惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

GbyAI
GbyAI
T
Tenable Blog
Webroot Blog
Webroot Blog
L
Lohrmann on Cybersecurity
S
Securelist
S
Schneier on Security
NISL@THU
NISL@THU
Know Your Adversary
Know Your Adversary
C
Cybersecurity and Infrastructure Security Agency CISA
T
The Exploit Database - CXSecurity.com
L
LINUX DO - 热门话题
C
CXSECURITY Database RSS Feed - CXSecurity.com
O
OpenAI News
I
Intezer
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
TaoSecurity Blog
TaoSecurity Blog
S
Secure Thoughts
Application and Cybersecurity Blog
Application and Cybersecurity Blog
P
Privacy International News Feed
H
Hacker News: Front Page
N
Netflix TechBlog - Medium
M
MIT News - Artificial intelligence
博客园 - Franky
PCI Perspectives
PCI Perspectives
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Microsoft Azure Blog
Microsoft Azure Blog
MongoDB | Blog
MongoDB | Blog
L
LangChain Blog
P
Proofpoint News Feed
S
Security Affairs
WordPress大学
WordPress大学
The Last Watchdog
The Last Watchdog
S
SegmentFault 最新的问题
小众软件
小众软件
F
Full Disclosure
博客园 - 叶小钗
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
T
The Blog of Author Tim Ferriss
Simon Willison's Weblog
Simon Willison's Weblog
P
Palo Alto Networks Blog
Security Latest
Security Latest
P
Proofpoint News Feed
月光博客
月光博客
T
Tailwind CSS Blog
Scott Helme
Scott Helme
Hacker News - Newest:
Hacker News - Newest: "LLM"
Google Online Security Blog
Google Online Security Blog
T
Threat Research - Cisco Blogs
Help Net Security
Help Net Security
Project Zero
Project Zero

Show HN

CSP Radar GitHub - awebai/aweb-team-coord-worktrees: An aweb team template for a minimum team with a permanent coordinator and worktrees with local developers. GitHub - fujibee/agmsg GitHub - lucastononro/notify: 100% local, free, offline attention skill for Claude Code: plays a sound and speaks a short status update when a long task finishes, blocks, or needs a decision. GitHub - sebastianwessel/skills: AI Skills tivatdoar / workout-to-work · GitLab GitHub - enumura1/py-sql-cleaner: Find, format, and safely extract embedded SQL from Python files. GitHub - intent-bench/intent-bench: Intent fulfillment benchmark for agentic AI engineering GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - 0gsd/enough: a personal language system for planning, writing, and translation. GitHub - Kaelio/ktx: ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer GitHub - ThatXliner/xtras: Xliner's Claude Code Skills GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. GitHub - search-router/simple-search: Open-source reference app on top of the Search Router API: FastAPI + Jinja metasearch service with pluggable backends, deterministic mocks (no API key needed), RTL UI, Redis cache, and a demo ads cabinet. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - StackOneHQ/stack-nudge We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. make sidebar/address bar rounded corner toggleable
GitHub - patriceckhart/zot-sdk-javascript: TypeScript SDK for embedding zot rpc in Node.js apps and server-side framework routes, including Next.js, Nuxt, Remix, SvelteKit, Express, Fastify, and Bun servers.
patriceckhar · 2026-06-19 · via Show HN

TypeScript SDK for embedding zot rpc in Node.js applications.

The SDK starts a long-lived zot rpc child process and talks newline-delimited JSON over stdin/stdout. It is intended for Node-compatible server runtimes. Do not import it in browser components or edge runtimes.

Install

npm install @patriceckhart/zot-sdk-javascript
# or
pnpm add @patriceckhart/zot-sdk-javascript
# or
yarn add @patriceckhart/zot-sdk-javascript
# or
bun add @patriceckhart/zot-sdk-javascript

During install, postinstall detects your OS and CPU. If zot is already on PATH, it uses that. Otherwise it downloads the matching release asset from GitHub, verifies checksums.txt, and stores the binary under the package vendor/ directory. Platform binaries are not committed to this package.

Bun

Bun may block dependency lifecycle scripts and print Blocked 1 postinstall. If that happens, either trust the package with Bun or run the installer manually after bun add:

node node_modules/@patriceckhart/zot-sdk-javascript/scripts/install-zot.js

If zot is already installed on your PATH, no download is needed.

Environment controls:

  • ZOT_SKIP_INSTALL=1: skip binary download.
  • ZOT_FORCE_INSTALL=1: download even when zot exists on PATH.
  • ZOT_VERSION=v0.2.31: pin a zot release tag.
  • ZOT_BINARY=/path/to/zot: use a specific binary at runtime.

Node.js usage

import { ZotClient } from "@patriceckhart/zot-sdk-javascript";

const zot = new ZotClient({
  provider: "anthropic",
  model: "claude-sonnet-4-5",
  cwd: process.cwd(),
});

for await (const event of zot.promptStream("Explain this project in 3 bullets")) {
  if (event.type === "text_delta") process.stdout.write(event.delta);
  if (event.type === "tool_call") console.log("\ntool:", event.name, event.args);
}

zot.close();

One-shot prompt:

import { createZotClient } from "@patriceckhart/zot-sdk-javascript";

const zot = await createZotClient({ provider: "openai", cwd: process.cwd() });
const result = await zot.prompt("Write a tiny README for this app");
console.log(result.text);
zot.close();

Framework usage

zot rpc is stateful, so keep one client per chat session on the server. The SDK works in any Node-compatible server framework that can spawn child processes. It does not work in browser code or edge runtimes.

Next.js route handler example

This minimal example streams text deltas as Server-Sent Events.

// app/api/chat/route.ts
import { ZotClient } from "@patriceckhart/zot-sdk-javascript";

export const runtime = "nodejs";

const clients = new Map<string, ZotClient>();

function getClient(sessionId: string) {
  let client = clients.get(sessionId);
  if (!client) {
    client = new ZotClient({
      provider: process.env.ZOT_PROVIDER ?? "anthropic",
      model: process.env.ZOT_MODEL,
      cwd: process.cwd(),
    });
    clients.set(sessionId, client);
  }
  return client;
}

export async function POST(req: Request) {
  const { message, sessionId = "default" } = await req.json();
  const client = getClient(sessionId);

  const stream = new ReadableStream({
    async start(controller) {
      const encoder = new TextEncoder();
      try {
        for await (const event of client.promptStream(message)) {
          if (event.type === "text_delta") {
            controller.enqueue(encoder.encode(`data: ${JSON.stringify({ delta: event.delta })}\n\n`));
          }
          if (event.type === "done") {
            controller.enqueue(encoder.encode("data: [DONE]\n\n"));
          }
        }
      } catch (error) {
        controller.enqueue(encoder.encode(`event: error\ndata: ${JSON.stringify(String(error))}\n\n`));
      } finally {
        controller.close();
      }
    },
  });

  return new Response(stream, {
    headers: {
      "content-type": "text/event-stream",
      "cache-control": "no-cache",
    },
  });
}

Nuxt server route example

// server/api/chat.post.ts
import { ZotClient } from "@patriceckhart/zot-sdk-javascript";

const zot = new ZotClient({
  provider: process.env.ZOT_PROVIDER ?? "anthropic",
  model: process.env.ZOT_MODEL,
  cwd: process.cwd(),
});

export default defineEventHandler(async (event) => {
  const body = await readBody<{ message: string }>(event);
  const result = await zot.prompt(body.message);
  return { text: result.text };
});

API

const client = new ZotClient(options);
await client.start();
await client.hello();
await client.ping();
await client.prompt("message");
client.promptStream("message");
await client.abort();
await client.compact();
await client.getState();
await client.getMessages();
await client.clear();
await client.setModel("model-id");
await client.getModels();
client.close();

Important options:

  • binary: path to zot. Defaults to ZOT_BINARY or zot.
  • provider, model, cwd, apiKey, baseUrl map to zot rpc flags.
  • systemPrompt, appendSystemPrompt, reasoning, maxSteps, noTools, tools map to zot rpc flags.
  • rpcToken: sends the initial hello token when ZOTCORE_RPC_TOKEN is set on the child process.

Auth

Use normal zot auth. Run zot and /login, or pass provider API keys via environment variables such as ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, KIMI_API_KEY, and others supported by zot.

Notes

  • One ZotClient wraps one zot rpc process, cwd, model, and session.
  • Use it only in Node-compatible server runtimes with child process support.
  • Only one prompt or compact operation should be active per client.
  • For multiple projects or concurrent chats, create multiple clients.
  • The process exits when closed or when stdin closes.

License

MIT