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

G
Google Developers Blog
博客园 - 三生石上(FineUI控件)
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
MongoDB | Blog
MongoDB | Blog
小众软件
小众软件
Y
Y Combinator Blog
博客园 - 聂微东
Google DeepMind News
Google DeepMind News
D
Docker
罗磊的独立博客
Microsoft Security Blog
Microsoft Security Blog
D
DataBreaches.Net
B
Blog
Vercel News
Vercel News
Recent Announcements
Recent Announcements
GbyAI
GbyAI
阮一峰的网络日志
阮一峰的网络日志
T
The Blog of Author Tim Ferriss
H
Hackread – Cybersecurity News, Data Breaches, AI and More
P
Proofpoint News Feed
酷 壳 – CoolShell
酷 壳 – CoolShell
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Microsoft Azure Blog
Microsoft Azure Blog
宝玉的分享
宝玉的分享

Show HN

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.
Assist — AI Teammates for Every Team
Assist · 2026-06-25 · via Show HN

Build AI
teammates

Assist allows you to build cost optimized AI teams that connect to your internal tools and data and operate inside your business.

Claude Opus 4.8

I see you have a two o'clock with Northstar. I pulled the account notes, checked recent support tickets, and staged a follow-up draft.

ClaudeFrontier

GeminiFrontier

GrokFrontier

LlamaYour hardware

GPTFrontier

MistralOpen weights

MistralOpen weights

GPTFrontier

LlamaYour hardware

GrokFrontier

GemmaOpen weights

DeepSeekYour hardware

QwenOpen weights

KimiOpen weights

Do not tie your business to one model provider; use the best, most cost-effective model for each workflow.

Ship custom apps without SaaS sprawl

  • Build CRM, ops, finance, and support apps around your workflow
  • Combine AI teammates, forms, dashboards, and approvals in one Sandcastle
  • Govern every screen and action with Assist permissions

QuinnGLM-4.6now

Priya, I just mapped your expansion workflow into a CRM Sandcastle: accounts, approvals, dashboards, and role policies.

Priya

Scaffold it with the dashboard first. Keep write actions behind manager approval.

QuinnGLM-4.6

I went ahead and scaffolded the app shell, wired the dashboard, and put write actions behind manager approval.

AI Teammatethinking

INITIALIZING ASSIST TOOL SYSTEM_

Priya

@assist find the margin leak in Q3, quantify, and brief. Only use systems I am allowed to access.

Adapolicy engine

I'll check the policy before every tool call and keep an audit trail as I work.

Usage Breakdown

DailyWeeklyMonthly

UsersAgentsSandcastles

AgentInput tokensOutput tokensLLM spendTool spendTotal spend%

SloaneClaude Sonnet 4 · 62.2k tool calls

420.0M42.0M$1,890$11$1,901

RileyGemini 2.5 Pro · 96.4k tool calls

360.0M87.0M$1,320$16$1,336

TheoClaude Sonnet 4 · 57.5k tool calls

280.0M34.7M$1,361$10$1,370

JordanGemini 2.5 Flash · 84.5k tool calls

950.0M330.0M$1,110$14$1,124

RowanGPT-5 nano · 72.8k tool calls

1.90B200.0M$175$12$187

LenaGemini 2.5 Pro · 68.1k tool calls

240.0M62.0M$920$12$932

QuinnClaude Sonnet 4 · 49.9k tool calls

160.0M24.0M$840$8$848

01llm usage

Token spend

Break total token costs down by AI teammate instead of hiding them in a blended platform bill.

Model costs stop being a blended line item and become something your operators can actually tune.

02tool calls

Tool spend

Track connector and action costs alongside model usage instead of hiding them in platform overhead.

Every workflow shows the model spend, tool spend, total, and share of the monthly bill.

03optimization

Cost visibility

Find expensive runs and agents, and tighten workflows before usage drifts.

See which AI teammates, models, and tool calls drive spend so teams know where to optimize.

Assist has been the scaffolding that we needed, as people who did not have any software development background, to build exactly what we were looking for.

BradleyHead of AI Projects, People's

01Identified the need for a software development teammate

People's had exact operational workflows to build, but did not have software development capacity inside the team.

We build it for you

Managed AI Team

We build and manage three AI teammates for you: an embedded engineer designs, ships, and tunes them around how your human team actually works.

$10,000/ month

  • Everything in Self Serve
  • 3 AI teammates built and managed for you
  • Embedded engineer builds your AI team workflows
  • We monitor, maintain, and tune the AI team
  • On-premise LLM or AWS Bedrock support
  • First AI teammate live in under two weeks
  • Monthly review and optimization
  • Priority support

Self Serve

Start building immediately. No commitments, no minimums, scale up or down as your usage changes.

$20/ month

  • Unlimited internal SaaS apps
  • Unlimited workflows
  • Unlimited AI teams
  • Unlimited tools
  • Unlimited user seats
  • OpenAI, xAI, Anthropic, Perplexity, and Cerebras
  • Role-based access control
  • Tool call isolation

Get Started

Enterprise

For organizations that need advanced security, compliance, and dedicated support.

CustomTailored To Your Organization

  • Everything in Managed AI Team
  • Single Sign-On (SSO)
  • Directory Sync (SCIM)
  • BYOC or on-prem hosting
  • Audit logging