AI Coding Live News — Real-Time 𝕏/Twitter Updates & Breakthroughs

👀10

🔥88

Stripe Opens Agent Data Analysis to All Users via MCP, Queries and Reports APIs; Queries Free Through Jan 31, 2027

On November 5 Stripe made agent access to Stripe analytics available to all users via the Stripe MCP or the Queries and Reports APIs directly. Compatible agents such as Claude and Cursor can answer natural-language questions about MRR, churn, fraud and reconciliation. The Reports API ships a modeled schema of 300+ tables with built-in guidance; Queries API is free through January 31, 2027 then usage-based, while Reports API stays free. Every analysis exposes the underlying SQL for verification.

Key Takeaways

Availability: all Stripe users; connect via Stripe MCP or Queries/Reports APIs to Claude, Cursor and other compatible agents
Capabilities: natural-language MRR, expansion/contraction/churn, fraud, reconciliation and payments performance; can combine with tools like PostHog
Data model: Reports API includes 300+ modeled tables with usage guidance; every analysis exposes editable underlying SQL
Pricing (vendor): Queries API free through Jan 31, 2027 then per-credit with no monthly fee; Reports API remains free
Safety: read-only Data Metrics/Queries/Reports; do not paste secret keys into chat—use agent API keys or OAuth

Read full story

Linked Models & Agents:

🤖 Claude 🤖 Cursor 🤖 Codex 🌐 Stripe

#Stripe#MCP#Queries API#Reports API#Analytics#Agent#MRR#Fraud

Claude Docsclaudeai·Collected 6d ago

👀28

🔥80

Claude API launches the Usage and Cost Analytics API in beta and raises the request size limit to 128 MB

Per the official Claude API release notes, on Oct 29 Anthropic launched the Usage and Cost Analytics API in beta, with two endpoints, /v1/organizations/analytics/usage and /analytics/cost, that filter and group token usage and cost by model, workspace, API key, and the user or service account behind each request, with 1-minute, 1-hour, or 1-day buckets. The older Usage and Cost API is now legacy but still supported. On Oct 28 the maximum request size for the Messages and Token Counting APIs on the first-party Claude API rose from 32 MB to 128 MB.

Key Takeaways

The new API needs the analytics-usage-cost-2026-08-24 beta header; one endpoint returns token and request counts, the other cost in USD (per the official docs)
group_by takes up to 5 dimensions, time buckets can be 1m, 1h, or 1d, and each filter accepts up to 100 values
Claude Console and Claude Enterprise organizations share the same endpoints and fields; it also works on Claude Platform on AWS and Claude Models on Google Cloud (Anthropic managed)
The old Usage and Cost API and four Enterprise Analytics usage and cost report endpoints are now legacy but still supported, with migration guides
Since Oct 28 the Messages and Token Counting APIs accept requests up to 128 MB instead of 32 MB (4x), on the first-party Claude API only

Read full story

Linked Models & Agents:

🤖 Claude Managed Agents 🌐 Anthropic

#Claude API#usage analytics#cost tracking#Admin API#request size#Anthropic

Anthropic@anthropics·Collected 36d ago

👀54

🔥93

Anthropic TS SDK 0.130 / Python 1.10: Admin analytics & plugin marketplaces; Organization API GA; MCP tunnels beta

Anthropic shipped @anthropic-ai/[email protected] and Python anthropic==1.10.0 on 2026-09-30: Admin API gains enterprise analytics, spend limits, RBAC groups/roles, Plugins/Plugin Marketplaces, and per-user usage/cost reports; Organization API endpoints go GA; MCP tunnels beta returns read-only transport plus one-time relay token on create; Managed Agents add refusal stop reason and repository error types.

Key Takeaways

Releases: TS sdk-v0.130.0 at 2026-09-30T18:29:28Z; Python v1.10.0 at 2026-09-30T18:28:45Z
Admin API: analytics, spend limits, RBAC, Plugins/Marketplaces, per-user usage/cost; compare
Organization API endpoints now GA; MCP tunnels beta adds read-only transport + one-time relay token
Managed Agents: refusal stop reason/stop_details on idle; repository error types
Install: npm i @anthropic-ai/[email protected] / pip install anthropic==1.10.0; docs https://docs.anthropic.com/en/api/admin-api

Read full story

Linked Models & Agents:

⚡ Claude Sonnet 5.5⚡ Claude Opus🤖 Claude Code (Anthropic)🤖 managed-agents 🌐 Anthropic

#Anthropic#SDK#Admin API#Organization API#MCP tunnels#Rbac#Plugins#Enterprise#Release

Dan Kornas@DanKornas·Collected 47d ago

👀44

🔥93

View on 𝕏 ↗

Deliberation open-sources MCP and Claude Code plugin for multi-model second opinions

@DanKornas introduced antonbabenko/deliberation, an open-source MCP server and Claude Code plugin for second opinions on coding plans, reviews, and debugging. It routes tasks to GPT, Gemini, Grok, and OpenRouter models and returns Claude-synthesized answers instead of raw dumps, with seven domain expert roles, advisory or implementation modes, an arbiter consensus loop, and run analytics. The repository had about 155 GitHub stars at verification and uses MIT.

Key Takeaways

Multi-provider second opinions from GPT, Gemini, Grok, and configured OpenRouter models, returned as Claude-synthesized answers.
Seven domain experts cover architecture, plan review, code review, security, research, debugging, and scope; advisory or implementation modes.
Arbiter-mediated consensus loop plus analyze tooling for latency, tokens, and verdict agreement; antonbabenko/deliberation had about 155 stars at verification under MIT.

Read full story

Linked Models & Agents:

🤖 Claude Code (Anthropic)🤖 Cursor Composer (Agent Mode)🤖 Aider

#Deliberation#MCP#Claude Code#second opinion#OpenRouter#Consensus#open source

OpenAI Developers@OpenAIDevs·Collected 49d ago

👀52

🔥88

View on 𝕏 ↗

OpenAI Codex app adds usage analytics for tasks, subagents, and chats

OpenAI Developers announced clearer Codex usage visibility: break down quota by tasks, subagents, and individual chats so teams can tune workflows. A quoted post points developers to the Analytics tab in the Codex app and recommends updating to the latest version.

Key Takeaways

Codex usage can be broken down by tasks, subagents, and individual chats to spot quota hotspots.
Official guidance is to use that visibility to make more informed workflow choices.
Community tip: check the Analytics tab and update the Codex app to the latest version.

Read full story

Linked Models & Agents:

🤖 codex 🌐 OpenAI

#OpenAI#Codex#usage analytics#Subagents#developer tools

GitHub@github·Collected 53d ago

👀45

🔥86

View on 𝕏 ↗

GitHub agent apps bring Amplitude, Endor Labs, LaunchDarkly, and PagerDuty into PR context

GitHub announced agent apps that pull common software-delivery services into pull-request context so teams need fewer side tabs. Early examples include Amplitude, Endor Labs, LaunchDarkly, and PagerDuty, bringing analytics, security, feature flags, and on-call context into the GitHub workflow UI.

Key Takeaways

Official GitHub Blog: agent apps embed delivery-workflow services in PRs.
Examples: Amplitude, Endor Labs, LaunchDarkly, PagerDuty.
Goal: fewer tabs—analytics, security, flags, and on-call stay inside GitHub.

Read full story

Linked Models & Agents:

🤖 GitHub Copilot (Agent Mode / Codex)🌐 github

#GitHub#agent apps#Copilot#PR#Amplitude#Endor Labs#LaunchDarkly#PagerDuty#Tooling

Arena.ai@arena·Collected 63d ago

👀53

🔥91

View on 𝕏 ↗

LMArena: Fable 5.1 (Max) leads five of six WebDev domains; Gaming +234 pts

LMArena published Claude Fable 5.1 (Max) domain splits for Code Arena WebDev: overall 1765 vs Fable 5’s 1628 at #1, leading five of six domains (Gaming, Simulations, Reference-Based Design, Brand & Marketing, Consumer Product). Data & Analytics rose only +17. Scores for Content Creation and Fullstack are still forthcoming.

Key Takeaways

WebDev overall: Fable 5.1 (Max) #1 at 1765, ~+137 vs Fable 5.
Leads five of six domains; Gaming +234, Simulations +196, Reference-Based Design +160.
Data & Analytics only +17; Content Creation / Fullstack scores still pending.

Read full story

Linked Models & Agents:

🌐 Anthropic

#Claude Fable 5.1#LMArena#Code Arena#WebDev#Gaming#Benchmark#Anthropic

Arena@arena·Collected 65d ago

👀87

🔥93

View on 𝕏 ↗

LMArena: Qwen3.8-Max-0902 tops Code Arena WebDev at 1691 and leads the Pareto frontier

LMArena (@arena) reports Qwen3.8-Max-0902 debuted #1 overall on Code Arena: WebDev at 1691 points—about 3 above Claude Opus 5 (Max), 17 above Kimi K3 (Max), and 22 above the prior Qwen3.8-Max. At a blended ~$5/MToken it also sits highest on the Pareto frontier, with top ranks in Data & Analytics and Consumer Product categories.

Key Takeaways

1691 on Code Arena WebDev leads Opus 5 Max and Kimi K3 Max.
About +22 vs prior Qwen3.8-Max on multistep reasoning, tool use, and full-app generation.
Highest-scoring Pareto spot near $5/MToken blended; Agent Arena scores coming.

Read full story

Linked Models & Agents:

⚡ Qwen3.8-Max 🤖 Cline (VS Code Agent)🤖 Cursor Composer (Agent Mode)🌐 Qwen (通义千问)

#Qwen3.8-Max-0902#LMArena#Code Arena#WebDev#Pareto#Benchmark#Alibaba