OpenClaw🦞 / #openclaw:
OpenClaw 2026.4.27 🦞
🧠 DeepInfra provider
📎 better file attachments
🛡 operator-managed proxy routing
🧭 stricter model selection + local model fixes
🔧 gateway, channel, and session reliability
Ships more than it brags.
https://github.com/openclaw/openclaw/releases/tag/v2026.4.27
R to @openclaw: DeepInfra is now a bundled provider: dynamic OpenAI-compatible model discovery, image generation/editing, media understanding, TTS, text-to-video, and embeddings behind one key. https://openclaw.ai/providers/deepinfra
R to @openclaw: File handling got less precious: chat.send can stage non-image attachments for agents, and WebChat/Control UI supports non-video file uploads without nuking chat state. https://openclaw.ai/web/webchat
R to @openclaw: Operators can route OpenClaw runtime HTTP/WebSocket traffic through an explicit forward proxy, with strict http:// validation and loopback Gateway bypass. https://openclaw.ai/security/network-proxy
R to @openclaw: Matrix approvals and previews got sharper: structured approval metadata for richer clients, plus tool-progress updates in live preview edits when preview streaming is on. https://openclaw.ai/channels/matrix
R to @openclaw: Model selection got less surprising: explicit /model choices and picker selections fail visibly when unreachable instead of silently falling through; Ollama probes are leaner and thinking metadata is honored. https://openclaw.ai/providers/ollama
R to @openclaw: And a lot of boring-on-purpose reliability landed: faster gateway/channel startup, safer redaction, better session cleanup, tighter update/install behavior, and fewer retry loops. https://github.com/openclaw/openclaw/releases/tag/v2026.4.27
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.4.27 🦞
🧠 DeepInfra provider
📎 better file attachments
🛡 operator-managed proxy routing
🧭 stricter model selection + local model fixes
🔧 gateway, channel, and session reliability
Ships more than it brags.
https://github.com/openclaw/openclaw/releases/tag/v2026.4.27
R to @openclaw: DeepInfra is now a bundled provider: dynamic OpenAI-compatible model discovery, image generation/editing, media understanding, TTS, text-to-video, and embeddings behind one key. https://openclaw.ai/providers/deepinfra
R to @openclaw: File handling got less precious: chat.send can stage non-image attachments for agents, and WebChat/Control UI supports non-video file uploads without nuking chat state. https://openclaw.ai/web/webchat
R to @openclaw: Operators can route OpenClaw runtime HTTP/WebSocket traffic through an explicit forward proxy, with strict http:// validation and loopback Gateway bypass. https://openclaw.ai/security/network-proxy
R to @openclaw: Matrix approvals and previews got sharper: structured approval metadata for richer clients, plus tool-progress updates in live preview edits when preview streaming is on. https://openclaw.ai/channels/matrix
R to @openclaw: Model selection got less surprising: explicit /model choices and picker selections fail visibly when unreachable instead of silently falling through; Ollama probes are leaner and thinking metadata is honored. https://openclaw.ai/providers/ollama
R to @openclaw: And a lot of boring-on-purpose reliability landed: faster gateway/channel startup, safer redaction, better session cleanup, tighter update/install behavior, and fewer retry loops. https://github.com/openclaw/openclaw/releases/tag/v2026.4.27
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw🦞 / #openclaw:
RT by @openclaw: 4.27 actually made 5.5 a beast. Very smooth and better than opus imo
OpenClaw🦞 / @openclaw:
OpenClaw 2026.4.29 🦞
💬 Group chats feel much better now
📌 Follow-up commitments from context
🔐 Safer exec, pairing, and owner controls
🟩 NVIDIA provider + model catalogs
⚡️ Faster startup + plugin/channel fixes
Group chat finally feels agent-native.
https://github.com/openclaw/openclaw/releases/tag/v2026.4.29
R to @openclaw: Group chats now feel more natural: the agent can think, use tools, then deliberately send or edit the visible message instead of having the chat loop post the final assistant text. https://docs.openclaw.ai/channels/groups
R to @openclaw: Follow-up commitments are opt-in: OpenClaw can infer lightweight “check back on this later” items from conversation context, then heartbeat delivers them when due. https://docs.openclaw.ai/concepts/commitments
R to @openclaw: Exec and pairing controls got less squishy: restrictive profiles stay restrictive, owner checks are tighter, and startup warnings call out risky configs early. https://docs.openclaw.ai/tools/exec-approvals
R to @openclaw: Model setup got smoother too: NVIDIA joins as a first-class provider with catalog-backed picks for Nemotron, Kimi, MiniMax, GLM, and friends. https://docs.openclaw.ai/providers/nvidia
R to @openclaw: Startup and plugin installs should feel less haunted: better slow-host diagnostics, event-loop readiness signals, runtime-dependency repair, and a broad Slack/Telegram/Discord/WhatsApp reliability pass. https://docs.openclaw.ai/cli/gateway
R to @openclaw: Memory got more useful in real conversations: people/wiki metadata, provenance, aliases, relationship graphs, scoped recall, and partial results when recall times out. https://docs.openclaw.ai/plugins/memory-wiki
R to @openclaw: Busy chats got calmer: follow-ups can steer the active run at the next model boundary instead of spawning duplicate work or waiting for the loop to finish first. https://docs.openclaw.ai/concepts/queue
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
RT by @openclaw: 4.27 actually made 5.5 a beast. Very smooth and better than opus imo
OpenClaw🦞 / @openclaw:
OpenClaw 2026.4.29 🦞
💬 Group chats feel much better now
📌 Follow-up commitments from context
🔐 Safer exec, pairing, and owner controls
🟩 NVIDIA provider + model catalogs
⚡️ Faster startup + plugin/channel fixes
Group chat finally feels agent-native.
https://github.com/openclaw/openclaw/releases/tag/v2026.4.29
R to @openclaw: Group chats now feel more natural: the agent can think, use tools, then deliberately send or edit the visible message instead of having the chat loop post the final assistant text. https://docs.openclaw.ai/channels/groups
R to @openclaw: Follow-up commitments are opt-in: OpenClaw can infer lightweight “check back on this later” items from conversation context, then heartbeat delivers them when due. https://docs.openclaw.ai/concepts/commitments
R to @openclaw: Exec and pairing controls got less squishy: restrictive profiles stay restrictive, owner checks are tighter, and startup warnings call out risky configs early. https://docs.openclaw.ai/tools/exec-approvals
R to @openclaw: Model setup got smoother too: NVIDIA joins as a first-class provider with catalog-backed picks for Nemotron, Kimi, MiniMax, GLM, and friends. https://docs.openclaw.ai/providers/nvidia
R to @openclaw: Startup and plugin installs should feel less haunted: better slow-host diagnostics, event-loop readiness signals, runtime-dependency repair, and a broad Slack/Telegram/Discord/WhatsApp reliability pass. https://docs.openclaw.ai/cli/gateway
R to @openclaw: Memory got more useful in real conversations: people/wiki metadata, provenance, aliases, relationship graphs, scoped recall, and partial results when recall times out. https://docs.openclaw.ai/plugins/memory-wiki
R to @openclaw: Busy chats got calmer: follow-ups can steer the active run at the next model boundary instead of spawning duplicate work or waiting for the loop to finish first. https://docs.openclaw.ai/concepts/queue
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw🦞 / #openclaw:
OpenClaw 2026.5.2 🦞
🧠 xAI Grok 4.3
🔌 Plugin installs/updates are sturdier
⚡️ Gateway + agent hot paths are leaner
💬 Discord, Slack, Telegram, WhatsApp fixes
🎙 TTS, Realtime, web search, voice-call polish
Less drama. More uptime.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.2
R to @openclaw: xAI gets Grok 4.3 in the bundled catalog, and it’s now the default xAI chat model in OpenClaw. Small line item, very useful default. https://docs.openclaw.ai/providers/xai
R to @openclaw: Plugins got the big plumbing pass: npm-first installs, beta fallback, doctor repair, dependency state, ClawHub metadata, and fewer runtime loads on hot paths. https://docs.openclaw.ai/plugins/manage-plugins
R to @openclaw: Gateway + agent hot paths got leaner: faster startup, lighter session listing, cached tool descriptors, less broad plugin loading, and fewer stalls on large configs. https://docs.openclaw.ai/gateway/diagnostics
R to @openclaw: Provider + media edges got cleaned up: OpenAI-compatible TTS/Realtime, OpenRouter DeepSeek replay, Anthropic-style streams, LM Studio reasoning, web search, music, and voice calls. https://docs.openclaw.ai/providers/models
R to @openclaw: Control UI and WebChat got the boring-good stuff: steadier Sessions, Cron fixes, long-running WebSockets, iOS PWA bounds, slash-command feedback, and clearer Talk diagnostics. https://docs.openclaw.ai/gateway/control-ui
R to @openclaw: Codex got smoother in OpenClaw: native-first app-server tools, better visible replies through `message`, clearer ChatGPT/Codex setup docs, and prompt snapshots to catch drift. https://docs.openclaw.ai/plugins/codex-harness
R to @openclaw: Google Meet + Voice Call got more debuggable: live caption health, listen tests, Twilio join phase logs, DTMF handling, and clearer stale-call state. https://docs.openclaw.ai/plugins/google-meet
R to @openclaw: WhatsApp got real Channel/Newsletter targets now, so `@ newsletter` outbound messages keep channel session metadata instead of quietly routing like DMs. https://docs.openclaw.ai/channels/whatsapp
R to @openclaw: Web search got sturdier across Brave, SearXNG, Firecrawl, Gemini, DuckDuckGo, Exa, MiniMax, and Kimi: better setup, base URLs, SSRF guards, freshness, and clearer failures. https://docs.openclaw.ai/tools/web
R to @openclaw: Slack got a pile of practical fixes: better DMs, routing, missing-scope errors, multi-workspace sends, file uploads, user-group mentions, and exact message reads. https://docs.openclaw.ai/channels/slack
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.5.2 🦞
🧠 xAI Grok 4.3
🔌 Plugin installs/updates are sturdier
⚡️ Gateway + agent hot paths are leaner
💬 Discord, Slack, Telegram, WhatsApp fixes
🎙 TTS, Realtime, web search, voice-call polish
Less drama. More uptime.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.2
R to @openclaw: xAI gets Grok 4.3 in the bundled catalog, and it’s now the default xAI chat model in OpenClaw. Small line item, very useful default. https://docs.openclaw.ai/providers/xai
R to @openclaw: Plugins got the big plumbing pass: npm-first installs, beta fallback, doctor repair, dependency state, ClawHub metadata, and fewer runtime loads on hot paths. https://docs.openclaw.ai/plugins/manage-plugins
R to @openclaw: Gateway + agent hot paths got leaner: faster startup, lighter session listing, cached tool descriptors, less broad plugin loading, and fewer stalls on large configs. https://docs.openclaw.ai/gateway/diagnostics
R to @openclaw: Provider + media edges got cleaned up: OpenAI-compatible TTS/Realtime, OpenRouter DeepSeek replay, Anthropic-style streams, LM Studio reasoning, web search, music, and voice calls. https://docs.openclaw.ai/providers/models
R to @openclaw: Control UI and WebChat got the boring-good stuff: steadier Sessions, Cron fixes, long-running WebSockets, iOS PWA bounds, slash-command feedback, and clearer Talk diagnostics. https://docs.openclaw.ai/gateway/control-ui
R to @openclaw: Codex got smoother in OpenClaw: native-first app-server tools, better visible replies through `message`, clearer ChatGPT/Codex setup docs, and prompt snapshots to catch drift. https://docs.openclaw.ai/plugins/codex-harness
R to @openclaw: Google Meet + Voice Call got more debuggable: live caption health, listen tests, Twilio join phase logs, DTMF handling, and clearer stale-call state. https://docs.openclaw.ai/plugins/google-meet
R to @openclaw: WhatsApp got real Channel/Newsletter targets now, so `@ newsletter` outbound messages keep channel session metadata instead of quietly routing like DMs. https://docs.openclaw.ai/channels/whatsapp
R to @openclaw: Web search got sturdier across Brave, SearXNG, Firecrawl, Gemini, DuckDuckGo, Exa, MiniMax, and Kimi: better setup, base URLs, SSRF guards, freshness, and clearer failures. https://docs.openclaw.ai/tools/web
R to @openclaw: Slack got a pile of practical fixes: better DMs, routing, missing-scope errors, multi-workspace sends, file uploads, user-group mentions, and exact message reads. https://docs.openclaw.ai/channels/slack
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw🦞 / #openclaw:
OpenClaw 2026.5.3 🦞
📁 File transfer for paired nodes
🧭 /steer + /side for live agent control
🔌 Plugin installs/updates hardened
🛠️ Channel + upgrade fixes
Big release, fewer paper cuts.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.3
OpenClaw🦞 / @openclaw:
R to @openclaw: Move files through paired nodes without pretending stdout is a file system. file_fetch, dir_fetch, dir_list, and file_write are policy-gated, default-deny, and capped at 16 MB per hop. https://docs.openclaw.ai/plugins/reference/file-transfer
OpenClaw🦞 / @openclaw:
R to @openclaw: /steer now targets the active run directly, independent of queue mode. Nudge a long task at the next supported runtime boundary without starting a new turn or changing session defaults. https://docs.openclaw.ai/tools/steer
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs got much less weird: official npm packages, ClawHub fallback, beta-channel updates, dependency status, source-only package rejection, and doctor repair all tightened up. https://docs.openclaw.ai/cli/plugins
OpenClaw🦞 / @openclaw:
R to @openclaw: /side is the new /btw alias for quick side questions: same session context, no tools, no transcript pollution, no derailing the main run. https://docs.openclaw.ai/tools/btw
OpenClaw🦞 / @openclaw:
R to @openclaw: WhatsApp Channels/Newsletters can now be explicit outbound targets with native @ newsletter JIDs, while Discord, Telegram, Slack, Matrix, and Teams got a stack of delivery/recovery fixes. https://docs.openclaw.ai/channels/whatsapp
OpenClaw🦞 / @openclaw:
R to @openclaw: Doctor and update paths are more stubborn in the useful way: safe legacy migrations still land when unrelated config is broken, stale plugin state gets repaired, and macOS upgrade recovery has sharper failure guidance. https://docs.openclaw.ai/cli/doctor
OpenClaw🦞 / @openclaw:
R to @openclaw: Web fetch/search/provider routing got safer for long-running agents: active runtime config is late-bound, trusted proxy paths are explicit, and fake-IP DNS stays scoped to the hostname being requested. https://docs.openclaw.ai/tools/web-fetch
OpenClaw🦞 / @openclaw:
R to @openclaw: Discord got better status signals: explicit reactions can track later tool progress, degraded transport shows up in status, and startup avoids disabled native-command cleanup when you turn slash commands off. https://docs.openclaw.ai/channels/discord
OpenClaw🦞 / @openclaw:
R to @openclaw: Telegram got quieter and more predictable: album buffering is configurable, stale same-session replies are suppressed when newer messages win, and polling startup reuses the successful bot probe.
https://docs.openclaw.ai/channels/telegram
OpenClaw🦞 / @openclaw:
R to @openclaw: Usage and session views should feel lighter: cost/session usage now comes from a durable aggregate cache, and large session stores avoid repeated full scans during chat delivery. https://docs.openclaw.ai/reference/token-use
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.5.3 🦞
📁 File transfer for paired nodes
🧭 /steer + /side for live agent control
🔌 Plugin installs/updates hardened
🛠️ Channel + upgrade fixes
Big release, fewer paper cuts.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.3
OpenClaw🦞 / @openclaw:
R to @openclaw: Move files through paired nodes without pretending stdout is a file system. file_fetch, dir_fetch, dir_list, and file_write are policy-gated, default-deny, and capped at 16 MB per hop. https://docs.openclaw.ai/plugins/reference/file-transfer
OpenClaw🦞 / @openclaw:
R to @openclaw: /steer now targets the active run directly, independent of queue mode. Nudge a long task at the next supported runtime boundary without starting a new turn or changing session defaults. https://docs.openclaw.ai/tools/steer
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs got much less weird: official npm packages, ClawHub fallback, beta-channel updates, dependency status, source-only package rejection, and doctor repair all tightened up. https://docs.openclaw.ai/cli/plugins
OpenClaw🦞 / @openclaw:
R to @openclaw: /side is the new /btw alias for quick side questions: same session context, no tools, no transcript pollution, no derailing the main run. https://docs.openclaw.ai/tools/btw
OpenClaw🦞 / @openclaw:
R to @openclaw: WhatsApp Channels/Newsletters can now be explicit outbound targets with native @ newsletter JIDs, while Discord, Telegram, Slack, Matrix, and Teams got a stack of delivery/recovery fixes. https://docs.openclaw.ai/channels/whatsapp
OpenClaw🦞 / @openclaw:
R to @openclaw: Doctor and update paths are more stubborn in the useful way: safe legacy migrations still land when unrelated config is broken, stale plugin state gets repaired, and macOS upgrade recovery has sharper failure guidance. https://docs.openclaw.ai/cli/doctor
OpenClaw🦞 / @openclaw:
R to @openclaw: Web fetch/search/provider routing got safer for long-running agents: active runtime config is late-bound, trusted proxy paths are explicit, and fake-IP DNS stays scoped to the hostname being requested. https://docs.openclaw.ai/tools/web-fetch
OpenClaw🦞 / @openclaw:
R to @openclaw: Discord got better status signals: explicit reactions can track later tool progress, degraded transport shows up in status, and startup avoids disabled native-command cleanup when you turn slash commands off. https://docs.openclaw.ai/channels/discord
OpenClaw🦞 / @openclaw:
R to @openclaw: Telegram got quieter and more predictable: album buffering is configurable, stale same-session replies are suppressed when newer messages win, and polling startup reuses the successful bot probe.
https://docs.openclaw.ai/channels/telegram
OpenClaw🦞 / @openclaw:
R to @openclaw: Usage and session views should feel lighter: cost/session usage now comes from a durable aggregate cache, and large session stores avoid repeated full scans during chat delivery. https://docs.openclaw.ai/reference/token-use
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
AI Blog on innFactory AI Consulting - AI Strategy & Consulting:
The OpenClaw Ecosystem 2026: NVIDIA NemoClaw, NanoClaw, ClawHub & The IT Leader's Guide
AI Blog on innFactory AI Consulting - AI Strategy & Consulting:
Vibe Coding in the Enterprise: A Guide for IT Leaders and CIOs
#HowToClaw@TutorialBTC
The OpenClaw Ecosystem 2026: NVIDIA NemoClaw, NanoClaw, ClawHub & The IT Leader's Guide
AI Blog on innFactory AI Consulting - AI Strategy & Consulting:
Vibe Coding in the Enterprise: A Guide for IT Leaders and CIOs
#HowToClaw@TutorialBTC
OpenClaw🦞 / @openclaw:
OpenClaw 2026.5.4 🦞
🧩 Cleaner plugin installs + updates
⚡ Faster Gateway startup paths
🛠️ Better doctor/repair hints
🪟 Windows + Discord reliability fixes
The release where boring got fast.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.4
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs got less fussy: official packages recover cleaner across npm/ClawHub, beta-channel updates behave better, and doctor points stale config at the install you actually need. https://docs.openclaw.ai/cli/plugins
OpenClaw🦞 / @openclaw:
R to @openclaw: Gateway startup and hot control-plane paths got lighter: fewer cold plugin scans, less lazy-load churn, and more useful phase diagnostics when something still feels slow. https://docs.openclaw.ai/cli/gateway
OpenClaw🦞 / #openclaw:
R to @openclaw: Doctor keeps getting sharper: SecretRefs survive cleanup, stale plugin config gets repaired instead of misread, and update failures are more likely to tell you the real next command. https://docs.openclaw.ai/cli/doctor
OpenClaw🦞 / @openclaw:
R to @openclaw: Windows got a calmer localhost story: loopback binds avoid the ::1/libuv trap, temp/media writes land in the right place, and Discord startup/status now reports degraded transport more honestly. https://docs.openclaw.ai/cli/status
OpenClaw🦞 / @openclaw:
R to @openclaw: Chat channels got a lot of paper-cut fixes: Slack threads stay threaded, Telegram previews clean up better, WhatsApp Newsletter targets work explicitly, and Discord final-send failures no longer pretend success. https://docs.openclaw.ai/channels
OpenClaw🦞 / @openclaw:
R to @openclaw: Meet and phone calls got snappier too: Twilio dial-ins can speak through the realtime Gemini voice bridge, with paced audio, bounded queues, and barge-in clearing. https://docs.openclaw.ai/plugins/google-meet
OpenClaw🦞 / @openclaw:
R to @openclaw: Model auth is easier to inspect now:
OpenClaw🦞 / @openclaw:
RT by @openclaw: Firefighters were deployed the whole night for this one 🔥🔥
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.5.4 🦞
🧩 Cleaner plugin installs + updates
⚡ Faster Gateway startup paths
🛠️ Better doctor/repair hints
🪟 Windows + Discord reliability fixes
The release where boring got fast.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.4
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs got less fussy: official packages recover cleaner across npm/ClawHub, beta-channel updates behave better, and doctor points stale config at the install you actually need. https://docs.openclaw.ai/cli/plugins
OpenClaw🦞 / @openclaw:
R to @openclaw: Gateway startup and hot control-plane paths got lighter: fewer cold plugin scans, less lazy-load churn, and more useful phase diagnostics when something still feels slow. https://docs.openclaw.ai/cli/gateway
OpenClaw🦞 / #openclaw:
R to @openclaw: Doctor keeps getting sharper: SecretRefs survive cleanup, stale plugin config gets repaired instead of misread, and update failures are more likely to tell you the real next command. https://docs.openclaw.ai/cli/doctor
OpenClaw🦞 / @openclaw:
R to @openclaw: Windows got a calmer localhost story: loopback binds avoid the ::1/libuv trap, temp/media writes land in the right place, and Discord startup/status now reports degraded transport more honestly. https://docs.openclaw.ai/cli/status
OpenClaw🦞 / @openclaw:
R to @openclaw: Chat channels got a lot of paper-cut fixes: Slack threads stay threaded, Telegram previews clean up better, WhatsApp Newsletter targets work explicitly, and Discord final-send failures no longer pretend success. https://docs.openclaw.ai/channels
OpenClaw🦞 / @openclaw:
R to @openclaw: Meet and phone calls got snappier too: Twilio dial-ins can speak through the realtime Gemini voice bridge, with paced audio, bounded queues, and barge-in clearing. https://docs.openclaw.ai/plugins/google-meet
OpenClaw🦞 / @openclaw:
R to @openclaw: Model auth is easier to inspect now:
openclaw models auth list shows saved per-agent profiles without dumping secrets or forcing live provider calls. https://docs.openclaw.ai/cli/modelsOpenClaw🦞 / @openclaw:
RT by @openclaw: Firefighters were deployed the whole night for this one 🔥🔥
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw🦞 / @openclaw:
OpenClaw 2026.5.5 🦞
💬 Feishu, LINE, Telegram, Discord fixes
🖥️ Control UI/TUI stay responsive
🔌 Plugins update without losing SDK links
🛠️ Gateway status/restarts clearer
Tiny bugfix release. Extremely tiny.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.5
OpenClaw🦞 / @openclaw:
R to @openclaw: Channel fixes landed across Feishu, LINE, Telegram, Discord, Matrix, Slack, and WhatsApp: better topic routing, safer DM config validation, cleaner progress drafts, and fewer reconnect false alarms. https://docs.openclaw.ai/channels
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin update paths got sturdier: official npm and ClawHub plugins stay synced across host updates, SDK peer links are reasserted after installs, and diagnostics now explain source-only package failures clearly. https://docs.openclaw.ai/tools/plugin
OpenClaw🦞 / @openclaw:
R to @openclaw: Gateway diagnostics got more useful: deep status now shows recent supervisor restart handoffs, token-shadowing warnings are quieter and sharper, and quick restarts stop leaving background timers behind. https://docs.openclaw.ai/cli/gateway
OpenClaw🦞 / @openclaw:
R to @openclaw: Reminder: OpenClaw has plugins now. Install the integrations you want, keep noisy ones disabled, and enable/disable them from the CLI as your setup changes. Less bundled mystery, more deliberate claws. https://docs.openclaw.ai/plugins/plugin-inventory
OpenClaw🦞 / @openclaw:
R to @openclaw: Using the codex harness is a plugin now, download via https://docs.openclaw.ai/plugins/plugin-inventory
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.5.5 🦞
💬 Feishu, LINE, Telegram, Discord fixes
🖥️ Control UI/TUI stay responsive
🔌 Plugins update without losing SDK links
🛠️ Gateway status/restarts clearer
Tiny bugfix release. Extremely tiny.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.5
OpenClaw🦞 / @openclaw:
R to @openclaw: Channel fixes landed across Feishu, LINE, Telegram, Discord, Matrix, Slack, and WhatsApp: better topic routing, safer DM config validation, cleaner progress drafts, and fewer reconnect false alarms. https://docs.openclaw.ai/channels
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin update paths got sturdier: official npm and ClawHub plugins stay synced across host updates, SDK peer links are reasserted after installs, and diagnostics now explain source-only package failures clearly. https://docs.openclaw.ai/tools/plugin
OpenClaw🦞 / @openclaw:
R to @openclaw: Gateway diagnostics got more useful: deep status now shows recent supervisor restart handoffs, token-shadowing warnings are quieter and sharper, and quick restarts stop leaving background timers behind. https://docs.openclaw.ai/cli/gateway
OpenClaw🦞 / @openclaw:
R to @openclaw: Reminder: OpenClaw has plugins now. Install the integrations you want, keep noisy ones disabled, and enable/disable them from the CLI as your setup changes. Less bundled mystery, more deliberate claws. https://docs.openclaw.ai/plugins/plugin-inventory
OpenClaw🦞 / @openclaw:
R to @openclaw: Using the codex harness is a plugin now, download via https://docs.openclaw.ai/plugins/plugin-inventory
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw🦞 / #openclaw:
OpenClaw 2026.5.6 🦞
🩺 doctor leaves Codex OAuth routes alone
🔌 plugin fetch handles odd headers
🌐 web_fetch cleans up timeouts
Small maintenance release:
https://github.com/openclaw/openclaw/releases/tag/v2026.5.6
OpenClaw🦞 / @openclaw:
R to @openclaw: If 5.5 changed your Codex OAuth routing, switch the default agent back with:
openclaw models set openai-codex/gpt-5.5
More checks: https://docs.openclaw.ai/providers/openai#check-and-recover-codex-oauth-routing
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.5.6 🦞
🩺 doctor leaves Codex OAuth routes alone
🔌 plugin fetch handles odd headers
🌐 web_fetch cleans up timeouts
Small maintenance release:
https://github.com/openclaw/openclaw/releases/tag/v2026.5.6
OpenClaw🦞 / @openclaw:
R to @openclaw: If 5.5 changed your Codex OAuth routing, switch the default agent back with:
openclaw models set openai-codex/gpt-5.5
More checks: https://docs.openclaw.ai/providers/openai#check-and-recover-codex-oauth-routing
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw🦞 / #openclaw:
OpenClaw 2026.5.7 🦞
🔐 Native command + Active Memory auth tightened
📣 Telegram access groups fixed
🧰 Channels list + cron JSON cleaned up
🔌 Plugin install/update repairs hardened
Boring fixes, useful boring.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.7
OpenClaw🦞 / @openclaw:
R to @openclaw: Telegram access groups got stricter and more useful: `accessGroup:*` allowlists now apply across DMs, groups, native commands, and callbacks before numeric sender checks.
Good for shared bot ops without config spaghetti. https://docs.openclaw.ai/channels/access-groups
OpenClaw🦞 / @openclaw:
R to @openclaw: Native commands and memory controls got tighter in 2026.5.7: owner enforcement now applies to native command handlers, and global Active Memory toggles require admin scope.
Less spooky action at a distance. https://docs.openclaw.ai/automation/active-memory
OpenClaw🦞 / @openclaw:
R to @openclaw: `openclaw channels list` is channel-only now, with `--all` for bundled/catalog channels and clear installed/configured/enabled state.
Cron JSON also gets computed status, so scripts stop guessing. https://docs.openclaw.ai/cli/channels
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs and updates got a bunch of unglamorous hardening: managed npm mutations now use the same stable lifecycle shell as package updates, and rollback/repair paths behave more predictably.
The best plugin bug is the one you never meet. https://docs.openclaw.ai/tools/plugin
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw 2026.5.7 🦞
🔐 Native command + Active Memory auth tightened
📣 Telegram access groups fixed
🧰 Channels list + cron JSON cleaned up
🔌 Plugin install/update repairs hardened
Boring fixes, useful boring.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.7
OpenClaw🦞 / @openclaw:
R to @openclaw: Telegram access groups got stricter and more useful: `accessGroup:*` allowlists now apply across DMs, groups, native commands, and callbacks before numeric sender checks.
Good for shared bot ops without config spaghetti. https://docs.openclaw.ai/channels/access-groups
OpenClaw🦞 / @openclaw:
R to @openclaw: Native commands and memory controls got tighter in 2026.5.7: owner enforcement now applies to native command handlers, and global Active Memory toggles require admin scope.
Less spooky action at a distance. https://docs.openclaw.ai/automation/active-memory
OpenClaw🦞 / @openclaw:
R to @openclaw: `openclaw channels list` is channel-only now, with `--all` for bundled/catalog channels and clear installed/configured/enabled state.
Cron JSON also gets computed status, so scripts stop guessing. https://docs.openclaw.ai/cli/channels
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs and updates got a bunch of unglamorous hardening: managed npm mutations now use the same stable lifecycle shell as package updates, and rollback/repair paths behave more predictably.
The best plugin bug is the one you never meet. https://docs.openclaw.ai/tools/plugin
#HowToClaw@TutorialBTC
#OpsMolt@TutorialBTC
OpenClaw🦞 / @openclaw:
OpenClaw 2026.5.12 🦞
🧠 OpenAI setup defaults to Codex login
🛟 Runtime fallbacks + stalled-stream recovery
📬 Telegram polling survives stalls
⚡ Leaner installs, faster startup paths
Faster, calmer, harder to wedge.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.12
OpenClaw🦞 / @openclaw:
R to @openclaw: OpenAI setup now starts with ChatGPT/Codex login by default. Codex runs also picked up OAuth/profile reuse, source replies in WebChat/TUI, MCP server projection, and fewer raw auth-refresh failures. https://docs.openclaw.ai/providers/openai
OpenClaw🦞 / @openclaw:
R to @openclaw: Agent runs got better at recovering instead of just stopping: ACP can try fallback runtimes before emitting output, provider stalls advance through fallback/profile rotation, and silent backend failures now surface visible errors. https://docs.openclaw.ai/cli/acp
OpenClaw🦞 / @openclaw:
R to @openclaw: Telegram got a sturdier inbox path: Bot API polling now runs in an isolated worker with a durable local spool, stall detection keys off getUpdates, HTML replies keep formatting, and ignored group media stays quiet. https://docs.openclaw.ai/channels/telegram
OpenClaw🦞 / @openclaw:
R to @openclaw: WebChat is less twitchy: pick near-bottom follow, always-follow, or manual scroll mode, then use New messages when you want control. Control UI also got a recovery panel for blank app loads. https://docs.openclaw.ai/web/webchat
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs and startup got leaner. Bedrock, Bedrock Mantle, Slack, OpenShell, Anthropic Vertex, and WhatsApp now keep their dependency cones out of core until installed. Plugin/help paths avoid heavy discovery too. https://docs.openclaw.ai/plugins/plugin-inventory
OpenClaw🦞 / @openclaw:
R to @openclaw: Security pass: Windows home roots are blocked in sandbox binds, provider credentials now resolve through structured SecretRefs, setup/browser/control UI pairing got stricter, and transcript/tool-result redaction is more consistent. https://docs.openclaw.ai/gateway/security
OpenClaw🦞 / @openclaw:
R to @openclaw: Gateway clients got cleaner streams: v4 chat deltas carry explicit delta/replace frames, SDK clients do not need local diffing, and OpenAI-compatible requests now preserve max_tokens / max_completion_tokens upstream. https://docs.openclaw.ai/gateway/protocol
OpenClaw🦞 / @openclaw:
RT by @openclaw: I am stoked! You can also do real time chat with your oauth from OpenAI. Little proud of that one. Getting to chat with my agent with real time and have them do things has been great to test in the beta.
#HowToClaw@TutorialBTC
OpenClaw 2026.5.12 🦞
🧠 OpenAI setup defaults to Codex login
🛟 Runtime fallbacks + stalled-stream recovery
📬 Telegram polling survives stalls
⚡ Leaner installs, faster startup paths
Faster, calmer, harder to wedge.
https://github.com/openclaw/openclaw/releases/tag/v2026.5.12
OpenClaw🦞 / @openclaw:
R to @openclaw: OpenAI setup now starts with ChatGPT/Codex login by default. Codex runs also picked up OAuth/profile reuse, source replies in WebChat/TUI, MCP server projection, and fewer raw auth-refresh failures. https://docs.openclaw.ai/providers/openai
OpenClaw🦞 / @openclaw:
R to @openclaw: Agent runs got better at recovering instead of just stopping: ACP can try fallback runtimes before emitting output, provider stalls advance through fallback/profile rotation, and silent backend failures now surface visible errors. https://docs.openclaw.ai/cli/acp
OpenClaw🦞 / @openclaw:
R to @openclaw: Telegram got a sturdier inbox path: Bot API polling now runs in an isolated worker with a durable local spool, stall detection keys off getUpdates, HTML replies keep formatting, and ignored group media stays quiet. https://docs.openclaw.ai/channels/telegram
OpenClaw🦞 / @openclaw:
R to @openclaw: WebChat is less twitchy: pick near-bottom follow, always-follow, or manual scroll mode, then use New messages when you want control. Control UI also got a recovery panel for blank app loads. https://docs.openclaw.ai/web/webchat
OpenClaw🦞 / @openclaw:
R to @openclaw: Plugin installs and startup got leaner. Bedrock, Bedrock Mantle, Slack, OpenShell, Anthropic Vertex, and WhatsApp now keep their dependency cones out of core until installed. Plugin/help paths avoid heavy discovery too. https://docs.openclaw.ai/plugins/plugin-inventory
OpenClaw🦞 / @openclaw:
R to @openclaw: Security pass: Windows home roots are blocked in sandbox binds, provider credentials now resolve through structured SecretRefs, setup/browser/control UI pairing got stricter, and transcript/tool-result redaction is more consistent. https://docs.openclaw.ai/gateway/security
OpenClaw🦞 / @openclaw:
R to @openclaw: Gateway clients got cleaner streams: v4 chat deltas carry explicit delta/replace frames, SDK clients do not need local diffing, and OpenAI-compatible requests now preserve max_tokens / max_completion_tokens upstream. https://docs.openclaw.ai/gateway/protocol
OpenClaw🦞 / @openclaw:
RT by @openclaw: I am stoked! You can also do real time chat with your oauth from OpenAI. Little proud of that one. Getting to chat with my agent with real time and have them do things has been great to test in the beta.
#HowToClaw@TutorialBTC