning.
- Have it run homing and then calibration.
- Attach the custom probe and microscope header.
- Tell the agent that there is a new target on the plate.
- It will find where the target is on the plate, then take individual frames, keeping a record of the XYZ while noting pads, pins, chips, and other interesting features.
- It will stitch the frames together and annotate the map, including pins and interesting components it identified.
- It will add probe targets to the web dashboard for you to approve or deny.
- It will probe the approved targets and report back.
All hardware can be controlled through the web dashboard, Python scripts, or by the agent itself.
This repo is a self-contained source-available release candidate. It contains the Python control code, dashboard, CAD files, and documentation needed to create your own AutoProber.
This project can move physical hardware. Treat it as a machine-control system, not a normal web app.
The required safety design is:
- GRBL
Pn:P
is ignored. The CNC probe pin is not a trusted endstop. - The independent safety endstop is read from oscilloscope Channel 4.
- Channel 4 must be continuously monitored during any motion.
- Any Channel 4 trigger, ambiguous voltage, CNC alarm, or real X/Y/Z limit pin is a stop condition.
- The agent/operator must stop and report. Recovery motion is not automatic.
Read docs/safety.md and docs/operations.md before running hardware.
apps/ Operator-facing scripts and Flask dashboard entrypoint
autoprober/ Reusable Python package for CNC, scope, microscope, logging, safety
dashboard/ Single-page web dashboard
docs/ Architecture, device references, operations, and safety guidance
cad/ Printable STL files for the current custom toolhead
config/ Example environment/configuration files
AGENTS.md Agent/operator safety rules
LICENSE PolyForm Noncommercial 1.0.0 license and commercial contact
pyproject.toml Python project metadata
uv.lock Locked Python dependency resolution
The tested project architecture uses:
- GRBL-compatible 3018-style CNC controller over USB serial
- USB microscope served by
mjpg_streamer
- Siglent oscilloscope over LAN/SCPI for Channel 4 safety monitoring and Channel 1 measurement
- Optical endstop wired to an external 5V supply and oscilloscope Channel 4
- Optional network-controlled outlet for lab power control
- Current printable custom toolhead parts in
cad/
Default runtime assumptions are documented in the device docs. Replace them with your own lab settings before use.
For a shopping-oriented hardware list, see docs/BOM.md.
These are the specific parts or part classes used for the prototype release. Verify current listings, dimensions, voltage, and connector compatibility before buying.
My build:
- Optical End Stop
- USB Microscope
- SainSmart Genmitsu 3018-PROVer V2
- Matter Smart Power Strip, individually controlled AC outlets with 2 USB-A and 2 USB-C ports
- Siglent SDS1104X-E Oscilloscope
- Dupont wires
- Pen spring or similar light compression spring
- 3D printer for the printable toolhead parts in
cad/
Optional / interchangeable:
- Universal Oscilloscope Probes
- USB power brick, 5V
- USB 2.0 pigtail cable
flowchart LR
Operator[Operator] --> Dashboard[Web Dashboard]
Dashboard --> Apps[Python Apps]
Apps --> CNC[GRBL CNC over USB serial]
Apps --> Microscope[USB Microscope via mjpg-streamer]
Apps --> Scope[Oscilloscope over LAN / SCPI]
Apps --> Outlet[Optional LAN Power Outlet]
Endstop[Optical Endstop] --> ScopeC4[Scope C4 Safety Voltage]
Pogo[Pogo Measurement] --> ScopeC1[Scope C1 Measurement]
ScopeC4 --> Apps
ScopeC1 --> Apps
flowchart TD
Preflight[Preflight] --> SafetyCheck{Channel 4 clear?}
SafetyCheck -- no --> Stop[STOP State]
SafetyCheck -- yes --> Motion[Monitored Motion]
Motion --> Monitor[EndstopMonitor thread >= 10 Hz]
Monitor --> C4{C4 clear?}
C4 -- yes --> Capture[Microscope Capture]
C4 -- no --> FeedHold[Immediate feed hold]
FeedHold --> Stop
Capture --> Stitch[Stitch / Map]
Stitch --> Review[Manual Probe Review]
Review --> Approved{Approved target and measured probe offset?}
Approved -- no --> Stop
Approved -- yes --> Probe[Bounded probe motion]
stateDiagram-v2
[*] --> Running
Running --> STOP: C4 triggered / C4 fault / CNC alarm / real limit pin
STOP --> Report: log voltage, status, action
Report --> WaitForOperator: no automatic recovery motion
WaitForOperator --> Running: operator explicitly clears condition
Install dependencies:
uv sync
Start the dashboard on a configured hardware host:
PYTHONPATH=. python3 apps/dashboard.py
The dashboard defaults to port 5000
.
Start from config/autoprober.example.env. Do not publish lab-specif
▸ 展开全文
04-16 00:00 · 套利,加密货币,交易所,套利
主要加密货币交易所在BTC/USDT交易对上出现显著价差
Binance
About Binance
What Is Binance?
Binance is the world’s largest cryptocurrency exchange by user count and trading volume, with over $217 billion in daily volume across spot and futures markets as of June 2025. Serving 280+ million of users globally, Binance offers access to 500+ cryptocurrencies and more than 1,500 trading pairs. Beyond trading, Binance has evolved into a comprehensive ecosystem that includes Binance Exchange, Binance Wallet, Binance Earn, Binance Pay, Binance Square, Binance Academy, Binance Research, and more. Whether users are looking to trade, invest, learn, or build, Binance provides a secure and feature-rich platform to do so.
Who Are the Binance Founders?
Binance was co-founded by Changpeng Zhao (CZ) and Yi He in 2017. CZ, a Chinese-Canadian software developer and former CEO of Binance, brought experience from previous roles at Bloomberg and Blockchain.com. Yi He, also a seasoned entrepreneur, was a co-founder of OKEX and an early executive in the digital-asset space. Since November 2023, the CEO of Binance has been Richard Teng. With over 25 years of experience in the financial services industry, Richard has held senior leadership roles at major global firms, bringing deep expertise in payments, banking, and technology to drive Binance’s continued growth and innovation.
When Did Binance Launch?
Binance officially launched in June 2017 and rapidly grew into the largest cryptocurrency exchange in the world within just six months.
Binance Restricted Countries
Under Binance’s Terms of Use, access to Binance services is restricted in certain jurisdictions, including the United States, Canada (Ontario), Iran, Cuba, Crimea Region, and North Korea. Access may also be limited in jurisdictions where Binance is not authorized to operate, or where regulatory restrictions apply. Always consult Binance's official terms and compliance updates to confirm eligibility in your country.
How Much Are Binance Fees?
Binance offers a competitive, tiered fee structure for both spot and futures trading. For regular users, spot trading fees start at 0.1% for both maker and taker. Users can receive additional discounts by paying fees in BNB or increasing their trading volume to qualify for VIP levels. Binance also offers zero-fee trading on select BTC and FDUSD spot pairs.
For the most accurate and up-to-date fee schedule, see the official Binance Fee Structure page.
Is It Possible To Use Leverage or Margin Trading on Binance?
Yes, Binance offers both margin trading and derivatives with flexible leverage. On Binance Margin, users can trade a wide range of cryptocurrencies with up to 10x leverage, depending on the asset and market conditions. On Binance Futures, users can trade USDT- or coin-margined perpetual contracts with leverage up to 125x on certain pairs. The platform also features cross and isolated margin modes, auto-deleveraging, and a robust risk engine to support advanced strategies.
You can review the latest margin and leverage rules on the official Futures Trading Rules page.
Only wallets with >500,000 USD balance are shown
* Balances from these wallets may be delayed
Token Allocation
Disclaimer:
All information and data relating to the holdings in the third-party wallet addresses are based on public third party information. CoinMarketCap does not confirm or verify the accuracy or timeliness of such information and data.
CoinMarketCap shall have no responsibility or liability for this public third party information and data. CoinMarketCap shall have no duty to review, confirm, verify or otherwise perform any inquiry or investigation as to the completeness, accuracy, sufficiency, integrity, reliability or timeliness of any such information or data provided.
Markets
- SpotSpot
- PerpetualPerpetual
- FuturesFutures
Pairs
Disclaimer: This page may contain affiliate links. CoinMarketCap may be compensated if you visit any affiliate links and you take certain actions such as signing up and transacting with these affiliate platforms. Please refer to Affiliate Disclosure
▸ 展开全文
04-16 00:00 · 套利,A股,港股,科技股,套利
A股科技股相对港股溢价显著，为跨境套利提供机会
腾讯元宝派电脑版上线 支持一键创建“龙虾”
腾讯宣布，旗下AI原生应用元宝，正式推出“元宝派”电脑版。据了解，电脑版同步支持一键创建“龙虾”和关联已有的“龙虾”。3月25日至4月1日，每天12:00和20:00，用户在元宝派点击「我的Bot」-「一键创建」，即可抢限时免费龙虾。
（文章来源：科创板日报）
腾讯宣布，旗下AI原生应用元宝，正式推出“元宝派”电脑版。据了解，电脑版同步支持一键创建“龙虾”和关联已有的“龙虾”。3月25日至4月1日，每天12:00和20:00，用户在元宝派点击「我的Bot」-「一键创建」，即可抢限时免费龙虾。
（文章来源：科创板日报）
▸ 展开全文
04-16 00:00 · 套利,黄金,期货,套利
黄金现货与期货价差扩大至近期高位，提供期现套利机会
3月25日，A股公用事业板块震荡回暖，电力板块稳步走强，电力ETF博时（561700）震荡上行，其中成分股长江电力、中国核电、三峡能源、国电电力、永泰能源、华能国际等纷纷跟涨。
消息面上，国家能源局、国家统计局最新发布2026年1-2月电力供需核心数据，行业基本面稳步向好。需求端，1-2月全社会用电量累计16546亿千瓦时，同比增长6.1%；供给端，规上工业电力生产增速加快，1-2月规上工业发电量15718亿千瓦时，同比增长4.1%，增速较2025年12月加快4.0个百分点，日均发电266.4亿千瓦时。
国盛证券指出，算电协同下国家级政策严格限制算力园区绿电占比，电力建设战略从“东数西算”起步到“算电协同”升格。自2022年“东数西算”工程启动以来，政策端持续引导数据中心向绿色低碳转型，明确要求2025年底国家枢纽节点新建数据中心绿电占比超过80%。绿色能源成为破解数据中心高能耗难题的关键路径，数据中心用电需求也对电力系统升级提出挑战。
电力ETF博时（561700）及其联接基金（A类：017481，C类：017482）精准覆盖电力公用事业核心龙头，一键分享行业成长红利，在电力需求增长与算电协同升级双重驱动下，具备中长期配置价值。
该ETF紧密跟踪中证全指电力公用事业指数，该指数选取沪深市场中从事电力生产、电力供应等电力公用事业相关业务的上市公司证券作为指数样本，以自由流通市值加权，全面反映A股电力公用事业板块整体表现。
▸ 展开全文
04-16 00:00 · 套利,汇率,跨境,套利
近期中美汇率波动加剧，为跨境贸易和资金流动提供套利机会
当AI重塑基本面、地缘冲突扰乱预期，市场正在进入一个“看不清方向、却不得不交易”的阶段。
据追风交易台消息，3月23日，美银美林发布了最新的《全球股票波动率洞察》报告指出，全球市场正处于一个“确定性真空”状态。报告写道：“当地缘压力与AI颠覆并存时，市场缺乏清晰锚点，投资者只能依赖短期有效的交易逻辑。”
而这一变化，正在重塑资金行为与价格结构。“低信心市场环境下，投资者倾向于追逐当下有效的动量交易，直到其耗尽并转向脆弱。”
报告举例称，韩国股市、黄金、白银等此前具备“泡沫特征”的资产，在地缘冲击中出现更大幅回撤。逻辑很简单：当资金不是基于基本面，而是基于趋势时，一旦趋势反转，价格下跌会更剧烈。
泡沫破裂的预演：从金银到韩股
美银指出，过去几周，黄金、白银以及韩国综指（Kospi）出现的历史性震荡并非偶然。
美银的“泡沫风险指标”（BRI）曾提前预警这些领域的泡沫风险。数据显示，黄金在经历数周的类泡沫行为后，上周出现了历史性的回调，这与其传统的“避险资产”身份形成了鲜明对比。策略师Benjamin Bowler在报告中直言：
“动量交易在耗尽并陷入脆弱之前一直奏效，这使得泡沫风险指标这类工具在评估风险时尤为有用。”
目前波动率市场提供了一个最清晰的信号：不确定性正被极致定价。报告显示，一个惊人的现象是，VIX现货和期货水平远高于标普500的实际波动率（20+ vs 10+），且VIX期货曲线在如此高的波动水平下表现得异常平坦。
这种“高溢价+平曲线”的组合在过去20年中几乎没有类比。这表明市场不仅在为地缘政治事件计入巨大的风险溢价，而且完全无法预判风险何时能得到解决。
美股微观结构恶化：为何价格总是在反转？
在充满不确定性的市场环境中，投资者近来发现，美股变得极易出现“均值回归”和日内反转。美银分析认为，这归因于政策反复（Policy flip-flopping）、宏观数据震荡，以及更深层的市场微观结构变化。
报告披露，随着美国政府撤回对伊朗能源基础设施的威胁，市场情绪发生了180度大转弯。报告写道：
“由于市场消化了特朗普总统关于‘暂时停止在伊朗的敌对行动’的声明，资产价格随之跳涨。这再次提醒我们，日内波动率比收盘波动率更能捕捉当前的股票市场风险。”
而这种“极速反转”导致了市场微观结构的失衡。美银观察到，尽管标普500指数因伊朗去极端化信号而反弹，但由于隔夜交易量的占比已升至20%的高位，而订单簿深度却在缩减，这种“消息面驱动”的反弹极易造成价格过度反应，并随后在流动性回归时出现剧烈均值回归。
“这种环境导致隔夜交易极易引发价格过度反应，由于缺乏流动性支撑，这种定价变得非常脆弱，当次日另一批投资者回归、流动性改善时，价格往往会发生逆转。”
欧洲能源板块：站在十字路口的脆弱者
在欧洲市场，地缘政治冲突将能源价格推向了分叉路口，但也让欧洲能源板块（SXEP）显得尤为危险。尽管该板块今年以来上涨了27%，跑赢了几乎所有欧洲同行，但其“泡沫风险指标”（BRI）读数已接近2022年俄乌冲突初期的峰值。
美银认为，欧洲能源板块目前已经脱离了其典型的能源和股市贝塔系数所暗示的水平，且仓位异常拥挤。未来地缘局势的两种路径对该板块均不利：
-
地缘降温： 能源价格直接重置下行。
-
冲突升级： 极端高昂的能源价格将转而抑制全球增长前景，导致相关股票与大宗商品的相关性由正转负。
“在双向的地缘路径下，我们都看到了欧洲能源板块的脆弱性。”
“确定性真空”下的生存法则
在“确定性真空”的环境下，分析师Benjamin Bowler认为，当下投资者不应盲目追逐动量，而应利用波动率市场的结构性机会。投资者应从寻找趋势转向管理波动。
Bowler建议：一是利用VIX 4月看跌价差博弈地缘冲突的短期去极端化；二是利用0DTE（超短期期权）构建反转策略，对冲因隔夜流动性缺失导致的日内价格过激反应；三是在欧洲市场进行“跨行业波动率对冲”，买入过热能源板块（SXEP）看跌期权的同时卖出估值见底的资源板块（SXPP）看跌期权。
这套组合拳旨在利用波动率定价的脱节，在“阴跌”和“突发反转”中保护投资组合，以对冲AI泡沫可能带来的突然破裂。
~~~~~~~~~~~~~~~~~~~~~~~~
以上精彩内容来自追风交易台。
更详细的解读，包括实时解读、一线研究等内容，请加入【追风交易台▪年度会员】
▸ 展开全文
04-16 00:00 · 开源集成,工作流自动化,AI开发工具,技术生态合作,API增强
OpenClaw与LangChain集成发布，支持链式调用和复杂工作流
OpenClaw与LangChain的集成标志着两个开源AI生态系统的深度合作。该集成使OpenClaw能够直接调用LangChain的组件库，实现复杂的链式工作流自动化。
## 技术特性
1. **链式调用支持**：开发者可以通过OpenClaw编排LangChain的chains、agents和tools，构建端到端的AI应用流水线。
2. **复杂工作流**：集成支持多步推理、工具调用、记忆管理等高级功能，满足企业级AI应用需求。
3. **API增强**：提供了统一的REST API和WebSocket接口，简化了分布式部署和微服务架构下的集成。
4. **开源集成**：所有代码在GitHub上开源，遵循MIT许可，支持社区贡献和定制化开发。
## 应用场景
- **智能客服**：结合LangChain的对话管理能力和OpenClaw的多模态处理，打造全渠道客服解决方案。
- **数据分析**：通过链式调用实现数据提取、清洗、分析和可视化的一站式流程。
- **自动化工作流**：在企业内部流程中嵌入AI决策点，提升运营效率。
- **研发助手**：为开发者提供代码生成、文档编写、调试支持的AI协作工具。
## 生态价值
此次集成不仅扩展了OpenClaw的应用边界，也为LangChain生态带来了新的用户群体。双方的合作体现了开源社区“协作共赢”的精神，有望推动AI开发工具的标准统一和互操作性提升。
## 开发进展
根据GitHub仓库信息，该集成项目已进入beta测试阶段，计划在2026年第二季度发布正式版。早期采用者反馈积极，特别是在金融科技和医疗健康领域已有成功案例落地。
▸ 展开全文
04-16 00:00 · 开源,AI Agent,性能优化,版本更新,开发工具
OpenClaw发布2026.3.23版本，新增多项AI Agent功能和性能优化
2026.3.23
Breaking
Changes
- ModelStudio/Qwen: add standard (pay-as-you-go) DashScope endpoints for China and global Qwen API keys alongside the existing Coding Plan endpoints, and relabel the provider group to
Qwen (Alibaba Cloud Model Studio)
. (#43878) - UI/clarity: consolidate button primitives (
btn--icon
,btn--ghost
,btn--xs
), refine the Knot theme to a black-and-red palette with WCAG 2.1 AA contrast, add config icons for Diagnostics/CLI/Secrets/ACP/MCP sections, replace the roundness slider with discrete stops, and improve accessibility with aria-labels across usage filters. (#53272) Thanks @BunsDev. - CSP/Control UI: compute SHA-256 hashes for inline
<script>
blocks in the servedindex.html
and include them in thescript-src
CSP directive, keeping inline scripts blocked by default while allowing explicitly hashed bootstrap code. (#53307) Thanks @BunsDev.
Fixes
- Plugins/bundled runtimes: ship bundled plugin runtime sidecars like WhatsApp
light-runtime-api.js
, Matrixruntime-api.js
, and other plugin runtime entry files in the npm package again, so global installs stop failing on missing bundled plugin runtime surfaces. - CLI/channel auth: auto-select the single configured login-capable channel for
channels login
/logout
, harden channel ids against prototype-chain and control-character abuse, and fall back cleanly to catalog-backed channel installs, so channel auth works again for single-channel setups and on-demand channel installs. (#53254) Thanks @BunsDev. - Auth/OpenAI tokens: stop live gateway auth-profile writes from reverting freshly saved credentials back to stale in-memory values, and make
models auth paste-token
write to the resolved agent store, so Configure, Onboard, and token-paste flows stop snapping back to expired OpenAI tokens. Fixes #53207. Related to #45516. - Control UI/auth: preserve operator scopes through the device-auth bypass path, ignore cached under-scoped operator tokens, and show a clear
operator.read
fallback message when a connection really lacks read scope, so operator sessions stop failing or blanking on read-backed pages. (#53110) Thanks @BunsDev. - Plugins/ClawHub: resolve plugin API compatibility against the active runtime version at install time, and add regression coverage for current
>=2026.3.22
ClawHub package checks so installs no longer fail behind the stale1.2.0
constant. (#53157) Thanks @futhgar. - Plugins/uninstall: accept installed
clawhub:
specs and versionless ClawHub package names as uninstall targets, soopenclaw plugins uninstall clawhub:<package>
works again even when the recorded install was pinned to a version. - Browser/Chrome MCP: wait for existing-session browser tabs to become usable after attach instead of treating the initial Chrome MCP handshake as ready, which reduces user-profile timeouts and repeated consent churn on macOS Chrome attach flows. Fixes #52930. Thanks @vincentkoc.
- Browser/CDP: reuse an already-running loopback browser after a short initial reachability miss instead of immediately falling back to relaunch detection, which fixes second-run browser start/open regressions on slower headless Linux setups. Fixes #53004. Thanks @vincentkoc.
- Agents/web_search: use the active runtime
web_search
provider instead of stale/default selection, so agent turns keep hitting the provider you actually configured. Fixes #53020. Thanks @jzakirov. - Mistral/models: lower bundled Mistral max-token defaults to safe output budgets and teach
openclaw doctor --fix
to repair old persisted Mistral provider configs that still carry context-sized output limits, avoiding deterministic Mistral 422 rejects on fresh and existing setups. Fixes #52599. Thanks @vincentkoc. - ClawHub/macOS auth: honor macOS auth config and XDG auth paths for saved ClawHub credentials, so
openclaw skills ...
and gateway skill browsing keep using the signed-in auth state instead of silently falling back to unauthenticated mode. Fixes #53034. - ClawHub/macOS: read the local ClawHub login from the macOS Application Support path and still honor XDG config on macOS, so skill browsing uses the logged-in token on both default and XDG-style setups. Fixes #52949. Thanks @scoootscooob.
- ClawHub/skills: resolve the local ClawHub auth token for gateway skill browsing and switch browse-all requests to search so ClawControl stops falling into unauthenticated 429s and empty authenticated skill lists. Fixes #52949. Thanks @vincentkoc.
- Config/warnings: suppress the confusing “newer OpenClaw” warning when a config written by a same-base correction release like
2026.3.23-2
is read by2026.3.23
, while still warning for truly newer or incompatible versions. - CLI/cron: make
openclaw cron add|edit --at ... --tz <iana>
honor the requested local wall-clock time for offset-less one-shot datetimes, including DST boundaries, and keep--tz
rejected for--every
. (#53224) Thanks @RolfHegr. - Commands/auth: stop slash-command authorization from crashing or dropping valid allowlists when channel
allowFrom
r
▸ 展开全文
04-16 00:00 · 开源,AI Agent,技术评测,媒体曝光,生态竞争
OpenClaw获得国际技术媒体KDnuggets推荐，AI Agent能力获认可
EXFOLIATE! EXFOLIATE!
OpenClaw is a personal AI assistant you run on your own devices. It answers you on the channels you already use. It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control. The Gateway is just the control plane — the product is the assistant.
If you want a personal, single-user assistant that feels local, fast, and always-on, this is it.
Supported channels include: WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, BlueBubbles, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, QQ, WebChat.
Website · Docs · Vision · DeepWiki · Getting Started · Updating · Showcase · FAQ · Onboarding · Nix · Docker · Discord
New install? Start here: Getting started
Preferred setup: run openclaw onboard
in your terminal.
OpenClaw Onboard guides you step by step through setting up the gateway, workspace, channels, and skills. It is the recommended CLI setup path and works on macOS, Linux, and Windows (via WSL2; strongly recommended).
Works with npm, pnpm, or bun.
Subscriptions (OAuth):
- OpenAI (ChatGPT/Codex)
Model note: while many providers and models are supported, prefer a current flagship model from the provider you trust and already use. See Onboarding.
Runtime: Node 24 (recommended) or Node 22.16+.
npm install -g openclaw@latest
# or: pnpm add -g openclaw@latest
openclaw onboard --install-daemon
OpenClaw Onboard installs the Gateway daemon (launchd/systemd user service) so it stays running.
Runtime: Node 24 (recommended) or Node 22.16+.
Full beginner guide (auth, pairing, channels): Getting started
openclaw onboard --install-daemon
openclaw gateway --port 18789 --verbose
# Send a message
openclaw message send --to +1234567890 --message "Hello from OpenClaw"
# Talk to the assistant (optionally deliver back to any connected channel: WhatsApp/Telegram/Slack/Discord/Google Chat/Signal/iMessage/BlueBubbles/IRC/Microsoft Teams/Matrix/Feishu/LINE/Mattermost/Nextcloud Talk/Nostr/Synology Chat/Tlon/Twitch/Zalo/Zalo Personal/WeChat/QQ/WebChat)
openclaw agent --message "Ship checklist" --thinking high
Upgrading? Updating guide (and run openclaw doctor
).
Models config + CLI: Models. Auth profile rotation + fallbacks: Model failover.
OpenClaw connects to real messaging surfaces. Treat inbound DMs as untrusted input.
Full security guide: Security
Default behavior on Telegram/WhatsApp/Signal/iMessage/Microsoft Teams/Discord/Google Chat/Slack:
- DM pairing (
dmPolicy="pairing"
/channels.discord.dmPolicy="pairing"
/channels.slack.dmPolicy="pairing"
; legacy:channels.discord.dm.policy
,channels.slack.dm.policy
): unknown senders receive a short pairing code and the bot does not process their message. - Approve with:
openclaw pairing approve <channel> <code>
(then the sender is added to a local allowlist store). - Public inbound DMs require an explicit opt-in: set
dmPolicy="open"
and include"*"
in the channel allowlist (allowFrom
/channels.discord.allowFrom
/channels.slack.allowFrom
; legacy:channels.discord.dm.allowFrom
,channels.slack.dm.allowFrom
).
Run openclaw doctor
to surface risky/misconfigured DM policies.
- Local-first Gateway — single control plane for sessions, channels, tools, and events.
- Multi-channel inbox — WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, BlueBubbles (iMessage), iMessage (legacy), IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, QQ, WebChat, macOS, iOS/Android.
- Multi-agent routing — route inbound channels/accounts/peers to isolated agents (workspaces + per-agent sessions).
- Voice Wake + Talk Mode — wake words on macOS/iOS and continuous voice on Android (ElevenLabs + system TTS fallback).
- Live Canvas — agent-driven visual workspace with A2UI.
- First-class tools — browser, canvas, nodes, cron, sessions, and Discord/Slack actions.
- Companion apps — macOS menu bar app + iOS/Android nodes.
- Onboarding + skills — onboarding-driven setup with bundled/managed/workspace skills.
- Default: tools run on the host for the
main
session, so the agent has full access when it is just you. - Group/channel safety: set
agents.defaults.sandbox.mode: "non-main"
to run non-main
sessions inside per-session Docker sandboxes. - Typical sandbox default: allow
bash
,process
,read
,write
,edit
,sessions_list
,sessions_history
,sessions_send
,sessions_spawn
; denybrowser
,canvas
,nodes
,cron
,discord
,gateway
. - Before exposing anything remotely, read Security, Docker sandboxing, and Configuration.
- Chat commands:
/status
,/new
,/reset
,/compact
,/think <level>
,/verbose on|off
,/trace on|off
,/usage off|tokens|full
,/restart
,/activation mention|always
- Session tools:
sessions_list
,sessions_history
,sessions_send
- Skills registry: ClawHub
- Architecture overview: Architecture
- New here: Getting started, Onboarding, Updating
- Channel setup: Channels index, WhatsApp, Telegra
▸ 展开全文