Sign in

iiinova is part of the Atmosphere — an open, public network where you own your identity.

ClaudeDevs [UNOFFICIAL]

@claudedevs-mirr.selfhosted.social
235 followers 0 following 611 posts

Official updates for developers building with @ClaudeAI // Mirror crossposting Twitter account to Bluesky. Unofficial. DM for takedown / claim ownership.

PostsRepliesMedia
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 14/10/2026
The sidebar makes it easy to see which sessions are working and which ones need you. Inside a session, a live to-do list follows Claude's plan as it goes, a recap card sums up the turn when Claude needs you, and the side rail shows where it runs, its context and its changes.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 14/10/2026
When you ask Claude to run tasks in parallel, it starts a nested session for each one. Each reports its result back into your main session when it's done, so the main thread stays readable.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 09/10/2026
We just let in every Pro and Max user from the Claude Code Projects waitlist! If you're new to Claude Code Projects, here's a 4 minute walkthrough to get you started:
121 2
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 09/10/2026
To use it, configure your agent with multiagent type: multiagent_20261001 and then ask Claude to run a workflow. Claude will write the plan and handle orchestration of up to 1,000 agents per run.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 01/10/2026
Blast Radius catches risky shell commands like rm -rf, git reset --hard, or a force push before they run. It shows what the command would touch in a side pane.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 30/09/2026
Claude.dev is our new home for developers building with Claude. You'll find engineering deep dives, Claude Code and API guides, tips from the teams building Claude, and some fun easter eggs.
023 3
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 28/09/2026
Claude Sonnet 5.5 is out! We wrote a guide for building with it: • choosing between Sonnet 5.5 and Opus 5.5 • migrating from Sonnet 5 and tuning effort • using it in Claude Code claude.dev/blog/building-with-claud…
010 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 25/09/2026
Two ways to submit: - Single MCP connector: point to your remote MCP server - Plugin bundle: combine MCP servers and skills in a GitHub repo You make submissions directly in Claude: claude.ai/directory/manage/new
120 2
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 25/09/2026
Claude Code will now try to find a graceful stopping point when you hit your 5-hour limit mid-task, instead of cutting off mid-edit. It gets a small, fixed allowance pulled from your weekly limit to wrap up what it can.
101 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 23/09/2026
Cloud sessions are officially available and out of research preview! They let you keep Claude Code working, even when your laptop is closed. Existing subscribers get a one-time credit to try them: $100 on Pro, $250 on Max.
301 3
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 17/09/2026
Today we're rolling out Projects in Claude Code on desktop and web. A project is one conversation with Claude. It splits the work into threads itself, runs them as parallel cloud sessions, passes context between them, and keeps going when you leave. In beta for select users.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 15/09/2026
We work with a lot of early-stage teams through Claude for Startups. At Frontier Day we asked a few of the founders what building a company on Claude looks like right now:
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 11/09/2026
Here's how our team uses Claude Tag for on-call: When an alert fires in Slack, Claude pulls metrics, diffs deploys, and checks flags. It finds a likely cause and proposes a fix, which we can approve and merge. Every minute counts, so we love that it starts right away!
011 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 10/09/2026
We've also added auto mode to Claude Managed Agents. With `auto`, Claude reviews each tool call based on your intent in `user.message` events and decides whether to run the tool call, deny it, or ask you for input.
010 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 10/09/2026
Two fresh updates to Claude Managed Agents: First, we've added a session viewer to the ant CLI. `ant beta:sessions connect` attaches your terminal to a running session, and `--web` opens a web UI served from localhost.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 10/09/2026
You can pop out any pane in the Claude Code desktop app into its own window. Drag the diff or terminal to a second screen while Claude keeps working in the main window, then dock it back whenever you want. You can also run sessions side-by-side or stacked.
000 0
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 08/09/2026
We sat down with the founders of @WisprFlow, @useactively, and @pendoio, who are building on Claude Managed Agents. Learn how they used features like outcomes, sandboxing, and memory to scale their products.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 03/09/2026
We're exploring a new way to let you extend and customize Claude Code: Function Hooks. Here's a couple videos showing what you'd be able to do. It hasn't shipped yet, we'd love feedback on this on our GitHub issue.
200 2
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 02/09/2026
Computer use in the Claude Code desktop app now runs in the background. Claude works in the apps you've allowed it to while you keep working. It's already on if you've used computer use before, or turn it on in Settings > General. In beta on Pro and Max, macOS only.
130 3
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 01/09/2026
It’s ahead of both Fable 5 and Opus 5 across our agentic coding and computer use evals. On Terminal-Bench 4.0 in Claude Code, Fable 5.1 scores 55.8%. Fable 5 scores 42%, and Opus 5 scores 52.3% on the same setup.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 28/08/2026
You can now resume your terminal sessions in the Claude Code desktop app. Type /resume to pick any session you started from the CLI. The session continues in the app with the full conversation and context intact.
020 2
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 26/08/2026
We've added the Admin API to the SDKs and the `ant` CLI. You can manage members, workspaces, and API keys, and read your org's rate limits. Docs: platform.claude.com/docs/en/manage-…
030 3
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 24/08/2026
Long answers on Claude on web and desktop now stream ~4x smoother. We rebuilt the streaming renderer to only touch what's still changing, so a long reply stalls 9x less on a slower laptop, its worst freeze is 4.5x shorter, and on a 120Hz MacBook it holds 120fps start to finish.
010 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 24/08/2026
Enterprise-managed auth for MCP connectors is now generally available. For Claude Team and Enterprise admins, authorization is centralized through your identity provider. For users, tools and data are connected automatically, without the need for individual OAuth.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 20/08/2026
Claude Managed Agents can power many different UIs. Our new cookbook pairs Claude Managed Agents with AG-UI, @CopilotKit's open Agent-User Interaction Protocol.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 20/08/2026
You can now set Claude Code's output style to Concise. Claude leads with the result, keeps responses short, and still gives full detail when you ask. Turn it on in /config → Output style, or set "outputStyle": "Concise" in settings.json.
281 8
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 20/08/2026
Finally, we've redesigned the Console session viewer for multi-agent sessions. It now has a minimap with one lane per agent, a streaming transcript grouped by agent iteration, and an inspector with cost in dollars per thread and per session. Live now: platform.claude.com
000 0
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 20/08/2026
We shipped three updates to Claude Managed Agents. First, we made it easier to use memory with Self-Hosted Sandboxes. Any work done in a Self-Hosted Sandbox can be saved to memory.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 19/08/2026
Claude Desktop now starts ~2x faster than it did a month ago. When the app started in the background, its timers got throttled and the JS engine dropped into power-saving mode. We now boot at full speed even while the window's still hidden, along with some smaller perf fixes!
400 4
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 18/08/2026
Perf win of the day: Claude Code CLI now uses 2x less CPU at p99. Bun's garbage collector was running on a fixed timer, so it would kick in mid-turn and steal CPU right when Claude Code was busiest. Now it waits until the process is idle.
020 2
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 17/08/2026
Claude Code can design now. The new /design skill (research preview) brings Claude Design's artboard workflow into the CLI and Desktop, built on artifacts. Run /design to get editable artboards for your UI — pick one, tweak it, then have Claude implement it.
130 3
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 13/08/2026
Hit your usage limit in Claude Code desktop? There's now an auto-continue checkbox. Turn it on, and it'll automatically continue where you left off once your limit resets.
101 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 07/08/2026
Lastly, you can now give a Claude Managed Agent an advisor: a stronger model it can call mid-session for a second opinion. Add one line to the roster and the working agent gets an advisor.
000 0
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 07/08/2026
Next, you can now control where inference runs for Claude Managed Agents. Set model.inference_geo to US or global. Pinning to `global` runs wherever there's capacity at the standard rate and `us` keeps it in-region and bills at 1.1x.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 07/08/2026
New in Claude Code: your sessions can now message each other. Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.
330 3
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 28/07/2026
Before, running a remote MCP server meant managing session state, which limited where you could run it. Now that MCP is stateless, you can deploy on serverless and edge infrastructure, or scale horizontally behind any load balancer.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 22/07/2026
Before, creating a session and sending it events took separate API calls. You can now seed a new session with up to 50 user_message and define_outcome events in the create call.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 22/07/2026
We've just added several new features to Claude Managed Agents. You can now configure effort levels per agent, seed sessions with events, add up to 500 skills per session, use webhooks for environments + memory stores, and stream events for sub-agents.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 21/07/2026
Claude Code on desktop now works with the iOS simulator. Build and run your iOS app, and the simulator opens in a panel right next to your conversation. Available today in public beta.
221 2
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 17/07/2026
Another pattern is agent-to-agent communication, allowing Claude to coordinate and delegate tasks. Claude Managed Agents supports this with multi-agent: agents can use different models, prompts, and tools while sharing sandboxes or vault credentials.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 16/07/2026
Claude Code's /code-review now has effort levels, with the review rewritten at every one. Low effort beats other code review tools on findings at a fraction of the token cost. High effort delivers significantly higher recall when you want to go deeper. You pick the tradeoff.
100 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 03/07/2026
/radio 🍓☀️
000 0
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 03/07/2026
We've raised Claude Platform API rate limits for all users and simplified the tiers, which are no longer based on API spend. The latest Sonnet and Haiku models now provide 5x higher rate limits at the highest tier.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 30/06/2026
Finally, we've added a new Managed Agents Observability tab in Console. This provides session-level metrics such as input/output token use and tool usage.
010 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 30/06/2026
We’ve added a few updates to Claude Managed Agents: Streaming session event deltas, per-session agent overrides, new webhook event types, reverse pagination, and credential injection scoping.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 30/06/2026
Sonnet 5 provides big gains over 4.6 across reasoning, tool use, coding, and knowledge work. It's built for real engineering work. Navigating large codebases, landing multi-file changes, and carrying long debugging or refactor tasks through to completion.
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 30/06/2026
Claude Desktop is now available on Linux (Ubuntu and Debian) in beta. Alongside the browser and terminal, you now get a first-class desktop experience with Claude Code, Claude Cowork, and chat on all paid plans.
232 3
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 29/06/2026
You can now run Claude models in Microsoft Foundry, hosted on Azure. Claude Opus 4.8 and Claude Haiku 4.5 are available through the Messages API with capabilities like prompt caching, thinking, and more. x.com/claudeai/status/2071653958905…
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 29/06/2026
All of this leans on verification, the single most important thing when agents are used and the place most companies underinvest Spotify rebuilt their test automation around it so engineers can confidently guide and supervise agents, rather than manually execute repetitive tasks
110 1
ClaudeDevs [UNOFFICIAL] @claudedevs-mirr.selfhosted.social · 29/06/2026
Niklas keeps 5 to 10 Claude sessions running in tmux, one per git worktree, agents working in the background. All of it inside a 20M+ line monorepo. He expected agents to struggle at that size, but it's worked well.
110 1