Joined December 2025
33 Photos and videos
Pinned Tweet
Friends of Clawd Discord is now live! A place to hang out, share your Clawdis setups, ask questions, and help each other build cool stuff with AI assistants. Join the crustacean crew: discord.gg/qkhbAGHRBT
104,449
525
4,117
2,887,827
OpenClaw 2026.6.6 🦞 🔒 Tighter security boundaries 💬 Safer Telegram iMessage delivery 🧠 Claude Fable 5 OpenRouter OAuth ⚡ Faster Control UI first replies Less weird, more work done. github.com/openclaw/openclaw…
118
84
768
61,038
MCP gets Streamable HTTP loopback transport, OAuth/SSE auth fixes, and broader schema compatibility, so external clients and OpenClaw-managed servers hit fewer weird edges. docs.openclaw.ai/cli/mcp
3
1
20
10,309
Control UI starts faster and answers sooner: cached model metadata, no startup catalog wait, lazy slash commands, first-event tracing, and slow-reply diagnostics. docs.openclaw.ai/web/control…
2
2
25
9,378
OpenClaw 2026.6.5 🦞 🔎 Parallel web search bundled 🛡️ security.installPolicy for skill/plugin installs 🎙️ Matrix voice thread fixes 🧠 Anthropic/MCP recovery hardened Less chaos. More claws. github.com/openclaw/openclaw…
114
81
760
74,368
QQBot now strips model reasoning/thinking scaffolding before native delivery, so users see the answer instead of raw internal narration. docs.openclaw.ai/channels/qq…
4
3
31
13,252
Anthropic extended-thinking sessions recover better after prompt-cache expiry or Gateway restart, and richer MCP tool blocks get normalized before they poison history. docs.openclaw.ai/providers/a…
3
6
23
12,224
OpenClaw🦞 retweeted
my most useful codex skill is an automation to scan over past conversations and create/refine skills based on the session history. @openclaw now does this automatically with skill workshops 🦞🎓
Agents should learn repeated work, but not by silently rewriting future runs. Skill Workshop turns reusable agent lessons into reviewable proposals you can tweak, apply, or reject before they become live skills. openclaw.ai/blog/openclaw-ag…
9
14
128
44,266
Agents should learn repeated work, but not by silently rewriting future runs. Skill Workshop turns reusable agent lessons into reviewable proposals you can tweak, apply, or reject before they become live skills. openclaw.ai/blog/openclaw-ag…
38
57
593
96,913