v2026.7.1-beta.2最新預發佈
openclaw 2026.7.1-beta.2
Highlights OpenAI GPT-5.6 support: OpenClaw now recognizes the GPT-5.6 model family across catalog, capability, and runtime selection paths. (#98333) Thanks @steipete-oai. External harness...
398更新日誌 →
OpenClaw 版本發佈
即時了解 OpenClaw 最新版本、更新日誌和下載資訊。
v2026.7.1-beta.1預發佈
openclaw 2026.7.1-beta.1
Highlights OpenAI GPT-5.6 support: OpenClaw now recognizes the GPT-5.6 model family across catalog, capability, and runtime selection paths. (#98333) Thanks @steipete-oai. External harness...
353更新日誌 →
v2026.6.11穩定版
openclaw 2026.6.11
We heard the feedback. v2026.6.11 focuses on the rough edges that make OpenClaw feel less dependable, with fixes for misplaced replies, stuck sends, reconnects, model setup failures, and safer admin...
55,272更新日誌 →
v2026.6.11-beta.2預發佈
openclaw 2026.6.11-beta.2
2026.6.11 Highlights More capable channel control: Slack relay mode, native Mattermost /oc_queue, and per-DM model overrides make channel operations easier to automate and tune. (#94707, #95546,...
202更新日誌 →
v2026.6.11-beta.1預發佈
openclaw 2026.6.11-beta.1
2026.6.11 Highlights More capable channel control: Slack relay mode, native Mattermost /oc_queue, and per-DM model overrides make channel operations easier to automate and tune. (#94707, #95546,...
更新日誌 →
v2026.6.10穩定版
openclaw 2026.6.10
Automatic fast mode starts short conversations quickly, then returns longer or fallback work to normal mode without losing visible state. Provider routing, channel progress, session identity, and...
32,687更新日誌 →
v2026.6.10-beta.2預發佈
openclaw 2026.6.10-beta.2
2026.6.10 Highlights Automatic fast mode for talks: OpenClaw can enable fast mode for short conversational turns, then return to normal mode for longer runs with bounded fallback and delivery...
157更新日誌 →
v2026.6.10-beta.1預發佈
openclaw 2026.6.10-beta.1
Highlights More reliable agent turns and session state: OpenClaw now preserves pending subagent completion announcements, keeps chat history transcripts non-empty, maintains media index alignment,...
98更新日誌 →
v2026.6.9穩定版
openclaw 2026.6.9
2026.6.9 Highlights Richer Telegram delivery: Telegram now sends rich HTML, preserves rich markdown and sticker paths, renders progress drafts and command output more faithfully, normalizes HTML...
20,882更新日誌 →
v2026.6.9-beta.1預發佈
openclaw 2026.6.9-beta.1
2026.6.9 Highlights Richer Telegram delivery: Telegram now sends rich HTML, preserves rich markdown and sticker paths, renders progress drafts and command output more faithfully, and keeps mentions...
147更新日誌 →
v2026.6.8穩定版
openclaw 2026.6.8
2026.6.8 Highlights Richer channel delivery: Telegram and WhatsApp are less brittle: Telegram renders structured text with tables, lists, expandable blockquotes, preserved intentional line breaks,...
33,545更新日誌 →
v2026.6.8-beta.2預發佈
openclaw 2026.6.8-beta.2
2026.6.8 Highlights Richer channel delivery: Telegram and WhatsApp are less brittle: Telegram renders structured text with tables, lists, expandable blockquotes, preserved intentional line breaks,...
92更新日誌 →
v2026.6.8-beta.1預發佈
openclaw 2026.6.8-beta.1
2026.6.8 Highlights Richer channel delivery: Telegram and WhatsApp are less brittle: Telegram renders structured text with tables, lists, expandable blockquotes, preserved intentional line breaks,...
131更新日誌 →
v2026.6.7-beta.1預發佈
openclaw 2026.6.7-beta.1
2026.6.7 Highlights Durable channel replies: Telegram polling and preview failures recover instead of ending a stream, Slack keeps delivered replies in the transcript, and top-level image sends...
更新日誌 →
v2026.6.6穩定版
openclaw 2026.6.6
2026.6.6 Highlights Tighter security boundaries: transcript, sandbox, MCP, browser, channel, and exec-approval paths now fail closed around unsafe access, timed-out approvals, and malformed boundary...
2,248更新日誌 →
v2026.6.6-beta.2預發佈
openclaw 2026.6.6-beta.2
2026.6.6 Highlights Tighter security boundaries: transcript, sandbox, MCP, browser, channel, and exec-approval paths now fail closed around unsafe access, timed-out approvals, and malformed boundary...
46更新日誌 →
v2026.6.6-beta.1預發佈
OpenClaw 2026.6.6-beta.1
2026.6.6 Highlights Tighter security boundaries: transcript, sandbox, MCP, browser, channel, and exec-approval paths now fail closed around unsafe access, timed-out approvals, and malformed boundary...
更新日誌 →
v2026.6.5穩定版
openclaw 2026.6.5
2026.6.5 Highlights Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132)...
55,753更新日誌 →
v2026.6.5-beta.6預發佈
openclaw 2026.6.5-beta.6
2026.6.5 Highlights Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132)...
54更新日誌 →
v2026.6.5-beta.5預發佈
openclaw 2026.6.5-beta.5
2026.6.5 Highlights Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132)...
47更新日誌 →
v2026.6.5-beta.3預發佈
OpenClaw 2026.6.5-beta.3
2026.6.5 Highlights Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132)...
29更新日誌 →
v2026.6.5-beta.2預發佈
openclaw 2026.6.5-beta.2
2026.6.5 Highlights Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132)...
491更新日誌 →
v2026.6.5-beta.1預發佈
openclaw 2026.6.5-beta.1
2026.6.5 Highlights Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132)...
279更新日誌 →
v2026.6.2-beta.1預發佈
openclaw 2026.6.2-beta.1
2026.6.2 Highlights Governed plugin and skill installs: the old dangerous-code scanner gives way to an operator install policy with clearer doctor, CLI, ClawHub, package, archive, source, upload, and...
更新日誌 →
v2026.6.1穩定版
openclaw 2026.6.1
2026.6.1 Highlights Resilient agent and Codex runs: interrupted tool calls, stale session bindings, compaction handoffs, auth-profile failover, reasoning-tag cleanup, yielded subagents, and...
37,032更新日誌 →
v2026.6.1-beta.3預發佈
openclaw 2026.6.1-beta.3
2026.6.1 Highlights Resilient agent and Codex runs: interrupted tool calls, stale session bindings, compaction handoffs, auth-profile failover, reasoning-tag cleanup, yielded subagents, and...
65更新日誌 →
v2026.6.1-beta.2預發佈
openclaw 2026.6.1-beta.2
2026.6.1 Highlights Resilient agent and Codex runs: interrupted tool calls, stale session bindings, compaction handoffs, auth-profile failover, reasoning-tag cleanup, yielded subagents, and...
73更新日誌 →
v2026.6.1-beta.1預發佈
openclaw 2026.6.1-beta.1
2026.6.1 Highlights Resilient agent and Codex runs: interrupted tool calls, stale session bindings, compaction handoffs, auth-profile failover, reasoning-tag cleanup, yielded subagents, and...
38更新日誌 →
v2026.5.31-beta.4預發佈
openclaw 2026.5.31-beta.4
2026.5.31 Highlights Faster Control UI chat: transcript rendering, draft persistence, pending-send paint, scrolling, and first-message work no longer block one another while a conversation is active....
更新日誌 →
v2026.5.31-beta.3預發佈
openclaw 2026.5.31-beta.3
2026.5.31 Highlights Faster Control UI chat: transcript rendering, draft persistence, pending-send paint, scrolling, and first-message work no longer block one another while a conversation is active....
更新日誌 →