· Updated
As agents gain more autonomy, memory bottlenecks and security risks become primary deployment hurdles. OpenClaw addresses both by automating the extraction of durable facts and hardening the system against SSRF (server-side request forgery). These fixes prevent untrusted tool outputs from tricking the agent into executing unauthorized commands.
You can now run character-vibes evaluation reports to compare how different models maintain a specific persona during tests. The update also streamlines Android pairing and allows Ollama models to display thinking tokens. This release is available as an open-source update on GitHub with new Plugin SDK exports.
OpenClaw 2026.4.9 🦞 🧠 Dreaming: REM backfill + diary timeline UI 🔐 SSRF + node exec injection hardening 🔬 Character-vibes QA evals 📱 Android pairing overhaul your agent now dreams about you. romantic or terrifying? yes. 🦞https://t.co/PzQw0AK9vn
More like this
