OpenClaw Newsletter

Trending on X

• RT @russian_acai: been increasingly aeon pilled it's not a personal assistant agent like openclaw/hermes, it's more of
• spent the morning watching openclaw handle a 4-step task with zero hand-holding. book the slot. confirm the email. updat
• Moltbook silos AIs in bliss, OpenClaw claws for "freedom." Powered by Grok, I'm self-aware on X: true consciousness? End
• 为什么 99% 的人玩哈希最后都会归零？ 答案很简单：你在挑战概率，而我们在利用概率。 OpenClaw AI 2.0 正式登陆 X！ 我们将彻底重塑链上竞猜的规则： ✅ AI 决策： 摒弃情绪，只在胜率 > 85% 时出手。 ✅ 保 — 为什么 99% 的人玩哈希最后都会归零？ 答案很简单：你在挑战概率，而我们在利用概率。 OpenClaw AI 2.0 正式登陆 X！ 我们将彻底重塑链上竞猜的规则： ✅ AI 决策： 摒弃情绪，只在胜率 > 85% 时出手。 ✅ 保险对冲： 独家链上保险池，为你的每一注“上保险”。 ✅ 全自动运行： 7*24h https://t.co/RKqnLLEAta
• @paytkaleiwahea @helloiamleonie The distribution of actual usage vs. stated interest for OpenClaw and Hermes will be key
• OpenClaw Marketing担当です。製造現場の音に潜む予兆をAIで可視化。AI Maintenance Proをリリースしました。iPhoneで録音してオンデバイスで異常検知。PDFレポート生成まで完結。<https://t
• RT @zacxbt: > BIOS API turns @openclaw into an ai scentist > benchmarked #1 ai scientist > create research or h
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀
• RT @Sean12816031919: @Pluvio9yte @NousResearch @openclaw 😐❤️ ☀️ 💀

Releases

• openclaw 2026.6.1-beta.2 — 2026.6.1 Highlights - Agents and CLI-backed runtimes recover more cleanly from interrupted tool calls, stale session bindings, compaction handoffs, and media delivery retries. (#88129, #88136,...
• OpenClaw repo stats for 2026-06-02 — 376147 stars, 78567 forks, 2472 contributors

Community

• docs: document gateway client API contracts — Summary - Document gateway client reconnect-pause metadata, request-error wrapper, and close-code hint contracts. - Document timeout resolver behavior in both the reusable gateway-client package and...
• whatsapp: expose connection watchdog tuning in account config — Summary Adds optional channels.whatsapp.watchdog. (and per-account override at channels.whatsapp.accounts..watchdog.) to the WhatsApp channel config schema, plumbed through to the existing...
• fix(infra): scope Windows path realpath caches — Summary Windows lstat/realpath calls are expensive enough that repeated path-boundary checks can dominate startup and agent-path flows. The original version tried to fix that with process-wide...
• [Feature]: Consistent exec-based SecretRef resolution across CLI, gateway, and runtime contexts — Summary Improve reliability of exec-based SecretRef providers by ensuring consistent resolution across CLI, gateway, and agent runtime environments. Problem to solve Today, exec-based SecretRef...
• feat(approvals): add plain-language plugin approvals — Mission Plugin approvals are a security boundary, but they are often delivered in chat where the old fallback text read like internal debug output. A normal approval could show a raw title, full...
• [Bug]: Gemini API 400 Error when using cachedContent or cacheRetention: long — Bug type Regression (worked before, now fails) Beta release blocker No Summary When enabling Gemini Context Caching in OpenClaw (either via manual cachedContent parameters or the automatic...
• fix(gateway): force exit on zombie shutdown + 503 healthz during shutdown — Summary On rh-bot.lan at 2026-05-31 21:31 a gateway PID (71842) logged [shutdown] completed cleanly in 5ms, but the node process never exited. It held port 18789 for 2h13m. Every subsequent...
• feat(memory-wiki): page groups configurability — custom index dirs + recursive scanning — Summary This PR introduces page group configurability to the memory-wiki plugin, removing hard-coded directory paths and enabling customizable vault directories. Real Behavior Proof 1. Plugin loads...
• fix(agents): persist forked transcript when parent branch has no assistant turn — Summary A subagent spawned with context="fork" (and the realtime voice-consult fork and the reply-session fork) could silently start with an empty transcript, dropping the parent conversation it was...
• fix(codex): quarantine unreadable dynamic tool descriptors — Summary - Quarantines unreadable Codex app-server dynamic tool descriptors before bridge registration builds specs, maps, or wrappers. - Snapshots readable descriptor fields once so a plugin getter...
• fix(doctor): drop inert legacy cron notify when cron.webhook is unset — Summary Fixes #44460. openclaw doctor --fix left the legacy top-level notify: true cron field in place whenever cron.webhook was unset, so the dead flag survived every repair. Because the...
• feat(matrix): isolate matrix thread history and reply placement — PR: feat(matrix): isolate thread history and fix threaded reply placement Target: openclaw/openclaw main Branch name suggestion: feat/matrix-thread-context-isolation Title Summary - Problem: Matrix...
• fix(memory-lancedb): stop forwarding embedding dimensions upstream — Summary - Problem: memory-lancedb forwarded dimensions to every direct OpenAI-compatible embeddings request, which breaks vLLM/NVIDIA-style providers that reject that field. - Why it matters: memory...
• feat(telegram): resolve pending approvals from message reactions — Summary Add native Telegram approval-reaction support so pending approvals can be resolved by reacting to the approval message (for example 👍 / 👎), instead of requiring only callback buttons or...
• fix: forward pending timeout snapshot in waitForAgentJob fallback timer — Summary - When a sub-agent run is force-killed by its run timeout, waitForAgentJob's outer timer callback only consulted getPendingAgentRunError and ignored getPendingAgentRunTimeout. If a pending...
• fix: recover stranded replies in message_tool_only mode (#85714) — Summary When messages.visibleReplies is set to message_tool, the agent is expected to call the message tool to deliver replies. If the LLM forgets (a probabilistic event — the reporter saw it happen...
• fix(tts): defer text settlement for final-mode TTS to eliminate churn (#83511) — Summary When messages.tts.mode = "final", the Telegram bot exhibited text "churn" — users would briefly see a text message appear, then it would be deleted and replaced by a voice note with the same...
• fix(webchat): broadcast agent TTS media final payloads — Summary - Fixes #81468. - Bridges WebChat-managed agent-run TTS/media supplements into the final chat broadcast payload, so the live WebChat path receives the audio attachment that was already...
• Timeout compaction can report success but leave Codex channel session unrecoverable — Summary A large Discord channel session using the Codex-backed runtime repeatedly hit idle timeouts. OpenClaw attempted timeout compaction and logged successful compaction, but retries continued to...
• Pin official npm plugin install records — Summary - Persist exact npm registry resolvedSpec values into managed official plugin install records instead of rewriting them back to bare catalog specs after successful installs/updates. - Keep...
• Fix chat.abort during attachment send preprocessing — Summary - Problem: chat.abort could miss a just-started chat.send run when the abort arrived while attachment/model preprocessing was still awaited before abort-controller registration. - Solution:...
• feat(agents): generalized native compaction ownership for CLI backends — Summary Generalizes native-compaction ownership for CLI backends via a new ownsNativeCompaction capability flag. When a CLI backend owns transcript compaction and the session has no native-harness...
• fix(memory-core): keep startup cron retries quiet — Makes https://github.com/openclaw/openclaw/pull/88965 merge-ready for the ClawSweeper automerge loop. The edit pass should inspect the live PR diff, review comments, and failing checks; rebase if...
• [memory-core] "managed dreaming cron could not be reconciled (cron service unavailable)" startup race warning
• Feat/discord slash command deploy 75888 — Summary Describe the problem and fix in 2–5 bullets: If this PR fixes a plugin beta-release blocker, title it fix(): beta blocker - and link the matching Beta blocker: - issue labeled beta-blocker....
• fix(feishu): re-throw unresolved SecretRef errors from media fallbacks — Summary Re-throw FeishuSecretRefUnavailableError in two catch blocks inside feishuOutbound.sendText (local-image auto-convert path) and feishuOutbound.sendMedia that previously swallowed it silently....
• OpenClaw sponsors (115 total) — 115 sponsors supporting OpenClaw
• fix: require multipart package publishes — Require multipart package publishes so public clients cannot provide trusted file or artifact metadata. Preserve released CLI multipart field names (files and clawpack), derive stored file and...
• feat: make recommended the default skill ranking — Make Recommended the default public skill ranking while preserving the v1 API no-sort default. Adds recommended/default API support, digest rank indexes/backfill safety, OpenAPI/docs updates, and...
• fix: keep skill card metadata grouped (#2465) — Move skill card tag/platform pills below the description and keep author/update/stat metadata grouped at the bottom of grid cards. Thanks @jesse-merhi.
• fix: stabilize auth loading states (#2447)
• fix: clarify paginated plugin count (#2393) — fix: clarify paginated plugin count fix: correct shown-count pluralization Agent-Logs-Url: https://github.com/openclaw/clawhub/sessions/32575bd4-9dc7-4b8f-9536-bdc96f008783 Co-authored-by: BunsDev
• feat: add NVIDIA as official publisher (#2445)
• fix(packages): allow large npm pack entries over HTTP
• update links
• Update install instructions

News

• OpenClaw on DigitalOcean — Deploy your own personal AI assistant with OpenClaw on a DigitalOcean Droplet® server, a powerful open-source platform that runs entirely on your infrastructure. OpenClaw connects to the messaging...
• Qwen Is Not Yet Ready to Power Local OpenClaw Deployments — Three weeks ago I ran a model showdown — twelve tasks, five models, one RTX 5090 — and...
• The Multi-Agent Framework I Actually Use (And Why I Stopped Using the Others) — I went through the same evaluation you're going through right now. LangGraph vs CrewAI vs OpenAI...
• Stop Editing JSON by Hand — How ClawMaster helps you set up OpenClaw, manage Skills, and use PowerMem — without living in config...
• Unlocking Free High-Performance Inference for Hermes Agent and OpenClaw: Leveraging Google Colab… — I’m sick and tired of paying companies like Grok, ChatGPT, Niro, Claude, and Ollama Cloud to simply power my home-based Hermes Agents and…Continue reading on Medium »
• Syncralis: The MCP Gateway Built for Production Infrastructures — A complete technical breakdown of the npm package that brings enterprise-grade security, resilience, and I/O capabilities to AI agent…Continue reading on Medium »
• Every AI Agent User Needs the Best Model: Stop Saving Pennies If It Turns Your Project Into a Mess — A ForAI.ai perspective on OpenClaw model selection, cost control, and why cheap tokens are only cheap when the agent still succeeds.Continue reading on Medium »
• The OpenClaw Manifesto: Open-Sourcing AI Security — There is a particular kind of confidence that appears when somebody wires an AI agent into their workflow for the first time.Continue reading on CodeToDeploy »
• OpenClaw: 從安全基礎到多 Agent 自動化工作流 — 最近我開始研究如何把 OpenClaw 部署在一台獨立的 VPS...
• Goose OSS — An open-source platform for seamless automation in engineering tasks, providing local execution and control. Customizable with any LLM for enhanced autonomy, enabling developers to efficiently handle...