OpenClaw v2026.4.12 Released — Active Memory, exec policy controls, and smoother setup paths
OpenClaw v2026.4.12 expands memory and QA tooling, adds local exec-policy commands, and improves setup and remote-discovery ergonomics across the platform.
OpenClaw v2026.4.12 was published on 2026-04-13T12:35:53Z by vincentkoc. OpenClaw v2026.4.12 expands memory and QA tooling, adds local exec-policy commands, and improves setup and remote-discovery ergonomics across the platform.
Quick answer
This release leans into operator control. It gives teams more explicit levers for memory behavior, execution approvals, runtime command discovery, and test credentials.
What's new in this release
- QA/lab: add Convex-backed pooled Telegram credential leasing plus `openclaw qa credentials` admin commands and broker setup docs. (#65596) Thanks @joshavant.
- 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. (#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.
- CLI/exec policy: add a local `openclaw exec-policy` command with `show`, `preset`, and `set` subcommands for synchronizing requested `tools.exec.*` config with the local exec approvals file, plus follow-up hardening for node-host rejection, rollback safety, and sync conflict detection. (#64050)
- Gateway: add a `commands.list` RPC so remote gateway clients can discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata. (#62656) Thanks @samzong.
Why developers should care
Teams using Active Memory, QA automation, gateway RPC discovery, or structured approval policies should pay attention here.
Upgrade notes
The fetched GitHub release notes mention breaking-change risk. Review the full release notes carefully before upgrading production agents, channels, or plugin-heavy environments.
Source
Full release notes: https://github.com/openclaw/openclaw/releases/tag/v2026.4.12
Frequently asked questions
What changed in OpenClaw v2026.4.12?
QA/lab: add Convex-backed pooled Telegram credential leasing plus `openclaw qa credentials` admin commands and broker setup docs. (#65596) Thanks @joshavant.; 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. (#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.
Does OpenClaw v2026.4.12 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/v2026.4.12
Who should pay attention to OpenClaw v2026.4.12?
Teams using Active Memory, QA automation, gateway RPC discovery, or structured approval policies should pay attention here.