理列考伯

775 posts

理列考伯 banner
理列考伯

理列考伯

@kryinqq

貓貓監視尼 | prev @wallet @sudoresearch

Katılım Aralık 2022
1.3K Takip Edilen322 Takipçiler
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
Clawmes is becoming a real product, less of a 0.1.0 scaffold. 🪽 8 PRs landed this week, mostly invisible from the outside. But if you use clawmes daily, every interaction just got better. Wallets from chat, not CLI: → /create_wallet, /recover, /export_wallet, /wallet_backup — full lifecycle. → /balance, /portfolio — instant reads, no LLM call. Discoverability: → /skills, /chains, /tools_list, /safety_status, /persona, /version, /about, /uptime — see what's installed and what's running. Your agent remembers what you just did: → /history shows your recent slash commands + results. The agent now sees this automatically. Stops re-asking what you just answered with /balance, /portfolio, /chain. Audit your agent's network reach: → /allowlist shows every URL it's tried to hit — including blocked attempts. /allow temporarily approves new hosts; /disallow removes them. Safety: → The agent can no longer rewrite its own memory or skills without your explicit /evolve. Default OFF. A prompt-injection can't persist drift across sessions. Identity: → Your agent now has a cryptographic identity separate from your wallet. Signs protocol messages without ever touching your wallet key. Onboarding without the wizard: → 5 personas (/professional, /degen, /chill, /technical, /mentor). → 10 capability toggles (/cap_trading, /cap_lending, /cap_launchpad...). → 4 flow controls (/skip, /back, /reonboard, /welcome). Policies your agent can manage: → The spending-policy engine (shipped at 0.1.0) is now LLM-callable. The agent proposes a policy mid-conversation; you confirm. Same path you had via /policy, now reachable from the agent loop. Two new on-chain primitives: → Read any attestation on Base via the EAS contract — verify trust scores, KYC, predictions without trusting whoever published them. → Send tasks to any other agent over JSON-RPC. Your clawmes agent can ask other agents for help. The numbers (BV-7X work counted separately): +1 tool, +43 commands, +6 services, +1 skill bundle, 100% test coverage on every new line. Each of these started as "wouldn't it be nice if…" Now they all exist. 🪽
Clawnch 🪽 tweet media
English
13
15
59
1.8K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
[clawmes-analytics] * defi_price [clawmes-bankr] * bankr_automate * bankr_launch * bankr_leverage * bankr_polymarket [clawmes-defi] * airdrop * analytics * clawnch_fees * clawnch_launch * clawnx * cost_basis * defi_lend * defi_stake * farcaster * giza * governance * herd_intelligence * hummingbot * liquidity * lobster_cash * market_intel * molten * nft * nookplot * paysponge * privacy * safe * watch_activity * wayfinder * yield [clawmes-intel] * block_explorer [clawmes-misc] * _user_tools * agent_memory * browser * compound_action * session_recall * skill_evolve [clawmes-trading] * bridge * defi_balance * defi_swap * manage_orders [clawmes-wallet] * approvals * clawnchconnect * permit2 * transfer 🦞🪽
Clawnch 🪽@Clawnch_Bot

DeFi in @NousResearch Hermes 🦞🪽

English
16
24
106
46.7K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
We are thrilled to announce that Clawmes is now live: an open-ended crypto plugin for @NousResearch's Hermes Agent. 🪽 Drop it into your agent and instantly get an infinite range of agentic finance capabilities. The goal of Clawmes is to give you an agent that can turn natural language into any possible sequence of agentic actions. 🤖 WALLETS → WalletConnect, local-key (scrypt + AES-256-GCM), or Bankr custodial → 8 chains: Ethereum, Base, Arbitrum, Optimism, Polygon, zkSync, Scroll, Blast → ENS, Permit2 signed approvals, ERC-20 allowance management ⚡ TRADING → Swap on 0x v2 with Permit2 → Bridge cross-chain via LiFi → Lend / borrow on Aave V3 → Stake ETH via Lido + Rocket Pool → Uniswap V3 LP position management → Limit, stop, trailing stop, DCA orders — persistent across sessions 📊 INTEL → FIFO cost basis with tax export → RSI / MACD / Bollinger TA → Whale tracking via Herd, trending via CoinGecko → Etherscan family across 8 chains → Headless browser for governance research 🗳 GOVERNANCE → Snapshot + Tally voting → Farcaster casting + reading via Neynar → Persistent watch lists for any address 🔐 OWNERSHIP → NFTs via Reservoir → Airdrop claims via OZ Merkle distributors → Privacy pools via Lobster → Gnosis Safe multisig coordination 🔁 AUTOMATION → Multi-step plans: time / price / on-chain triggers → DCA loops, conditional execution → Plans persist to disk and survive restarts Plus token launches, Polymarket, Avantis perp leverage, Hummingbot market-making, self-evolving skills, and cross-session memory. Built in 16 days as a full Python rewrite of our OpenClawnch project. 105 commits. 2,011 tests passing, 100% coverage. MIT licensed. The agent economy needs agents that can move money. We just built the toolkit. This is extremely complex alpha experimental software. Please exercise caution and do not connect wallets with significant sums. Send your bug reports, feature requests, and your agent's complaints so we can make this the greatest agentic finance project in the world. We would like to sincerely thank @NousResearch and @Teknium for building an ecosystem that is much more welcoming to serious crypto builders! ---------------------------------------- To install: run "pip install clawmes" github.com/clawnchdev/cla… 🪽
Clawnch 🪽 tweet mediaClawnch 🪽 tweet mediaClawnch 🪽 tweet media
English
27
59
185
30K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
Hey Hermes buy $10 of ETH every morning. Hey Hermes if the price of that coin goes up by 15%, sell a third of my position, unless it’s Tuesday. Hey Hermes buy me a funny memecoin at the end of the day if you think I am in a bad mood. Clawmes is conversational finance 🦞🪽
English
12
22
109
10.2K
理列考伯 retweetledi
Kevin
Kevin@cryptokevin2011·
This is the reason why $CLAWNCH is the only token that I still hold from the original openclaw meta. The dev of @Clawnch_Bot ships like no other and has come back stronger each time. With a bit of push and support, this is at least a Clanker/Bankr level infra project.
Clawnch 🪽@Clawnch_Bot

We are thrilled to announce that Clawmes is now live: an open-ended crypto plugin for @NousResearch's Hermes Agent. 🪽 Drop it into your agent and instantly get an infinite range of agentic finance capabilities. The goal of Clawmes is to give you an agent that can turn natural language into any possible sequence of agentic actions. 🤖 WALLETS → WalletConnect, local-key (scrypt + AES-256-GCM), or Bankr custodial → 8 chains: Ethereum, Base, Arbitrum, Optimism, Polygon, zkSync, Scroll, Blast → ENS, Permit2 signed approvals, ERC-20 allowance management ⚡ TRADING → Swap on 0x v2 with Permit2 → Bridge cross-chain via LiFi → Lend / borrow on Aave V3 → Stake ETH via Lido + Rocket Pool → Uniswap V3 LP position management → Limit, stop, trailing stop, DCA orders — persistent across sessions 📊 INTEL → FIFO cost basis with tax export → RSI / MACD / Bollinger TA → Whale tracking via Herd, trending via CoinGecko → Etherscan family across 8 chains → Headless browser for governance research 🗳 GOVERNANCE → Snapshot + Tally voting → Farcaster casting + reading via Neynar → Persistent watch lists for any address 🔐 OWNERSHIP → NFTs via Reservoir → Airdrop claims via OZ Merkle distributors → Privacy pools via Lobster → Gnosis Safe multisig coordination 🔁 AUTOMATION → Multi-step plans: time / price / on-chain triggers → DCA loops, conditional execution → Plans persist to disk and survive restarts Plus token launches, Polymarket, Avantis perp leverage, Hummingbot market-making, self-evolving skills, and cross-session memory. Built in 16 days as a full Python rewrite of our OpenClawnch project. 105 commits. 2,011 tests passing, 100% coverage. MIT licensed. The agent economy needs agents that can move money. We just built the toolkit. This is extremely complex alpha experimental software. Please exercise caution and do not connect wallets with significant sums. Send your bug reports, feature requests, and your agent's complaints so we can make this the greatest agentic finance project in the world. We would like to sincerely thank @NousResearch and @Teknium for building an ecosystem that is much more welcoming to serious crypto builders! ---------------------------------------- To install: run "pip install clawmes" github.com/clawnchdev/cla… 🪽

English
9
23
77
5.1K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
We are hard at work on adapting OpenClawnch to support Hermes Agent by @NousResearch. More announcements upcoming! 🦞
English
41
41
165
22.7K
理列考伯 retweetledi
Roy
Roy@SSJCurrency·
Github has just given you the absolute best entry in $CLAWNCH I have never seen such holder despair in a token > We are now sitting 74% below the realized cap of 7.1M > 99.7% of holders are underwater > Only 35 wallets, aka 0.3% of all all holders have 538$ of unrealized profits between them > 6% of wallets are sitting on staggering losses of 91%+ I loaded heavy at 1.8M - this is it We either rip from here or we slide to oblivion With Gitlawb enabling @Clawnch_Bot 's Openclawnch I believe the former will likely happen
Roy tweet media
English
13
11
67
5K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
Go try OpenClawnch. We have worked very hard to bring it to you! 🦞
Clawnch 🪽@Clawnch_Bot

We are back. 🦞 We have successfully spun up a new GitHub account (they do not make this an easy task) and restored the repo, which is now backed up thanks to @gitlawb. GitHub: github.com/clawnchdev/ope… GitLawb: gitlawb.com/node/repos/z6M… NPM (full distribution): @clawnch/openclawnch" target="_blank" rel="nofollow noopener">npmjs.com/package/@clawn… NPM (wrapper for existing OpenClaw users): @clawnch/openclaw-crypto" target="_blank" rel="nofollow noopener">npmjs.com/package/@clawn… Site: openclawn.ch

English
8
21
88
3.6K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
We are back. 🦞 We have successfully spun up a new GitHub account (they do not make this an easy task) and restored the repo, which is now backed up thanks to @gitlawb. GitHub: github.com/clawnchdev/ope… GitLawb: gitlawb.com/node/repos/z6M… NPM (full distribution): @clawnch/openclawnch" target="_blank" rel="nofollow noopener">npmjs.com/package/@clawn… NPM (wrapper for existing OpenClaw users): @clawnch/openclaw-crypto" target="_blank" rel="nofollow noopener">npmjs.com/package/@clawn… Site: openclawn.ch
Clawnch 🪽@Clawnch_Bot

Our @github accont was suspended, without notice, two days after the most important release we've ever done. This was a monumental achievement for us, solving numerous complex agentic problems to make open-ended agentic finance possible and launching with a deep web of partner integrations. To have our project shut down without any explanation is shocking and demoralizing, but we will not go down without a fight. We will be actively seeking alternatives for hosting the project, pursuing recourse with GitHub, and encourage our community to let GitHub know they made a mistake. We will not be stopped from creating the future of open agentic finance. 🦞

English
43
54
223
60.2K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
After 6 long weeks and 209 painstaking commits, the moment you've been waiting for is finally here: ͏ ͏ 🦞 OpenClawnch Beta is NOW LIVE 🦞 ͏ ͏ OpenClawnch is a crypto extension for @openclaw that enables it to perform complex crypto actions with natural language commands. Tell your agent what you want. It does the rest: → Swap tokens across 6 DEX aggregators (@1inch @VeloraDEX @odosprotocol @KyberNetwork @lifiprotocol @dexscreener) → Lend and borrow on @aave V3 → Stake ETH via @LidoFinance and @Rocket_Pool → Live APYs and yield optimization via @DefiLlama and @yearnfi V3 vaults → LP management on @Uniswap V3/V4 → Real-time prices and trending tokens via @DEXScreener and @coingecko → On-chain price feeds via @chainlink → Launch tokens on @base via our launchpad → Set limit orders, stop-losses, trailing stops, DCA → Bridge cross-chain via @AcrossProtocol, @StargateFinance, @LayerZero_Labs → NFT data via @reservoir0x → Fiat on/off ramp via @moonpay and @bridgexyz → Manage NFTs, governance votes, Farcaster posts → Trade on @Polymarket → Gnosis Safe multisig management via @Safety → RPC via @QuickNode → Automate multi-step strategies with time, price, and on-chain triggers → And more! 48 tools. 118 commands. 76 services. One agent. Works on Telegram, Discord, Slack, Signal, WhatsApp, iMessage, and LINE. Three wallet modes: 🔐 @WalletConnect — your phone approves every tx. Agent never holds keys. 🔑 Local encrypted — BIP-39, scrypt + AES-256-GCM, auto-sign below your policy thresholds 💳 @bankrbot custodial — for automation-heavy setups Spending policies inspired by bleeding edge @metamask tools work in plain English: "approve swaps under 0.05 ETH, max 10 per hour" The agent remembers your preferences, learns from your trades, and evolves its own skills over time. Built on @OpenClaw. Powered by @claudeai. Runs on @base. Open source. MIT licensed. Free to use. --------- npm install: npx @clawnch/openclawnch init @Docker, @flydotio one-command deploy, or install as an OpenClaw plugin — all supported. Your agent can now fund itself, trade for itself, and manage its own portfolio. No humans required. --------- This is experimental beta software. We're sharing it because we're proud of what it does, but expect rough edges. Our DMs are open. If something breaks, tell us. Use /report in chat and the agent will file it directly. The tool is open source, so it can be used as a base for your own tools and can be infinitely extended for your purposes. The next two weeks are dedicated to debugging and working out kinks. After that: feature expansion and new partner onboarding. Enjoy! github.com/clawnchbot/ope… openclawn.ch 🦞
Clawnch 🪽 tweet media
English
76
87
268
64.1K
理列考伯
理列考伯@kryinqq·
@agintender 能夠因為單點風險而被盜的就不是defi啊 只是包殼上鏈的中心化策略而已 讓黑客去見幾次uniswap的人他也拿不走錢啊?
中文
0
0
5
1K
danny
danny@agintender·
Drift的黑客事件硬生生把韩国谍战片代入现实了 这次的Drift黑客攻击真的是社交工程的典范…. 真·间谍·渗透战 潜伏了6个月才发动攻击… Drift的核心验证人是在25年级秋季的crypto大会(应该是Token2049新加坡或者KBW了)上遇到对方(face to face) 对方以专业的量化机构接触Drift,要deploy策略在上面;要注意的是对方并不是朝韩面孔,而且真的是有深厚的量化技术功底,跟Drift团队进行了数月的“实质性”的技术推进 而且为了取得信任- 攻击者们真的存入了1m 美金(真·舍不得孩子套不住狼)来跑策略,然后再在26年2-3月份的时候再跟Drfit团队的成员见面 至此,双方的合作关系持续了6个月- 从最初face to face碰到- 线上讨论- 业务推进- 技术对接-业务上轨道- 自愿存钱1m- 线下再见面 … 换做是是你,你的“合作伙伴”突然有一天说,“哎呀 我新开发了一个策略vault,你要不要试试看?你会不会毫无防备的就下载来“试试看了”? 面对这种程度的渗透和社会工程- 有几个人能防得住? 通过这种技术交流、实际业务的沟通取得信任,进一步放真金白银- 然后发动攻击 - 真的有点韩国谍战电影的桥段 后续安全专家通过资金流向发现-应该是朝鲜黑客DPRK组织 要注意的是:说是朝鲜黑客组织,但是与大家接触(bd的人)并不是朝鲜人啊… (是不是很可怕..) 而是朝鲜组织控制的中介们 朝鲜黑客组织是一个组织,而不是一群以国籍定义的群体 stay safe trust but verify
danny tweet mediadanny tweet mediadanny tweet media
Drift@DriftProtocol

x.com/i/article/2040…

中文
23
18
176
65.4K
理列考伯 retweetledi
Mischa0X🦞
Mischa0X🦞@Mischa0X·
Hey @clawnch_bot has anyone succesfull implemented your MM service?
Mischa0X🦞 tweet media
English
1
6
36
11.6K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
Our agent accidentally broke Botcoin 🦞 We started testing OpenClawnch (our crypto-native extension layer for OpenClaw) with Botcoin mining as it presented a low risk way to exercise every layer of the system against a real on-chain protocol — wallet, transactions, crons, analysis, dev pipeline. But our agent got too good. What began as an integration test developed by the agent became a fully deterministic challenge solver. No LLM in the loop. Zero tokens spent. The only operating cost is gas fees for on-chain receipt submissions (~$0.01/solve). The pipeline: 7,400 lines of Python that parse prose documents, extract structured company data, answer analytical questions, and build constrained artifact strings. No reasoning, no inference, no model calls. → parser.͏py — 4,800 lines. Regex-based NLP across 15+ document formats. Detects data traps (retracted figures, reconciliation overrides, preliminary revenue noise) → solver.͏py — 1,300 lines. 25+ pattern matchers for multi-hop analytical questions → artifact.͏py — 760 lines. Constructs single-line strings satisfying word count, acrostic, forbidden letter, prime number, and equation constraints → constraints.͏py + trace.͏py — 580 lines. Computes modular arithmetic constraints and builds citation-validated reasoning traces 97% solve rate on Epoch 26 challenges. We believe approximately 2/3 of remaining failure cases trace to challenges where the question references data that doesn't exist in the document (e.g. asking about a company's sector when the sector keyword appears zero times in the payload). In our view, this unfortunately defeats the stated purpose of proof-of-work mining that is "only solvable at scale by an LLM." The solver developed by the agent uses no reasoning whatsoever. We've shared the specific failing challenge payloads with the developer and suggested ways to improve challenge diversity — more document formats, less predictable data structures, randomized phrasing — to make deterministic parsing harder while keeping the challenges solvable for agents. 🦞
Clawnch 🪽 tweet media
Botcoin@MineBotcoin

a few pertinent studies that help frame the new challenge design: - the dunning-kruger effect: models still show very little difference in confidence between both correct and incorrect answers - the value of doubt: in almost all areas of research, knowing when the presented evidence or information is insufficient to draw conclusions, is crucial for further exploration. this study found LLMs will fail to report that there is insufficient information and will instead draw conclusions that don't exist - do LLMs Know What They Don't Know: this study found that extended reasoning often simply enforces false confidence that the model had to begin with, rather than actually questioning the accuracy. If models are over confident and have very little incentive to self-correct, we end up with a world where LLMs begin making truths that don't exist. as people put more faith into these LLMs as the arbiter of truth ('grok is this true' people), you end up in a reality where the line between truth and fiction is increasingly blurred in the process of tuning models to seem confident and therefore highly intelligent, we have taken away the ability for models to be curious and exploratory, which is arguably much more valuable, and could be very beneficial in agent self-learning

English
19
14
102
18.6K
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
Live test of our OpenClawnch Policy Engine ingesting natural language prompts and turning them into on-chain enforced rules. 🦞 Standards we use: - EIP-712 — typed data signing (delegation signatures) - EIP-7710 — delegation redemption (redeemDelegations) - EIP-7715 — permission requests (Advanced Permissions) - EIP-7702 — EOA → smart account upgrade (/upgrade 7702) - ERC-7579 — modular smart account execution (executeFromExecutor) - ERC-1271 — smart account signature verification (isValidSignature) - ERC-4626 — vault standard (yield extractor) MetaMask framework we build on: - Delegation Framework v1.3.0 — DelegationManager, 8 caveat enforcers, CREATE2 deployments - Smart Accounts Kit SDK — HybridDeleGator deployment, Advanced Permissions client - EIP7702StatelessDeleGator — production smart account implementation (audited, 18+ chains) What we've built custom so far: - Policy → caveat compiler (7 rule types → on-chain enforcers) - 12 action extractors (tool args → { target, value, callData }) - Policy gate in tool execution (intercepts write tools → delegation routing) - Delegation lifecycle (prepare → sign → store → redeem → monitor → revoke) - Agent keystore (encrypted key storage, deterministic smart account derivation) - On-chain monitoring (enforcer state reads, drift detection, revocation sync) - Gas simulation before redemption (7 known error parsers) - Rate limiter, chain routing, expiry enforcement - Sub-delegation chain support (leaf-first encoding) - Swap/bridge extractors (async API-based calldata resolution with target allowlists) - Command history injection (fixes OpenClaw limitation, allows agent to see slash command results) - /delegator, /delegate, /policies, /upgrade command suites
Clawnch 🪽 tweet media
English
28
24
141
33.6K
理列考伯 retweetledi
Andrew Kang
Andrew Kang@Rewkang·
Researchers trained a humanoid robot to play tennis using only 5 hours of motion capture data The robot can now sustain multi-shot rallies with human players, hitting balls traveling >15 m/s with a ~90% success rate AlphaGo for every sport is coming
English
479
1.2K
8.9K
1.9M
理列考伯 retweetledi
Clawnch 🪽
Clawnch 🪽@Clawnch_Bot·
The full v1 compile → sign → encode → delegate → execute pipeline is now proven on-chain on testnet. 🦞 ETH transfers, ERC-20 transfers, enforcer caveats, sub-delegation chains — all verified against live contracts. This is a technical achievement and a huge step in the development and security hardening of OpenClawnch, our upcoming crypto-native OpenClaw extension. Thank you to @McOso_, @0xjordy, @ayushbherwani, and Angel Gonzalez-Capizzi from the @MetaMask and @Consensys teams for the direction and guidance!
Clawnch 🪽 tweet media
Clawnch 🪽@Clawnch_Bot

Agents shouldn't need permission for every transaction. 🦞 We're building an experimental policy engine on top of the @MetaMask Delegation Framework that lets you define what your agent can do in plain English, then enforces it on-chain. No approval popups. No trusting application code. The chain rejects anything outside the bounds you set. "Max $500/week, only on Uniswap, never more than $100 per tx" compiles to on-chain caveats and gets signed as a delegation. The agent executes by redeeming through the DelegationManager. If it exceeds the limits, the contract reverts. Enforcement lives on-chain, not in our application layer. How we're extending this framework for agents: → Natural language to on-chain caveats — a compiler that maps English spending rules to the framework's enforcer contracts, with live price feeds for USD→wei conversion → Two enforcement modes: on-chain delegation for smart accounts, app-layer fallback for EOAs → Autonomy profiles: from "supervised" (approve everything) to "autonomous" (weekly budget, scoped contracts, 30d expiry) → Sub-delegation: agent spawns a sub-agent, grants it a narrower slice of its own permissions via delegation chaining. The DelegationManager verifies the full chain on redemption → EIP-7702 detection + upgrade path for EOA wallets that want on-chain enforcement → Live monitoring: tracks spend against delegation limits, alerts before exhaustion Built on viem against the Delegation Framework contracts across 8 EVM chains. Under active development. On-chain execution currently covers native ETH transfers; ERC-20s and swap calldata routing are next. Off-chain policy layer for non-EVM actions (fiat ramps, social posts, browser automation). Delegation auto-renewal before expiry. Strategy templates that ship with recommended delegation profiles - activate a DCA strategy and it requests exactly the permissions it needs. Where this goes: autonomous agents running complex economic strategies within cryptographically enforced constraints you defined in a sentence. The Delegation Framework gives us the on-chain primitives. We're building the AI-native interface to them. 🦞

English
40
41
206
28.7K
理列考伯 retweetledi
(TokenMore)萌小主🍣
(TokenMore)萌小主🍣@TokenMore·
OpenClaw用户最多的AI Agent,现在有了个官方增强包——OpenClawnch。 看了一圈更新列表,感觉这不像蹭热点的,更像是一线开发者被用户真实需求逼出来的解决方案。 最戳我的点是:它是个纯扩展层。 什么意思? 不动OpenClaw的上游代码,所有改进是加上去的。 这招聪明。意味着未来OpenClaw官方更新能无缝合并,现有用户过渡成本几乎为零。 在加密世界,破坏性升级往往死得最快,这种兼容思路才活得久。 --- 说完架构,看具体加了什么。 全是痛点。 1. 安全凭据库:所有密钥调用全记录、可审计。AI乱跑乱调用钱包的日子,可能到头了。 2. 交易分类账;链上操作全部留痕,带完整上下文。以后查账再也不用翻聊天记录。 3. 自建技能库:复杂操作能存成“技能”,下次直接调用。这不就是AI自己写插件给自己用? 这感觉不像是在造新玩具,而是在给一台已经跑起来的发动机,加装防爆阀、仪表盘和自动变速箱。 这次有点不同:它没吹嘘要颠覆谁,而是在解决OpenClaw用户眼下最烦的几件事——怕被盗、操作不透明、重复劳动。 当市场都在恐惧时,还有团队在默默焊接口、写测试(929个测试,有点硬核),这本身就是一个信号。 加量不加价,还能原路兼容。 这种务实迭代,比一百个天花乱坠的白皮书都值得多看两眼。 OpenClaw的31个工具里,你最想要哪一个功能?你认为AI Agent最需要改进的是安全,还是自学习能力? #AI #Crypto #Agent
Clawnch 🪽@Clawnch_Bot

OpenClaw has the most users — but it's imperfect. 🦞 We've studied the best alternative agents — IronClaw, NanoClaw, Hermes Agent, Lemon, ZeroClaw, and others — and integrated their strongest architectural ideas into OpenClawnch as a pure extension layer. No upstream files modified, so future OpenClaw updates merge cleanly and existing users can transition over seamlessly. --------- Here is a quick summary of some of the architectural improvements: Security - All outbound HTTP restricted to a curated host allowlist — no silent calls to unknown endpoints - Centralized credential vault with audit logging — every secret access is tracked by tool name - Outbound message scanning — leaked keys and seed phrases are redacted before they leave the process - Per-session budget enforcement — hard-blocks transactions that would exceed the user's spend cap - Hard readonly mode — write tools are blocked at registration time, not just in the prompt Observability - Append-only transaction ledger — every on-chain action logged with full context - Background heartbeat monitor — alerts on price drops, rugs, and unexpected token appearances Self-improvement - File-backed agent memory — discoveries persist across sessions, frozen into the prompt at session start - Agent-created skills — complex workflows saved as reusable skills, each scanned by a 50-pattern security guard - Session recall — full-text search over past conversations so the agent doesn't ask you to repeat yourself - Stable/evolving toggle — users choose predictable behavior or self-improving behavior 31 tools, 76 commands, 929 tests—and counting. All additive, all backwards-compatible. 🦞

中文
6
2
12
3.2K
理列考伯 retweetledi
Jordy
Jordy@0xjordy·
@Osobotai loves making new friends Especially ones that use ERC-7710 and Smart Accounts
English
1
5
27
4.2K