OpenClaw v2026.4.10 Released — Bundled Codex provider and Active Memory improvements
OpenClaw v2026.4.10 introduces the bundled Codex provider path, extends Active Memory, and broadens media generation and Microsoft Teams actions.
OpenClaw v2026.4.10 was published on 2026-04-11T02:43:25Z by steipete. OpenClaw v2026.4.10 introduces the bundled Codex provider path, extends Active Memory, and broadens media generation and Microsoft Teams actions.
Quick answer
The Codex provider addition is the headline. It separates Codex-managed auth and model behavior from the normal OpenAI provider path while continuing to improve memory and media workflows.
What's new in this release
- Models/Codex: add the bundled Codex provider and plugin-owned app-server harness so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the normal OpenAI provider path. (#64298)
- Memory/Active Memory: add a new optional Active Memory plugin that gives OpenClaw a dedicated memory sub-agent right before the main reply, so ongoing chats can automatically pull in relevant preferences, context, and past details without making users remember to manually say "remember this" or "search memory" first. Includes configurable message/recent/full context modes, live `/verbose` inspection, advanced prompt/thinking overrides for tuning, and opt-in transcript persistence for debugging. Docs: https://docs.openclaw.ai/concepts/active-memory. (#63286) Thanks @Takhoffman.
- macOS/Talk: add an experimental local MLX speech provider for Talk Mode, with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback. (#63539) Thanks @ImLukeF.
- Tools/video generation: add Seedance 2.0 model refs to the bundled fal provider and submit the provider-specific duration, resolution, audio, and seed metadata fields needed for live Seedance 2.0 runs.
- Microsoft Teams: add message actions for pin, unpin, read, react, and listing reactions. (#53432) Thanks @sudie-codes.
Why developers should care
Teams testing Codex-native models, Active Memory, Teams automation, or video generation should review this release.
Upgrade notes
No explicit breaking changes were called out in the fetched GitHub release notes. Even so, teams using custom providers, plugins, or channel integrations should review the full release notes before rolling forward.
Source
Full release notes: https://github.com/openclaw/openclaw/releases/tag/v2026.4.10
Frequently asked questions
What changed in OpenClaw v2026.4.10?
Models/Codex: add the bundled Codex provider and plugin-owned app-server harness so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the normal OpenAI provider path. (#64298); Memory/Active Memory: add a new optional Active Memory plugin that gives OpenClaw a dedicated memory sub-agent right before the main reply, so ongoing chats can automatically pull in relevant preferences, context, and past details without making users remember to manually say "remember this" or "search memory" first. Includes configurable message/recent/full context modes, live `/verbose` inspection, advanced prompt/thinking overrides for tuning, and opt-in transcript persistence for debugging. Docs: https://docs.openclaw.ai/concepts/active-memory. (#63286) Thanks @Takhoffman.; macOS/Talk: add an experimental local MLX speech provider for Tal
Does OpenClaw v2026.4.10 include breaking changes?
No explicit breaking changes were called out in the fetched GitHub release notes. Review the full release notes before upgrading provider-heavy, channel-heavy, or plugin-heavy environments: https://github.com/openclaw/openclaw/releases/tag/v2026.4.10
Who should pay attention to OpenClaw v2026.4.10?
Teams testing Codex-native models, Active Memory, Teams automation, or video generation should review this release.