Changelog

Track every improvement to OpenClaw. New features, fixes, and platform updates.

v2026.5.12 feature

Telegram polling resilience and externalized provider plugins

  • Telegram ingress moved to an isolated worker with a durable local spool so polling survives main-loop stalls
  • Externalized Amazon Bedrock, Slack, OpenShell sandbox and Anthropic Vertex so installs only pull what you use
  • Sandbox blocks Windows USERPROFILE home roots so credential-bearing binds (.codex, .openclaw, .ssh) are denied
  • Added acp.fallbacks so ACP turns try backup runtime backends before any output is emitted
  • Control UI/WebChat persisted auto-scroll mode selector (follow streaming, near-bottom, or off)
  • Stale long-poll offsets discarded after Telegram bot token rotation so bots no longer silently skip messages
v2026.5.7 fix

Delivery, cron and channel reliability fixes

  • Cron list/show JSON now includes computed job status for external tooling
  • Agent delivery reports failure when an outbound send returns no adapter result
  • Telegram, Discord and WhatsApp routing and authorization fixes
  • Native commands and Active Memory toggles now require the correct admin scope
  • Plugin install/rollback uses a consistent npm lifecycle shell to avoid broken cleanup
v2026.5.6 fix

Codex OAuth routing hotfix

  • Reverted the 2026.5.5 doctor --fix repair that rewrote valid -codex/* OAuth routes
  • Plugin runtime fetch drops third-party header metadata that broke guarded/proxy requests
  • Web fetch bounds dispatcher cleanup so timed-out fetches return tool errors instead of hanging
  • Debug proxy normalizes captured fetch headers before replaying requests
v2026.5.5 fix

Sessions, runtime visibility and provider fixes

  • Sessions, status and Control UI surfaces now show each session agent runtime
  • doctor --fix repairs heartbeat-poisoned default sessions and stale TUI restore pointers
  • xAI Grok Responses models no longer receive unsupported reasoning-effort controls
  • OpenAI-compatible streaming flushes the first chunk so cold setups do not hang clients
  • Control UI chat keeps assistant progress text visible across history reloads
v2026.5.4 feature

Realtime Gemini voice bridge for Google Meet calls

  • Twilio Meet dial-in joins speak through the realtime Gemini voice bridge with paced audio
  • Windows loopback listener binds to 127.0.0.1 to avoid dual-stack localhost stalls
  • Codex audio transcription advertised in runtime/manifest metadata
  • Workspace-scoped plugin metadata reuse trims cold plugin scans on hot paths
  • Refreshed runtime/provider deps including Pi 0.73.0, , Anthropic, Slack and TypeScript
v2026.5.3 feature

Bundled file-transfer plugin and plugin install hardening

  • New file-transfer plugin: file_fetch, dir_list, dir_fetch and file_write with default-deny path policy
  • Hardened official plugin install, uninstall, update and ClawHub fallback paths
  • Added /steer for queue-independent steering of an idle active session
  • Unified streaming.mode "progress" drafts across Discord, Telegram, Matrix, Slack and Teams
  • doctor --fix now commits safe legacy migrations even when unrelated validation fails
v2026.5.2 feature

npm-first plugin cutover and startup leanness

  • External plugin install, update, doctor repair and beta-channel fallback moved to npm-first
  • Leaner and agent hot paths: startup, session listing, prompt prep and tool planning
  • Control UI and WebChat resilience across Sessions, Cron and long-running WebSockets
  • WhatsApp Channel/Newsletter outbound targets and Telegram/Discord/Slack/Signal fixes
  • Added Grok 4.3 to the bundled xAI catalog as the default xAI chat model
v2026.4.29 feature

Active-run steering by default and a people-aware memory wiki

  • Active-run steering on by default with visible-reply enforcement and opt-in follow-up commitments
  • Memory grows into a people wiki: provenance views, per-conversation Active Memory filters, partial recall on timeout
  • Added the NVIDIA provider with API-key onboarding and static catalogs
  • Restricted tool profiles no longer implicitly widen when tools.exec/tools.fs are configured
  • Security and ops: OpenGrep scanning, sharper GHSA triage, safer exec/pairing/owner-scope handling
v2026.4.27 feature

Codex Computer Use and the DeepInfra provider

  • Codex Computer Use setup with status/install commands and fail-closed MCP checks
  • DeepInfra joins the bundled provider set with model discovery, media, TTS and embeddings
  • Tencent Yuanbao docs/catalog and QQBot group chat, streaming and media upload
  • Opt-in operator-managed outbound proxy routing with strict forward-proxy validation
  • Manifest-first model catalogs make provider rows, aliases and suppressions easier to audit
v2026.4.26 feature

Cerebras provider and a bundled Claude importer

  • Added Cerebras as a bundled provider with onboarding and a static model catalog
  • migrate adds a bundled Claude Code / Claude Desktop importer with dry-run and backups
  • Control UI raw-config pending-changes diff panel with redaction until reveal
  • Asymmetric embedding endpoint config for memory search (inputType / query / document)
  • matrix encryption setup enables Matrix E2EE, recovery bootstrap and verification in one flow
v2026.4.25 feature

Voice reply upgrade and new TTS providers

  • /tts latest, chat-scoped auto-TTS controls, personas and per-agent/per-account voice overrides
  • New TTS provider coverage: Azure Speech, Xiaomi, Local CLI, Inworld, Volcengine and ElevenLabs v3
  • Plugin startup moves to the cold persisted registry, cutting broad manifest scans
  • Expanded OpenTelemetry coverage across model calls, tool loops, exec and memory pressure
  • Control UI adds PWA install support and Web Push notifications
v2026.4.24 major

Google Meet bundled participant plugin and DeepSeek V4

  • Google Meet joins as a bundled participant plugin with personal Google auth and Chrome/Twilio realtime sessions
  • DeepSeek V4 Flash and V4 Pro added to the bundled catalog; V4 Flash is the onboarding default
  • Realtime voice loops in Talk, Voice Call and Google Meet can consult the full agent
  • Browser automation gains coordinate clicks, longer action budgets and per-profile headless overrides
  • Breaking: removed the Pi-only api.registerEmbeddedExtensionFactory compatibility path
v2026.4.23 feature

Image generation through Codex and OpenRouter OAuth

  • OpenAI image generation and reference-image editing through Codex OAuth (no OPENAI_API_KEY needed)
  • OpenRouter image generation and edits via the image_generate tool
  • Optional forked context for native subagent runs so a child can inherit the requester transcript
  • Per-call timeoutMs for image, video, music and TTS generation tools
  • OpenAI/Codex transcript replay no longer synthesizes missing tool results
v2026.4.22 feature

xAI media generation and Voice Call streaming transcription

  • xAI image generation, text-to-speech and speech-to-text, plus xAI realtime transcription for Voice Call
  • Voice Call streaming STT for Deepgram, ElevenLabs and Mistral; ElevenLabs Scribe v2 batch transcription
  • Onboarding auto-installs missing provider and channel plugins
  • Direct Responses models use native web_search automatically when web search is enabled
  • WhatsApp configurable native reply quoting and per-chat systemPrompt injection

Want the full technical details? Check out the GitHub releases.

View all releases on GitHub →