标签：#pens

reconmatch is a local-first transaction matching engine for accountants, bookkeepers, and controllers. Two CSVs in — books vs bank, invoices vs payments — a scored, auditable match report out. No account, no upload, no network call. Repo: github.com/SybilGambleyyu/reconmatch The unglamorous pain If you close books for a living, you already know the scene: two windows open, a bank CSV on the left, a general-ledger export on the right, and an afternoon disappearing into "which deposit is which invoice." Bank feeds help until they do not. The hard cases are ordinary: One deposit that covers three invoices Two payouts that sum to one sales batch on the books A check number in the memo on one side and a dedicated column on the other "ACH ACME CORP INV 1042" vs "Invoice payment ACME Corp" An orphan the feed never explained Enterprise close tools charge enterprise prices and want the data in their cloud. For a CPA firm or bookkeeper sitting on confidential client ledgers, "just upload the CSV" is often a non-starter. Spreadsheet VLOOKUP falls over on partial payments and batch deposits. What reconmatch does Matching runs in deterministic phases so the same inputs always produce the same proposals: Exact / reference-strong — amount within tolerance, date in window, shared invoice/check/wire token Amount + date — numbers line up even when memos are noise Fuzzy description — token overlap plus sequence similarity (pure Python stdlib) Group 1:N and N:1 — one line equals the sum of several on the other side Every accepted match carries a score and human-readable reasons suitable for a workpaper. Unmatched lines stay unmatched — the tool does not invent a story for them. pip install git+https://github.com/SybilGambleyyu/reconmatch.git reconmatch books.csv bank.csv -o ./march-recon Outputs: plain-text report, matches CSV, unmatched CSV, and full JSON. Zero required third-party dependencies. Python 3.10+. Library use from reconmatch import MatchConfig , match_transactions from rec

Most agent projects do not fail because the first model call is difficult. They become difficult when the prototype needs memory, tools, evaluation, a user interface, documentation that coding agents can navigate, and a repeatable review process. That is the problem the open-source AgentsKit ecosystem is trying to solve for JavaScript teams. It is a set of independent projects with shared contracts, rather than one application that must own the whole stack. The six public pieces 1. AgentsKit: the composable foundation AgentsKit provides focused JavaScript and TypeScript packages for runtimes, adapters, tools, skills, memory, RAG, evaluation, observability, sandboxing, and UI bindings. Its core has zero runtime dependencies and a CI-enforced 10 KB gzipped budget. Six formal contracts keep adapters, tools, memory, retrievers, skills, and runtimes substitutable. You can run a first local agent without an API key: npm install @agentskit/core @agentskit/runtime tsx Then connect OpenAI, Anthropic, Gemini, Ollama, or another adapter without changing the rest of the runtime composition. 2. AgentsKit Chat: one interaction model, seven renderers AgentsKit Chat defines an interactive agent experience once and renders it through React, React Native, Ink, Vue, Svelte, Solid, or Angular. It also supports deterministic local answers before an optional backend call. That matters for documentation and support interfaces where exact project facts should not require an LLM. pnpm dlx @agentskit/chat-cli@0.4.0 init my-chat --renderer react --yes 3. Registry: reusable source, not another dependency The AgentsKit Registry distributes ready-to-use agents in a shadcn-style model: the CLI copies the source into your project, so you can inspect and modify it. npx agentskit add research npx agentskit add code-review The public catalog currently includes research, code-review, and knowledge-promotion agents, and is open to contributions. 4. Agents Playbook: engineering rules that can execute Ag

Meituan's LongCat team shipped a quiet but meaningful update to its open-source talking-avatar stack: version 1.5 swaps the audio encoder, distills sampling down to 8 steps, and adds an INT8 path to fit the model on tighter GPUs. Here's what actually changed under the hood, and which flags you now have to pass. LongCat-Video-Avatar 1.5: DMD2 distillation, Wav2Vec2 replacement, and INT8 offloading LongCat-Video-Avatar 1.5 is an audio-driven talking-avatar generator that turns one portrait plus an audio clip into a lip-synced video with head motion, expression, and body dynamics. Released May 21, 2026, it is an avatar head built on the 13.6-billion-parameter dense LongCat-Video diffusion transformer [base model, Oct 2025]. The headline change: v1.5 replaces the Wav2Vec2 audio encoder used in v1.0 (Dec 16, 2025) with Whisper-Large-v3, which the team attributes to smoother, more natural lip dynamics. Three new flags define the v1.5 workflow, none of which exist in v1.0: Flag What it does Notes --use_distill Enables DMD2-based step distillation, collapsing generation to 8 NFE Mandatory for v1.5 — omitting it falls back to the full-chain v1.0 sampling schedule, not an 8-step path --use_int8 Loads the 13.6B dense DiT in INT8 to cut VRAM pressure Main lever for consumer GPUs --resolution Selects 480P or 720P output New in 1.5 Under the hood, the technique report describes Cross-Chunk Latent Stitching, which removes redundant VAE decode/encode cycles between autoregressive chunks, enabling seamless minutes-long generation without re-encoding overhead [arXiv:2605.26486]. That matters for long-form output where earlier tools drift or stutter at chunk boundaries. One caveat worth flagging before you invest a GPU-hour: Meituan claims parity-or-better results versus HeyGen, Kling Avatar 2.0, and OmniHuman-1.5 across 508 image-audio pairs, 770 crowdsourced evaluators, and 13,240 judgments [human-eval benchmark]. That evaluation is entirely author-controlled and reported as win-rat

A few weeks ago I wrote about describing your site once so any AI can use it. Since then the thing I was hand-waving at ("agents will check out for users") stopped being hypothetical. OpenAI shipped ACP and Google shipped AP2, and they solve the same problem in almost opposite ways. I implemented the merchant side of both. Here are the field notes, because the differences aren't obvious until you're in them. The 30-second version ACP (Agentic Commerce Protocol, OpenAI + Stripe) is session-based. The agent drives a live checkout session on your server, like a headless cart. It powers ChatGPT's Instant Checkout. AP2 (Agent Payments Protocol, Google) is mandate-based. Your store signs a "here is the cart and the price" object; the buyer's agent signs a "I authorize this" object. It leans on verifiable credentials and now the FIDO Alliance. Same goal. Completely different shape. ACP: a checkout session you don't own the UI for ACP is five REST endpoints and a state machine. The agent creates a session, updates it (address, shipping, coupon), and completes it: POST /checkout_sessions create from line items POST /checkout_sessions/:id update (address, shipping, discounts) POST /checkout_sessions/:id/complete pay What you return is a CheckoutSession: line items, live shipping options, and totals broken out (subtotal, discount, fulfillment, tax, total). Money is integer minor units (330 = $3.30). Payment completes when the agent hands you a Shared Payment Token and you charge it through Stripe. The card never touches the agent. The mental model: it's your existing checkout, minus the browser. AP2: sign the cart, don't run the session AP2 has no session. The agent sends you an Intent Mandate ("a red basketball shoe, under $120"). You price it and return a Cart Mandate you have cryptographically signed: { "contents" : { /* a W 3 C PaymentRequest: items , total , currency */ }, "merchant_authorization" : "<RS256 JWT>" // iss , sub , aud , exp , jti , cart_hash } That JWT is a

Most "AI agent" libraries fall into one of two buckets. Either they're a big framework you spend an afternoon configuring, or they're a tiny toy that drops the one feature you actually need in production: the ability to stop and ask a human before the agent does something you can't undo. I wanted the middle. So I wrote yieldagent : a small agent loop you can read end to end, with human-in-the-loop pause/resume built in, and no runtime dependencies. This post walks through how it works and why it's built the way it is. What an agent loop actually is Strip away the branding and an "agent" is a loop: Send the conversation to the model, along with the tools it's allowed to call. If the model asks to call a tool, run it and append the result. Repeat until the model answers without asking for a tool. That's it. The model decides the control flow at runtime; your job is to run the tools and feed the results back. Here's the core, lightly trimmed: for ( let step = 0 ; step < maxSteps ; step ++ ) { const reply = await call ( messages , toolSpecs ); messages . push ( reply ); if ( ! reply . tool_calls ?. length ) { yield { type : " final " , text : reply . content , messages }; return ; } for ( const tc of reply . tool_calls ) { const args = JSON . parse ( tc . function . arguments ); const result = await tools [ tc . function . name ]. run ( args ); messages . push ({ role : " tool " , tool_call_id : tc . id , content : JSON . stringify ( result ) }); } } Everything else in the library is in service of making this loop observable, testable, and safe to run against the real world. Why an async generator Notice the yield . The loop is an async generator, so the caller drives it: for await ( const step of agent ({ call , tools , messages })) { if ( step . type === " tool-start " ) console . log ( " -> " , step . tool , step . args ); if ( step . type === " final " ) console . log ( step . text ); } Every step (each tool call, each result, and the final answer) is handed back to

Open-source LLMs stopped being the budget option in 2026. Kimi K3 sits level with Claude Opus 4.8 on the Artificial Analysis Intelligence Index (its hosted API is live; the weights themselves are expected by July 27), GLM-5.2 held the top open-model spot before it, and the field behind them is deep enough that the hard part is choosing. This ranking covers the nine best open-weight models right now — on license, context window, hardware reality, and the per-token price you actually pay. Every one of them is available through LLM Gateway with one key, at each provider's published rate, so you can A/B any two of them by changing one word in a request. 1. Kimi K3 — the open frontier Moonshot AI · 2.8T params · 1M context · $3.00 / $15.00 per M The largest open-weight model ever announced — with one caveat: the weights are not downloadable yet. Moonshot expects to release them by July 27, 2026, and the license is still unannounced; the hosted API has been live since July 16. Ranks 4th of 189 models on the Artificial Analysis Intelligence Index — tied with Claude Opus 4.8 and GPT-5.5 — and took first place in Arena's blind Frontend Code testing. Always-on reasoning, vision, tools, and output configurable up to 1M tokens. The open model to beat, priced accordingly. Full breakdown here . Best for: teams that want closed-frontier quality with open-weight freedom. 2. GLM-5.2 — the value flagship Z.ai · 744B params · 1M context · $1.40 / $4.40 per M MIT-licensed, weights on Hugging Face, and the top-ranked open model until K3 arrived. A real 1M-token context, strong agentic-coding results, and built-in web search support — with output at under a third of K3's rate and input at about half. Also the largest model on this list that fits a single 8-GPU node (or one 512 GB Mac Studio) at INT4. Best for: the best capability-per-dollar in the open field. 3. DeepSeek V4 Pro — frontier scale at commodity prices DeepSeek · 1.6T params (49B active) · 1M context · $0.435 / $0.87 per M MI

Kimi K3 is the first open-weight model that makes the Kimi K3 vs Claude Opus 4.8 question worth asking seriously. On the Artificial Analysis Intelligence Index, K3 ranks fourth of 189 models — level with Opus 4.8 and GPT-5.5, behind only Claude Fable 5 and GPT-5.6 Sol. It also costs 40% less per token, and its weights are expected to be released by July 27. The honest answer is not "K3 wins" or "Opus wins" — it depends on what you're optimizing for. Here are the numbers, then the verdict. Benchmarks: Kimi K3 vs Claude Opus 4.8 Benchmark Kimi K3 Claude Opus 4.8 Artificial Analysis Intelligence Index 57 (4th/189) statistical tie GPQA Diamond 93.5% 93.6% Terminal-Bench 2.1 88.3%* 74.6%* SWE-bench Verified not published 88.6% Arena Frontend Code 1st (1,679) ranked below *Reported on different harnesses (Opus 4.8's score uses the Terminus-2 harness), so treat the Terminal-Bench gap as directional, not exact. Three takeaways. On graduate-level reasoning (GPQA Diamond) the models are statistically tied. On agentic terminal work, K3's published number is well ahead, with the harness caveat above. And in Arena's blind Frontend Code testing, developers ranked K3 first outright — ahead of every model, including Anthropic's. Where Opus 4.8 keeps an edge: SWE-bench Verified at 88.6% is a published, battle-tested result K3 has no counterpart for yet, and Anthropic's models remain the default target for agent harnesses — Claude Code, MCP tooling, and most agentic scaffolds are tuned against Claude first. K3 is three days old; its ecosystem is not. Pricing: 40% cheaper across the board Per-token rates through LLM Gateway (each provider's published pricing): Per million tokens Kimi K3 Claude Opus 4.8 Input $3.00 $5.00 Cached input $0.30 $0.50 Output $15.00 $25.00 Both have a 1M-token context window. K3's output limit defaults to 131K tokens but is configurable up to the full 1M in a single response; Opus 4.8 caps output at 128K. Concrete math: a coding-agent workload of 100M input a

Moonshot AI released Kimi K3 on July 16, and the benchmarks put an open-weight model next to the best closed ones for the first time. The catch is access. K3 sits on Moonshot's platform, GLM-5.2 on Z.ai's, DeepSeek V4 Pro on DeepSeek's, MiniMax M3 on MiniMax's — four accounts, four billing relationships, four API dashboards, all before you have written a line of code. LLM Gateway routes every one of them through a single OpenAI-compatible endpoint. One key, one bill, and a switch between Kimi K3 and any of 200+ models is a one-word change to your request. What is Kimi K3? Kimi K3 is Moonshot AI's flagship model for long-horizon coding and agentic work. At 2.8 trillion parameters — a mixture-of-experts design that activates 16 of its 896 experts per token — it is the largest open-weight model announced to date. Moonshot has committed to publishing the full weights by July 27, 2026. The specs that matter in practice: 1M-token context window (1,048,576 tokens), with output configurable up to the same 1M — enough to hold a large repository plus its docs in a single request Always-on reasoning — K3 thinks before every answer; there is no non-thinking mode Vision, tool calls, and JSON output supported out of the box Prompt caching at a 90% discount on repeated input Early results back up the size. K3 ranks fourth of 189 models on the Artificial Analysis Intelligence Index — level with Claude Opus 4.8 and GPT-5.5 — and took first place in Arena's Frontend Code evaluation in blind developer testing. It posted 93.5% on GPQA Diamond and 88.3% on Terminal-Bench 2.1, the strongest open-weight results published on both at release. Kimi K3 pricing Through LLM Gateway you pay Moonshot's published per-token rates: Tokens Price per million Input $3.00 Cached input $0.30 Output $15.00 The cached-input rate is the number to watch. Coding agents re-send the same system prompt, file context, and conversation history on every step, so in a long agent session most of your input tokens are

You followed an old breeding guide. You put Penking + Bushi into your breeding farm, dropped the cake, waited for the egg... and out hatched Sibelyx , not the Anubis the guide promised. You're not alone. Your guide isn't broken. The recipe changed. When Palworld hit 1.0, the breeding table got quietly rewritten. Almost every pairing that players had memorized from early-access now produces a different Pal. There's no in-game notice, no patch note that lists the hundreds of changed combos — just a lot of confused hatchings. So I dug into the data. Here's what I found, and the small tool I built to make sense of it. What actually changed in 1.0 I compared two snapshots of the game's breeding data — the pre-1.0 set and the current 1.0 release — both sourced from the open-source PalCalc project. The headline number: 97.7% of comparable pre-1.0 parent pairs now produce a different Pal. That's not a typo. If you take the breeding pairs that existed before 1.0 and run them against the current data, nearly all of them hatch something new. A few concrete examples players keep running into: Old recipe (pre-1.0) What it makes now (1.0) Penking + Bushi Anubis → Sibelyx ... (more pairs in the tool) The mismatch matters because most breeding guides and calculators on the internet still show the old results. Players follow them, breed, and get confused. The subtle trap: renumbering vs. real change There's a detail that trips up every breeding tool that tries to track this. When Palworld 1.0 launched, it also renumbered parts of the Paldeck (Pal #139 vs #116, etc.). A naive diff tool would see the number change and wrongly report "the breeding result changed!" — when really only the number changed, not the actual Pal. To avoid that false signal, I match Pals by their internal game name , not their Paldeck number. A renumbering is not mistaken for a changed breeding result. Only genuine recipe changes are counted. The tool: PalShift I wanted a dead-simple way to answer one question:

GitHub热门项目 | Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, and Hermes. | Stars: 2,511 | 165 stars this week | 语言: JavaScript

GitHub热门项目 | Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first. | Stars: 3,326 | 14 stars today | 语言: Rust

GitHub热门项目 | Web UI for the pi coding agent | Stars: 1,616 | 286 stars today | 语言: TypeScript

GitHub热门项目 | Expert-level WordPress knowledge for AI coding assistants - blocks, themes, plugins, and best practices | Stars: 1,901 | 7 stars today | 语言: JavaScript

GitHub热门项目 | A collection of AI agent skills for working with Expo projects and Expo Application Services | Stars: 2,286 | 55 stars today | 语言: JavaScript

GitHub热门项目 | Curated list of project-based tutorials | Stars: 274,500 | 276 stars today | 语言: Python

GitHub热门项目 | A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers. | Stars: 15,360 | 50 stars today | 语言: Python

GitHub热门项目 | Structured Outputs | Stars: 14,650 | 49 stars today | 语言: Python

GitHub热门项目 | | Stars: 12,083 | 14 stars today | 语言: Python

GitHub热门项目 | A skill for your coding agent to stop it from burying the answer. ADHD-friendly output. | Stars: 6,027 | 1,846 stars today | 语言:

How I Built a Full-Stack Quality Skill for AI Coding Agents AI coding agents are getting very good at writing code. But I kept running into the same problem: They can move fast, but without strong project rules they can also create messy architecture, duplicate utilities, inconsistent APIs, weak security checks, and frontend components that slowly drift away from the design system. So I built Full-Stack Quality Skill . It is a reusable AI coding skill for full-stack audits, architecture guidance, long-term project memory, and CI quality gates. Repo: https://github.com/lablnet/full-stack-quality-skill Website: https://skills.lablnet.com Why I Built It When I use AI agents like Cursor, Codex, Claude Code, Antigravity, or similar tools, I do not only want them to "write code". I want them to think like a careful senior engineer: Is the database normalized correctly? Are backend layers clean? Is business logic leaking into controllers? Are frontend components consistent? Are Vue components using composables? Are React components using hooks correctly? Are HTTP methods and status codes right? Is GraphQL safe from N+1 problems? Are security and privacy risks checked? Are tests missing for critical paths? Is documentation still matching the code? That is a lot to remember every time. So instead of repeating the same instructions in prompts, I turned them into a reusable skill. What It Covers The skill includes audit areas for: Database Backend Frontend Mobile HTTP APIs GraphQL Security Privacy Accessibility i18n Analytics Background jobs Infrastructure Testing Performance Observability Delivery / CI Multi-tenancy Payments Notifications Data import/export API compatibility Developer experience AI/LLM safety It also includes examples for common stacks: Node.js / TypeScript Python Django Laravel Java / Spring C# / ASP.NET Core Go Ruby on Rails React Next.js Vue Angular SvelteKit Flutter React Native Kotlin / Android Swift / iOS SQL GraphQL Read-Only Audits by Default One impo