Skip to main content

This Month in Claude

All levels

A plain-English digest of what's changed recently across Claude โ€” so you can skim "what's new and what it means for me" without reading every changelog. Newest first.

:::info How this page stays current Entries are added by the community and by an automated watcher that flags upstream changes for a human to write up. Each entry links its official source. See something missing? Add it. :::

How to read an entryโ€‹

Each update is tagged by surface โ€” ๐Ÿ—ฃ๏ธ Apps (chat/voice/mobile), ๐Ÿ› ๏ธ Claude Code, ๐Ÿ”Œ API, ๐Ÿง  Models โ€” and answers "what it means for you."

Recent updatesโ€‹

  • ๐Ÿ› ๏ธ Claude Code โ€” Self-hosted environments shipped August 7, 2026 in beta (Claude Code v2.1.224) on Team and Enterprise plans โ€” a first-party way to execute Claude Code cloud sessions (web, mobile, desktop, claude --cloud, scheduled routines) on your own hosts while orchestration and inference stay on api.anthropic.com. Three moving parts, same shape as GitHub Actions: an environment (a named destination created on the Cloud environments admin page, ID ccpool_...), one or more runners (long-lived claude self-hosted-runner processes on your Linux or macOS hosts), and sessions (spawned child claude processes that clone the repo and stream events back). Every connection is outbound HTTPS โ€” Anthropic never opens a port into your network. The operational surprise: a runner locks to the first user that lands on it and only serves that user until it drains, so minimum fleet size = concurrent active users, not concurrent sessions. Not available under ZDR; inference can't be routed off Anthropic (no Bedrock, Vertex, Foundry, or LLM gateway); GitHub-only checkouts today; Claude Tag, Claude Security, and Code Review sessions don't route yet. What it means: the full practitioner guide โ€” the four-command quickstart, the --drain-grace-sec / --retire-at lifecycle, the network shape, the production checklist, and the six gotchas (including the show-once environment secret and the 5-minute clock-skew auth failure) โ€” is at Self-Hosted Environments: run cloud sessions on your own boxes.
  • ๐Ÿ”Œ API โ€” Inference Hooks shipped August 5, 2026 in beta for Claude Enterprise โ€” a first-party, HTTPS webhook (not a WebSocket, despite some coverage) that lets your DLP or in-house AI security server allow-or-deny every governed prompt on claude.ai, Claude Code, and Cowork before the model sees it. One config covers all three surfaces. Every request is signed per Standard Webhooks (HMAC-SHA256 over {webhook-id}.{webhook-timestamp}.{raw body} with your whsec_ secret), the verdict is a small JSON object ({"action": "allow"} or {"action": "deny", "deny_reason": "..."} โ€” deliberately no redact today), and the transcript your server sees is what the user sees (text, tool calls, extracted attachment text) โ€” never system prompts, hidden reasoning, or raw file bytes. What it means: the biggest ops levers are the verdict timeout (1โ€“10 000 ms, 5 s default), failure handling (block vs allow uninspected), and the circuit breaker that stops enforcement on sustained failures โ€” get the deep-dive with the two signing bugs that catch every first integration and the shadow โ†’ percentage โ†’ role-exclusion โ†’ enforce rollout playbook at Inference Hooks: inline DLP for Claude Enterprise.
  • ๐Ÿ”Œ API (cross-AI) โ€” MCP Apps, the first official Model Context Protocol extension, is now covered in depth on AILmanac. Finalized January 26, 2026 and folded into the 2026-07-28 stateless core spec, MCP Apps lets a server ship an HTML UI that any MCP client renders in a sandboxed iframe, with the iframe speaking JSON-RPC 2.0 over postMessage back to the host. Extension identifier io.modelcontextprotocol/ui, MIME text/html;profile=mcp-app, resources at ui://<server>/<name>, tools link via _meta.ui.resourceUri. Default CSP is connect-src 'none' โ€” a UI cannot fetch anywhere until the resource declares connectDomains. What it means: every UI-initiated write is still a normal tool call the host mediates โ€” Apps can render and propose, they cannot silently execute. The full deep-dive on when it beats a plain result, the wire shapes, and the security model: MCP Apps: Interactive UIs Inside a Tool Call.
  • ๐Ÿ—ฃ๏ธ Apps โ€” Claude Cowork now runs on web + mobile with scheduled tasks โ€” launched July 7, 2026 (Max first, other paid plans rolling in over the following weeks). The architectural shift: Cowork sessions now execute on Anthropic's servers, not your machine, so scheduled tasks run on their cadence with the laptop closed and no device online. Frequency options are hourly / daily / weekdays / weekly / manual (no cron), each run spawns a fresh session with your connectors + skills + plugins, and approval prompts get pushed to your phone mid-run. Local file / browser / computer use stay desktop-only โ€” audit any scheduled prompt for local-machine actions or it'll silently skip them. What it means: the practical playbook (capability-by-surface matrix, the Dispatch-vs-Scheduled-vs-Interactive distinction, and the four gotchas that break silent runs โ€” including OAuth drift and the "if I'm asleep" timeout hole) is at Cowork Scheduled Tasks: Agents That Run With No Device On.
  • ๐Ÿง  Models (cross-AI) โ€” OpenAI previewed its "next major model" Astra on August 1, 2026 โ€” not with a keynote, but by pushing ten Lean-4 formalized proofs of previously unsolved problems (sphere packing, Connes rigidity, non-sofic groups, quantum parallel repetition, Ramsey lower bounds, etc.) to openai/ten-proofs. OpenAI described Astra as a multi-agent, long-horizon system that "coordinates multiple agents working together on long-running tasks over hours or days." What it means: there is no API, no pricing, no ChatGPT surface, and no release date โ€” Astra is internal-only and heading into the new U.S. federal review process. The widely-quoted "$2,000" figure is the token cost at Sol's API rates, not Astra's price. Your Claude vs GPT-5.6 vs Gemini decision this month does not change; keep shipping. Full "confirmed vs unknown" breakdown, the ten problems, and a should-I-wait rule of thumb: OpenAI Astra: The Preview Field Note.
  • ๐Ÿ”Œ API โ€” Enterprise user-management endpoints entered beta on July 13, 2026 โ€” the Admin API's members and invites endpoints are now callable on Claude Enterprise organizations (in addition to Console), and a new set of RBAC group and custom-role endpoints ships alongside them. Groups and custom-role routes require anthropic-beta: ce-user-management-2026-07-13 and DROP the anthropic-version header; members and invites take neither. Scopes are granular (read:members, write:members, read:rbac_groups, write:rbac_groups, read:org_audit). What it means: you can now automate offboarding, quarterly group audits, and JIT hire onboarding entirely from CI โ€” see the full playbook and the three gotchas at The Admin API: automate your Claude org.
  • ๐Ÿ”Œ API โ€” Managed Agents Memory Stores entered public beta on July 22, 2026 โ€” a first-party, server-side persistent-memory primitive for Managed Agents. Stores mount into the session sandbox at /mnt/memory/<slug>/ and the agent reads/writes them with its standard file tools. Every write creates an immutable memory version (30-day retention minimum), you can redact history for compliance, and content_sha256 preconditions give you optimistic concurrency. Limits: 8 stores per session, 2,000 memories per store, 100 kB per memory. What it means: the biggest header gotcha โ€” memory-store endpoints use agent-memory-2026-07-22; session endpoints (including attaching a store) still use managed-agents-2026-04-01, and sending both on the same request returns 400. Full walkthrough: Managed Agents Memory Stores.
  • ๐Ÿง  Models โ€” Claude Opus 5 (claude-opus-5) shipped July 24, 2026 โ€” Anthropic's fourth model in two months. Same $5 in / $25 out per MTok pricing as Opus 4.8, same 1M context and 128k output, but materially better numbers: 44.4% on Frontier-Bench v0.1 (vs Opus 4.8's 18.7%), 96.0% on SWE-bench Verified, 30.16% on ARC-AGI-3. Now the default on Claude Max and strongest available on Claude Pro. Two contract changes will break naive migrations: adaptive thinking is on by default and shares your max_tokens budget, and thinking: {"type": "disabled"} now returns 400 at the new xhigh or max effort tiers. What it means: if you pin claude-opus-4-8, read Claude Opus 5: The Field Guide before flipping the ID, and plan the Opus 4.1 โ†’ Opus 5 migration before the 5 August 2026 retirement.
  • ๐Ÿ› ๏ธ Claude Code โ€” Screen reader mode shipped July 14, 2026. Turn it on with claude --ax-screen-reader, CLAUDE_AX_SCREEN_READER=1, or "axScreenReader": true in settings: it plain-texts the transcript, hides decorative glyphs, flattens nested tables into Header: value. lines, and announces permission-mode changes aloud when you cycle with Shift+Tab. The same release added vimInsertModeRemaps (map jj โ†’ Escape) and mouse-click support in fullscreen menus. What it means: the CLI is now usable with assistive tech and lower-strain input โ€” see Claude Code Accessibility.
  • ๐Ÿ› ๏ธ Claude Code โ€” In-app browser on Desktop (Week 28, July 6โ€“10, 2026): Claude Code on desktop gets a built-in browser, so Claude can pull up docs, designs, or any site and interact with pages the way it already does with local dev-server previews. Also that week: /doctor (alias /checkup) is a full setup checkup that diagnoses and can fix issues, and auto mode now blocks transcript tampering and asks before rm -rf on unresolved variables. What it means: Claude can verify against real web pages without leaving the session, and setup problems get a one-command diagnosis.
  • ๐Ÿง  Models โ€” Claude Sonnet 5 shipped June 30, 2026 and is now the default model in Claude Code, with a native 1M-token context window and introductory pricing through August 31, 2026. It's the new balanced "start here" Sonnet tier, superseding Claude Sonnet 4.6 (now a legacy model). What it means: if you pin a model, migrate to claude-sonnet-5 โ€” but read Claude Sonnet 5: The Field Guide first, because non-default temperature/top_p/top_k now returns 400, manual extended thinking returns 400, adaptive thinking is on by default, and the new tokenizer produces ~30% more tokens for the same text. Also check the Current Models & Pricing table for exact IDs and live pricing before relying on a number from a blog post.
  • ๐Ÿ› ๏ธ Claude Code โ€” Dynamic workflows are in research preview: ask for one (or set /effort ultracode) and Claude writes a JavaScript script that orchestrates tens to hundreds of subagents in the background โ€” for codebase-wide audits, large migrations, and cross-checked research. Run /deep-research to see the bundled one, or /workflows to watch runs. What it means: you can now take on fleet-scale tasks one conversation could never coordinate, with the orchestration saved as a rerunnable command. See Dynamic Workflows & ultracode.
  • ๐Ÿง  Models โ€” A new top-tier model, Claude Fable 5 (claude-fable-5) and its Glasswing-only sibling Mythos 5 (claude-mythos-5) shipped June 9, 2026 on Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud and Microsoft Foundry โ€” Anthropic's first "Mythos-class" models, sitting above Opus. They share a 1M-token context, up to 128K output, and $10 / $50 per MTok pricing. What it means: Fable 5 is NOT a drop-in for Opus 4.8 โ€” it refuses in-band as HTTP 200 with stop_reason: "refusal", adaptive thinking is the only mode, raw chain-of-thought is never returned, and Anthropic added a new fallbacks parameter + SDK middleware + fallback-credit billing specifically for retries on Opus 4.8. It also carries mandatory 30-day retention (no ZDR). See the full field guide โ€” Claude Fable 5 & Mythos 5: The Flagship Field Guide.
  • ๐Ÿ› ๏ธ Claude Code โ€” Subagents can now spawn their own subagents (up to 5 levels deep), and /code-review --fix applies review findings to your working tree. What it means: delegation composes deeper, and review can close the loop instead of just reporting. Cross-check the official changelog for exact behavior.
  • ๐Ÿ”Œ API โ€” Capabilities like structured output, extended thinking, and prompt caching evolve. What it means: re-check the API section before relying on exact parameters.

Want the firehose?โ€‹

This is a digest, not a complete log. For everything:

Nextโ€‹