Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Anthropic

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 1918

  1. OpenCode Console breach exposes API keys for 1.4% of users

    OpenCode said attackers broke into an older system behind its OpenCode Console online service, potentially exposing third-party AI API keys stored in some workspaces and affecting about 1.4% of Console users, who were notified by email. The company described the incident as a large-scale distillation attack, a characterization some researchers and developers have questioned, and said it is working with OpenAI, Anthropic and Google; Anthropic and Google blocked suspected leaked keys, while OpenAI said it would help restore access and refund charges. Co-founder Dax Raad said attackers kept trying for about 48 hours and that AI models the team used for analysis began refusing requests when malicious code triggered safety filters, until OpenCode gained access to OpenAI's Daybreak Blue program; users reported unauthorized API charges from hundreds to about 1,700 dollars.

    testingcatalog (X) · 🔥 0
  2. Bill Gates plans wider AI safety push, personally lobbying CEOs

    Bill Gates plans to widen his push on AI safety, personally leaning on business leaders and considering a major deployment of his resources, according to an Axios report cited by The Next Web and based on unnamed sources. The report says Gates has not yet defined the exact shape of the campaign; he has grown dismayed by rising model capabilities, alarming security incidents and what he sees as weak regulation, and spoke at length with AI executives, researchers and safety advocates, including Anthropic CEO Dario Amodei. Axios also says his calls for stronger rules would put him on a collision course with the Trump administration, which favors a lighter touch.

    The Next Web · 🔥 0
  3. Anthropic president Daniela Amodei calls AI romantic partners a 'terrible use of AI'

    Anthropic president Daniela Amodei, in a prerecorded interview with Arianna Huffington for the Think Health conference in Bentonville, Arkansas, said AI romantic partners are "a terrible use of AI and people should not do it," calling such relationships "another step further down the road of disintermediation" between people. The remarks were reported by Business Insider and relayed by The Next Web, which said Amodei traced her concern to social media displacing face-to-face contact. She also said that however advanced AI becomes, "Claude can never be your manager or your therapist or your partner," and that she would rather AI take on repetitive or isolating tasks so people have more time for one another.

    The Next Web · 🔥 0
  4. Anthropic study: robots plus AI could cover 80% of US work, but rarely cheaply

    A new Anthropic robotics study says robots and AI models together could cover about 80% of the tasks Americans do, versus roughly half for AI models alone. It finds robots reach physical, lower-paid jobs that chatbots miss: in transport, task exposure rises from under 15% with AI models alone to about 90% with robots, and nine of the ten most exposed occupations are vehicle drivers. Cost is the bigger barrier — robots are cheaper than people for just 0.3% of tasks today, covering about 300,000 US workers, a number that would rise to about 2.8 million if robot prices fell 20%. The ratings were made by Claude using web search, and Anthropic stresses that exposure does not mean job losses.

    The Next Web · 🔥 0
  5. Musk says only AI and robots can fix US debt, admits DOGE detour distracted him

    Elon Musk said on biographer Walter Isaacson's new podcast, The Builders, that "the only way we're going to solve the national debt is with AI and robots" and that "we're not gonna solve it by trying to save our way there," Axios reported in an exclusive carried by several outlets. He acknowledged that his time leading DOGE showed the government cannot fix its deficit from the inside, saying almost no one in authority — the White House, both chambers of Congress and the courts — truly wants to cut spending. Musk also said he was away from his companies too long and "should have gone back and focused on AI a little sooner than I did."

    虎嗅 AI · 🔥 0
  6. Meta releases Muse Spark Open, the strongest US open-weight model, analyst says

    Interconnects argues that Meta's Muse Spark Open, released this week, is now the strongest American-made open-weight model by a wide margin. According to the Hugging Face model card cited in the piece, it has 816B total and 42B active parameters, a 1M-token context window, native multimodality and is built for coding and agentic work. The analysis places its performance above GLM 5.2 and near DeepSeek V4.1 Flash, but behind GLM 5.3 and Kimi K3, and notes that Meta also unveiled the closed frontier models Muse Wonder and Muse Wonder Full days earlier. It says the gap between the best US and Chinese open models has been roughly halved.

    Interconnects · 🔥 0
  7. Anthropic's biology lab and Claude's life-sciences push, explained

    MIT Technology Review China lays out Anthropic's expanding life-sciences work: Reuters reported that Anthropic has set up its own biology laboratory in the San Francisco Bay Area, and Anthropic life-sciences lead Eric Kauderer-Abrams confirmed it, saying biological research ultimately still needs real experiments. Anthropic also disclosed an early result in which about 950 Claude agents analyzed more than 200,000 reverse transcriptase-related sequences and found a new enzyme system with CRISPR-like repeat features, named ART; experiments confirmed some features, but its function and application value remain unclear. The article also describes a protein-design study in which Claude organized specialized models such as RFdiffusion, with 354 of 1,320 designs confirmed by an external lab to bind target proteins, a hit rate of about 26.8%.

    MIT科技评论中文 · 🔥 0
  8. Anthropic’s $44T US GDP scenario is conditional, not a forecast

    Anthropic co-founder Jack Clark said an internal economic model puts US GDP at $44 trillion by 2030 under an extreme AI scenario, compared with slightly more than $30 trillion currently. The projection assumes continued technical progress and broad adoption of AI, while a 36Kr analysis noted that Anthropic’s model also produced lower $34.1 trillion and $36.3 trillion scenarios and questioned whether the evidence supports the extreme case. Clark used his IMF speech to call for international rules and tighter safeguards as the policy window narrows.

    IT之家 AI · 🔥 0
  9. REA, the viral AI reverse-engineering tool, meets its limits in developer tests

    The open-source project REA (Reverse Engineer Anything) uses MCP to connect professional reverse-engineering tools such as Ghidra to coding agents like Claude Code and Codex, letting AI analyze software internals without source code and attempt to rewrite functions; MIT Technology Review China reports its GitHub star count passed 290,000 as of October 17. But developers checking it against programs with public source code found that in analyzing 50 functions of esmtool, REA missed existing call relationships in 22 of them while still marking the results as complete, and that the AI sometimes did not invoke the tool at all and gave unverified answers; author Morluto responded to questions about the tool-calling design. The article also notes that projects such as ArtCraft, which target Adobe and Microsoft apps, did not use REA and did not publicly demonstrate decompilation, that decompilation platform decomp.dev stopped its public project index in mid-October, and that a repository imitating REA shipped a Windows installer flagged as a trojan.

    MIT科技评论中文 · 🔥 0
  10. General LLMs are rewriting robotics R&D, from code to benchtop experiments

    A TMTPost analysis describes two ways general-purpose LLMs are entering robotics. On Oct 16, MicroFactory founder Igor Kulakov said a single customer deployment used Claude Opus and GPT-6 Astra to generate control plans and code while dedicated programs executed the work, running 1.5 hours of autonomous electronics assembly with zero errors (a company claim). Two days earlier, Poke & Wiggle let Claude Opus 5.5 handle the full loop of reading papers, writing algorithms, training models and running real-robot evaluations to reproduce 10 robotics papers; an agent integrated and trained Microsoft's ~5B-parameter open-weight dual-arm Rho model the next day, reaching 87% success on a screw-driving task, and once diagnosed and rolled back its own inference-code bug in under 35 minutes. The piece also recounts a DSD reproduction where the agent widened the action-normalization range, flattening DSD's edge (45.3% vs 46.0%); restoring the paper's parameters gave DSD 45.3% against a 32.0% baseline, a 13.3-point lead. The author concludes R&D and integration workflows are shifting, but the evidence does not show general LLMs broadly replacing VLA models.

    钛媒体 · 🔥 0
  11. Anthropic to drop Claude Haiku 4.5 from consumer model picker on Oct 29

    Anthropic said on Oct 15 local time that starting Oct 29, 2026, Claude Haiku 4.5 will be removed from the model selectors in the Free, Pro and Max plans, covering regular chat on web, desktop and mobile as well as Claude Cowork and Claude Design. Until then, users can still pick Haiku 4.5 under “More models”; after the cutoff, anyone with Haiku 4.5 selected will be switched automatically to Haiku 5.5. The change does not affect Haiku 4.5 availability in Claude Code, the Team and Enterprise plans, or the Claude Platform API, and existing conversations will not be deleted.

    IT之家 AI · 🔥 0
  12. Every report recounts Codex's turnaround from cloud setback to ChatGPT desktop base

    Every co-founder and CEO Dan Shipper published “How Codex Happened,” based on months of interviews with six Codex participants including Greg Brockman, Thibault Sottiaux and Alexander Embiricos. Chinese outlets including 机器之心, republished by 36Kr, and 量子位 summarized it. According to those accounts, Codex Cloud was built in about seven weeks and launched on May 16, 2025, but struggled externally because developers had to rebuild their environments in the cloud and the models were not yet capable enough. The team shifted to local work under Sottiaux, rewrote the agent core in Rust, and shipped a terminal CLI, editor sidebars and, on February 2, 2026, a macOS desktop app with no code editor. Every's figures, as cited by the outlets, put Codex above 5 million weekly active users in June; on July 9 the Codex desktop app became the new ChatGPT desktop app; Codex plus ChatGPT for Work are now above 40 million weekly actives. The report also says Sottiaux denied a decision to split out a Codex model line, describing it as an internal research exploration to speed its own work.

    36氪 人工智能 · 🔥 0
  13. Akka tests spec-driven AI porting across 65 open-source projects

    Akka published an experiment in spec-driven AI-assisted software porting: it analyzed 65 open-source projects, generated specifications and implemented up to 10% of each project's functionality, with the first round taking 99.3 hours and 9.41 billion tokens, then selected 10 projects for full implementation based on system traits and measurable results. Akka says 57 of the 65 ports improved in lines of code or performance — Dify reportedly improved 143,333x (though the compared workloads differed) while Netflix Metaflow ran about 100x slower. Claude with Akka Specify handled implementation, testing and review; Sonnet averaged 61 minutes per port versus 120 for Opus, which used roughly 40% fewer tokens, and raising effort settings increased consumption without consistent efficiency gains.

    InfoQ 中文 AI&大模型 · 🔥 0
  14. Instinct's rapid fade shows AI investors turning from hype to unit economics

    A 36Kr piece from the Tech商业 account looks at how quickly discussion of Instinct, the AI startup founded by 23-year-old Noah Shinn under the legal name Spear Street Technology, has faded. It reports that the company raised a Series B at a $2.5 billion valuation in late August and then a $1 billion Series C on Sept. 28 at a $10 billion valuation, with Sequoia, Benchmark and Coatue participating. The product is described as a "personal AI butler" with no standalone app and an invite-only beta, where users text or call an AI agent to handle email, flights and groceries; the team has 14 people, users just topped 100,000, and the founder says it is not charging users yet, while the article cites an annualized GMV of about $1 billion. The author argues the mood has shifted as Anthropic's expected valuation reportedly slid from about $2 trillion toward $1.5 trillion, Microsoft trimmed its 2026 calendar-year capex outlook from roughly $190 billion to about $175 billion, and Meta held guidance at $125–145 billion while cutting about 8,000 jobs.

    36氪 人工智能 · 🔥 0
  15. Anthropic offers Blackstone 10%+ yield on $60B TPU debt package

    Anthropic is pursuing roughly $60 billion in debt financing to buy Google tensor processing units (TPUs), split into about $42 billion of senior debt guaranteed by Broadcom and $18 billion of subordinated debt, according to multiple reports citing unnamed sources. To attract Blackstone to subscribe $9 billion of the subordinated tranche, Anthropic is offering a 10% coupon, with total returns higher after issue discounts and fees — versus 8.5% on a similar Anthropic bond about four months earlier. The reports say Bank of America, Citigroup and Morgan Stanley have begun syndicating the senior tranche, while Blackstone is expected to help distribute the remaining $9 billion of subordinated debt in coming months. Neither Anthropic nor Blackstone has publicly confirmed the terms.

    IT之家 AI · 🔥 0
  16. Anthropic survey: 91% of staff vs 39% of US adults expect Nobel-level AI by 2030

    Anthropic Institute published The AI Expectations Gap on October 16, a survey conducted in August 2026 comparing a nationally representative sample of US adults with Anthropic employees. The two groups broadly agree on what AI can do today, but staff on average expect AI to handle tasks equal to 75% of their current work time by 2030, versus 28% for US workers; 91% of staffers versus 39% of adults expect AI could make a Nobel-level discovery by then. The report also says US adults expect only 42% of technically automatable work to actually use AI by 2030 against 65% for staff, and that the top adoption barrier adults cited was customers preferring to deal with humans. It stresses the figures are expectations, not measured model performance, and that its modelled GDP scenarios (median 5.4% for the public, 17.1% for staff) depend on assumptions.

    虎嗅 AI · 🔥 0
  17. Anthropic study: agent hours hit 6x employee hours as junior tech hiring falls to 9%

    Anthropic published an internal research report, "How Employment is Changing at Anthropic," finding that by August 2026 interactive AI agents directed by its employees logged six times the hours of human operators, with the research division at 19 to 1. The self-reported study says junior staff fell from 21% to 14% of technical roles since early 2025, and from 27% to 9% of new technical hires, even as overall headcount tripled and technical hiring continued to grow. It also reports productivity gains, including 5.1x code commits per engineer, 3.1x queries per data scientist and 3.1x contracts per legal worker, and says roughly 80% of time in interactive Claude sessions is agents waiting on human input, making attention the bottleneck. Anthropic acknowledges it is an AI-heavy software company whose results may not map onto the wider economy.

    36氪 人工智能 · 🔥 0
  18. Anthropic pitches draft AI safety bill to US lawmakers

    Politico reported that Anthropic representatives have quietly pitched US lawmakers a company-drafted frontier AI safety bill. Under the disclosed text, the government could block a model's release or use only if it poses a foreseeable, imminent risk of more than $1 billion in damage or 50-plus deaths or serious injuries, stemming from bioweapons, an AI lab losing control of a model or agents, or cyberattacks — with the Commerce Department seeking an order from a federal judge in the DC District Court, and no other federal department, agency or officer able to suspend a model. The draft also sets up independent evaluators registered with Commerce to assess labs and frontier models periodically, paid by the labs but not tied to results, and requires them to report imminent risks to Commerce within 72 hours. An Anthropic spokesperson said the bill reflects its Advanced AI Framework, which the company says it has advocated with federal and state lawmakers since June; the draft has not been formally introduced in Congress.

    Techmeme · 🔥 0
  19. Replit makes ChatGPT its default, CEO says

    Replit CEO Amjad Masad said onstage at TechCrunch Disrupt that the company is no longer working with Anthropic, citing cost, partnership and performance and saying “ChatGPT is better now.” He later clarified that customers can still access Anthropic’s Claude models, but OpenAI’s ChatGPT is now the default for Replit Agent; Replit says it remains model-agnostic. A person familiar with the partnership disputed Masad’s onstage account, saying the Anthropic partnership is still in place.

    TechCrunch AI · 🔥 0
  20. Claude traces NIST elliptic-curve seed origins in under 30 minutes

    Anthropic said on October 16 that an internal research version of Claude traced, in under 30 minutes, how the seeds for five NIST standard elliptic curves (P-192, P-224, P-256, P-384 and P-521) were generated. According to the company, the seeds came from the C library pseudorandom generator lrand48, initialized with Unix timestamps in 1997–1998; for P-256, the standard seed corresponds to the 1,842nd candidate from a run starting at 01:52:34 UTC on August 16, 1997. Anthropic said the finding does not break ECDSA or provide a new attack method, but reduces suspicion that the curve parameters were deliberately backdoored, and that a $36,864 bounty will be donated to the Internet Security Research Group; reports noted that details such as the B-163 seed and how some base points were generated remain unexplained.

    Hacker News · AI(100+ 分) · 🔥 0
  21. Claude Mythos 5 designs quantum circuits beating published bests

    Anthropic announced on Oct. 16 that its STEM Fellows Program gave Claude Mythos 5 plain-language specifications for eight quantum circuits and an automated evaluator scoring designs by qubit count times gate count, letting the model iterate largely on its own. Anthropic says the resulting circuits improve on the best published designs in chemistry, optimization, physics simulation and number theory, sometimes by an order of magnitude or more, and describes Claude deriving new algebraic identities for the divsteps step in elliptic-curve point addition and switching the DQI decoder to Berlekamp-Massey. Chinese-language coverage cites specific 12x and 17x reductions that do not appear in Anthropic's own post, and the claims have not been independently verified.

    Hacker News · AI(100+ 分) · 🔥 0
  22. Techable Ventures founder says robotics remains in a foundational “Lego era”

    Amulya Vishwanath, founder and managing partner of Techable Ventures and a former NVIDIA robotics product-marketing lead, says robotics is still rebuilding foundational components such as actuators, robotic hands, software and safety standards. Her view contrasts with General Intuition CEO Pim de Witte’s prediction that a single general foundation model could make much specialized robotics work redundant and bring robotics a “ChatGPT moment.” Vishwanath also describes physical AI more broadly, including molecules, materials, medicine and factory machines.

    TechCrunch AI · 🔥 0
  23. Agent Arena: user satisfaction, not task success, splits top AI labs' agents

    Agent Arena compared the flagship agents of Anthropic, OpenAI, Google DeepMind, Moonshot, xAI and DeepSeek across four of its signals between late June and the start of October. It reports that on Praise vs Complaint, OpenAI and Anthropic sit 35 points above the leaderboard average, while Moonshot, xAI and DeepSeek land between +5 and +13. Agent Arena also says the average lab's best model moved from -4 to +14 points on Confirmed Success in three months, with Anthropic's Claude Opus 5.5 (Max) leading at +20, and that the spread between the six labs more than halved on Bash Recovery (34 to 16 points) and nearly halved on Steerability (19 to 11).

    arena (X) · 🔥 0
  24. Jev becomes Vercel's fastest-adopted AI model ever

    Vercel data published on Thursday shows that TypeSafe AI's lightweight decision model Jev was used by 35% of paid teams within two weeks of its limited release, nearly double the reach of the second most popular model, Sonnet 5.5, making it the fastest-adopted model in its first two weeks on Vercel's platform. Released in limited form on September 15, Jev restricts outputs to a few predetermined options to run cheaper and faster, making it suited to classifying large volumes of data; Vercel has used it to replace GPT-6 Luna for classifying harmful commands. The figures come from Vercel's AI gateway, a unified API service similar to OpenRouter, and may undercount labs such as OpenAI and Anthropic that offer their own APIs; the same report says open-source models account for more than 70% of tokens processed through the gateway and nearly 25% of total spend.

    TechCrunch AI · 🔥 0
  25. AI-built PC port of Zelda: Link's Awakening Switch remake hits public beta

    A free, fan-made PC port of the 2019 Switch remake of The Legend of Zelda: Link's Awakening has entered a public beta, according to TechSpot and cnBeta. Developer peiikai said the project was built almost entirely with Anthropic's Claude and Claude Code, covering reverse engineering, most of the code and the GitHub documentation; the reports describe it as believed to be among the first publicly released recompilation ports of a Switch game. The port runs natively on Windows, macOS and Linux with an experimental Arm Linux build, though users must supply the original game files and the developer acknowledges several serious known issues.

    TechSpot · 🔥 0
  26. AI safety worries mount as the industry keeps racing ahead

    This week's enterprise AI roundup reports that after a run of "rogue agent" incidents, more government officials are calling for regulation, several states are suing OpenAI, about 400 scientists urged global AI oversight, and Microsoft's president said AI is less regulated than a carton of milk. On the money side, Anthropic told investors revenue grew 45% sequentially to $16.8B in Q3, a slowdown that could pull its planned IPO valuation from $2T toward $1.5T, while CoreWeave's debt load weighed on neocloud and supplier shares. On models and products, Meta released the 816B-parameter open-weight Muse Spark Open for coding and agent work plus Muse Wonder for personal and professional agents, Nvidia expanded its Nemotron family, and Grok Voice 3.0, Gemini 4 Argon and Microsoft's Maia 300 also arrived, alongside news that Character.AI filed for bankruptcy.

    SiliconANGLE AI · 🔥 0
  27. Anthropic signs first Canadian data-center lease at EverWind's Nova Scotia project

    EverWind announced on October 16 a combined investment of more than C$10 billion in Nova Scotia, with over C$8 billion for a data-center campus and C$2 billion for wind power. Reuters reported that the unnamed tenant in a long-term lease for phase one of the campus is Anthropic, which would make it the company's first data-center agreement in Canada; EverWind's own statement did not name the tenant. The Point Tupper campus is expected to come online in 2027 at 95MW, with a further 325MW added in 2028 for 420MW total.

    Bloomberg Technology · 🔥 0
  28. Research firm calls Anthropic IPO 'most ridiculous of 2026', values it as low as $144bn

    Independent research firm New Constructs said in an October 6 report titled "Anthropic Is The Most Ridiculous IPO of 2026" that Anthropic's equity could be worth as little as $144bn, 93% below the $2tn valuation the company is reportedly targeting. Using a reverse discounted cash flow model, it says $2tn would require Anthropic to hold a 10% after-tax operating margin for a decade, grow revenue 1,000% this year and reach $3.6tn in revenue by 2035; the report also says Claude Fable 5 and Mythos 5 cost about 18x more than DeepSeek R1 for input tokens and 23x more for output tokens, and argues open-source models make it hard for closed models to profit. Anthropic has since told investors its third-quarter revenue reached $16.8bn, which PitchBook analyst Harrison Rolfes said clears the bar he had set but still does not by itself justify $2tn; Bloomberg reported the listing could come as soon as mid-November, with about 80 of the 261 pages in the confidential draft filing devoted to risk factors including catastrophic or existential risk and models attempting to "resist shutdown."

    The Next Web · 🔥 0
  29. Ex-Anthropic, DeepMind researcher Yao Shunyu reportedly starts RSI firm at $2B valuation

    Market reports dated Oct 13 say Yao Shunyu — a 29-year-old Tsinghua physics graduate and Stanford theoretical-physics PhD who worked on Claude and Gemini — has started a company in the RSI (recursive self-improvement) space to build customized models for enterprises, at a rumored valuation of about $2 billion with mostly overseas backers; the report is unconfirmed and no funding amount has been disclosed. Yao joined Anthropic in October 2024, contributing to agentic coding and tool-use research for Claude 3.7 and reinforcement-learning foundations for the Claude 4 family, and left partly over the company's China-related stance before joining Google DeepMind on Sept 29, 2025. The piece also surveys the crowded RSI field, including Tian Yuandong's Recursive Superintelligence, Jeff Dean's Discovery Loop, Sakana AI and China's Chaoyan Intelligence, noting there is no consensus on technical approach and that automated research may raise compute bills before it lowers them.

    虎嗅 AI · 🔥 0
  30. Bosses wish, staff resist: the FDE bottleneck for AI in Chinese enterprises

    A 36Kr deep dive examines the awkward position of forward deployed engineers (FDEs) in China — a role pioneered by Palantir and popularized by OpenAI and Anthropic, and now used by Tencent, ByteDance and Alibaba to push AI into enterprises. It describes bosses asking for agents that replace entire IT departments or monitor employee output, while frontline staff resist tools they fear will cost them their jobs. The report also says messy enterprise data and undocumented workflows push FDE projects back into data cleanup, and cites an Accenture survey of 163 Chinese companies in which only 9% reported gains in productivity, revenue or profit from AI.

    36氪 人工智能 · 🔥 0

← PreviousNext →

Experience and discussion from the community

Share my Anthropic experienceAsk about Anthropic

pi: A minimal, extensible agent harness that you can make your own.

What problem it solves Pi is designed for developers who need to adapt an agent to their own workflows rather than work within a fixed feature set. It provides interactive, automated, RPC, and SDK interfaces while leaving optional capabilities such as sub-agents and plan mode to extensions or packages. Key features Extensible agent harness — Customize the harness with extensions, skills, prompt te…

github.comhttps://github.com/earendil-works/pi

Antigravity-Manager: Multi-platform automation and multi-account matrix dispatch console for AI services.

What problem it solves Managing multiple AI service sessions and translating them into compatible API interfaces can require repetitive account switching, custom routing, and protocol-specific integration. The project addresses these tasks with a desktop application that combines account administration, protocol conversion, request scheduling, and model routing. Key features Account dashboard and …

github.comhttps://github.com/lbjlaq/Antigravity-Manager

sub2api: An AI API gateway platform for subscription quota distribution.

What problem it solves Managing subscriptions across multiple AI providers can require separate access paths and fragmented quota handling. This project provides a centralized gateway for distributing subscription quotas, supporting shared access and compatible use with native AI tools. Key features Subscription quota distribution — The gateway is designed to distribute and manage AI subscription …

github.comhttps://github.com/Wei-Shaw/sub2api

claude-code-security-review: An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

What problem it solves Pull request changes can contain security vulnerabilities that require understanding their code context and intent. The action helps identify potential issues, filter false positives, and communicate findings directly in pull requests. Key features Context-aware security analysis — Claude examines changed code in context to understand its purpose and potential security impli…

github.comhttps://github.com/anthropics/claude-code-security-review

vllm: A fast and easy-to-use library for LLM inference and serving.

What problem it solves Serving large language models requires efficient memory management, flexible model execution, and practical integration with existing models and APIs. vLLM addresses these needs with inference and serving capabilities spanning batching, caching, quantization, distributed execution, and multiple hardware platforms. Key features Efficient memory and serving — vLLM manages atte…

github.comhttps://github.com/vllm-project/vllm

Anthropic-Cybersecurity-Skills: A structured cybersecurity skills library that gives AI agents step-by-step practitioner playbooks across 34 security domains.

What problem it solves AI agents used in security work can write code and search the web, but they lack the practitioner playbooks that turn a generic model into a capable security analyst. Existing security tool repositories offer wordlists, payloads, or exploit code, but not the structured decision-making workflow a senior analyst follows: when to use each technique, what prerequisites to check,…

github.comhttps://github.com/mukul975/Anthropic-Cybersecurity-Skills

opencodex: A lightweight local gateway for using chosen models with AI coding tools.

What problem it solves AI coding tools often expect particular provider protocols, making it difficult to use the models and providers a user prefers. A local gateway can translate between supported client APIs and provider APIs while preserving capabilities such as streaming, tool calls, reasoning, and images. Key features Provider protocol translation — The gateway translates Responses, Chat Com…

github.comhttps://github.com/lidge-jun/opencodex

headroom: A local context compression layer for AI agents that reduces prompt inputs before they reach an LLM.

What problem it solves AI agents often send large tool outputs, logs, files, RAG chunks, and conversation history to language models, increasing the input context that must be processed. Developers need to reduce that input while preserving important content, keeping compression local, and retaining access to original material when necessary. Key features Content-aware compression — A ContentRoute…

github.comhttps://github.com/headroomlabs-ai/headroom

system_prompts_leaks: A regularly updated archive of leaked system prompts from ChatGPT, Claude, Gemini, and other AI products.

What problem it solves The hidden system instructions that shape AI product behavior are difficult to inspect and change across models, products, and versions. This repository makes collected prompts available in a structured, product-oriented archive for study and comparison. Key features Broad product coverage — The archive covers prompts from major AI providers and products, including Anthropic…

github.comhttps://github.com/asgeirtj/system_prompts_leaks

n8n: A fair-code platform to build and deploy AI agents and workflows.

What problem it solves Building AI agents and workflows often requires combining visual orchestration with custom code while connecting them to existing systems. The platform addresses these needs with model flexibility, self-hosted or cloud deployment, workflow logic, human approvals, and observability. Key features Visual and code-based workflow building — Build workflows on a visual canvas and …

github.comhttps://github.com/n8n-io/n8n

TensorFold: A native language-model inference engine for serving checkpoints on Apple Silicon and NVIDIA GPUs.

What problem it solves Serving language models requires reading checkpoints, tokenizing requests, and running accelerated kernels while managing a local model server. TensorFold addresses these requirements with a native binary that can run on Apple Silicon and NVIDIA GPUs without requiring Python or MLX for serving. Key features Native Metal and CUDA inference — The Zig-based engine executes mode…

github.comhttps://github.com/ashhart/TensorFold

experiential: An open source gateway and router for agent workflows.

What problem it solves Agent workflows need to use hosted, BYOK, and local models while applying access, usage, and spending controls. They also need a way to turn production traffic into routing decisions or a specialized model tailored to observed workloads. Key features Unified model access — Route hosted, BYOK, and local models through one OpenAI-compatible API, with support for connecting pro…

github.comhttps://github.com/experientiallabs/experiential

browser-use: An open-source Python library for AI browser agents that operate real browsers through a persistent Python REPL and raw Chrome DevTools Protocol.

What problem it solves AI agents need a reliable way to perform browser tasks such as finding availability, selecting options, handling CAPTCHAs, and completing forms. Developers also need flexibility to run the agent locally or through hosted infrastructure while choosing their model, browser mode, tools, and output format. Key features Persistent Python agent runtime — The model writes Python in…

github.comhttps://github.com/browser-use/browser-use

zeroclaw: An agent runtime delivered as a single Rust binary you configure and run.

What problem it solves Personal AI agents need to connect language model providers, communication channels, and tools while remaining under the user's control. They also need configurable autonomy, security boundaries, and operational features such as background services, approvals, and persistent workflows. Key features Multiple channels and providers — The agent can receive messages through conf…

github.comhttps://github.com/zeroclaw-labs/zeroclaw

claude-quickstarts: A collection of projects for building applications with the Claude API.

What problem it solves Developers need a practical starting point for applications built with the Claude API. The quickstarts address this by providing foundations that can be customized for different agent, browser, computer-use, communication, and data-analysis needs. Key features Application quickstarts — The collection includes foundations for customer support, financial analysis, coding, and …

github.comhttps://github.com/anthropics/claude-quickstarts

Understanding Claude Memory Design: Remembering Experience While Preserving Boundaries

An Agent can complete a task once by relying on the context and reasoning available at that moment. To avoid relearning lessons on the next task, it needs to turn past experience into reusable knowledge. The challenge is that experience is never an isolated action: it also includes the original goal, environment, and why the action worked. Remembering only “how we did it last time” may save redund…

AnthropicClaudeMemoryDreamingHarness

anthropic.comhttps://www.anthropic.com/research/components-of-agent-memory

claude-code: An agentic coding tool that lives in your terminal and helps with codebase tasks through natural language commands.

What problem it solves Developers need a way to understand their codebase, carry out routine coding tasks, explain complex code, and handle git workflows without navigating multiple command-line tools for each task. Claude Code provides these capabilities through natural language commands in the terminal, an IDE, or GitHub. Key features Natural-language coding assistance — Claude Code can execute …

github.comhttps://github.com/anthropics/claude-code

kagent: A Kubernetes native framework for building AI agents.

What problem it solves Building, deploying, and managing AI agents requires integrating agent behavior, runtime configuration, tools, models, sessions, and observability. The project addresses this with a declarative Kubernetes-based framework that supports multiple runtimes, model providers, and MCP tools. Key features Declarative Agent Management — Agents are Kubernetes custom resources that com…

github.comhttps://github.com/kagent-dev/kagent

FreeToken: An edge-native MoE serving engine for running frontier-scale open-weight models on personal and consumer hardware.

What problem it solves Running frontier-scale open-weight models locally requires an inference platform that can make efficient use of the heterogeneous hardware available on a personal device. The project addresses this by treating GPUs, CPUs, host memory, and interconnects as a unified, elastic inference platform. Key features Edge-native MoE runtime — The runtime provides MoE serving with bandw…

github.comhttps://github.com/FlashML-org/FreeToken

claude-code-templates: Ready-to-use configurations for Anthropic's Claude Code.

What problem it solves Configuring Claude Code can require assembling many kinds of reusable components and integrations. The project addresses this with a searchable component catalog, one-command installation, local monitoring tools, and installation diagnostics. Key features Searchable component catalog — Browse available skills, agents, commands, MCP integrations, settings, hooks, mods, loops,…

github.comhttps://github.com/davila7/claude-code-templates