OpenClaw

OpenClaw's 2026.3.28 update switched xAI integration to the Responses API and added plugin prompts that can request user permission during behavior. One user reported a /v1/models failure after upgrading with a missing operator.write scope, so teams should check auth changes before deploying.

Every opened Plus One, a hosted OpenClaw that lives in Slack, comes preloaded with internal skills, and works with a ChatGPT subscription or other API keys. It lowers the ops burden for deployed coworkers, so teams can test packaged agents before building their own stack.

OpenClaw 2026.3.24 adds native Microsoft Teams, OpenWebUI sub-agent access, Slack reply buttons, and a control surface for skills and tools. The release expands where the runtime can plug into enterprise workflows, while also increasing the surface area teams need to secure.

OpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.

OpenClaw's maintainer asked users to switch to the dev channel and stress normal workflows before a large release that may break plugins. Watch harness speed, context plugins, and permission boundaries closely while the SDK refactor lands.

OpenClaw 3.13 now connects to a real Chrome 146 session over MCP so agents can drive your signed-in browser instead of a separate bot context. Update if captchas or auth state were blocking your web automation flows.

LlamaIndex open-sourced LiteParse, a model-free local parser for 50+ document types that preserves layout well enough for agent workflows. Use it as a fast first pass before expensive OCR or VLM parsing, especially when you need table structure and local execution.

New third-party tests put MiniMax M2.7 at a 34% hallucination rate, roughly 65 tps, and 27.04% on Vibe Code Bench while users pushed it through physics-heavy web demos. It looks increasingly viable for agent workflows, but performance still swings by task and harness.

Xiaomi launched MiMo-V2-Pro through its own API and confirmed Hunter Alpha was an early internal build. That makes the model easier to compare directly for long-context coding and tool-use workloads.

NVIDIA introduced NemoClaw, a reference stack that installs OpenShell and adds sandbox, privacy, and policy controls around OpenClaw. Use it if you want always-on agents on RTX PCs, DGX Spark, or cloud without building the security layer yourself.

OpenClaw added Ollama as an official provider through openclaw onboard --auth-choice ollama, alongside documented OpenAI-compatible self-hosted backends such as vLLM. Use it to run Claw workflows against local or custom models instead of a single hosted stack.

OpenClaw-RL released a fully asynchronous online training stack that turns live interaction feedback into ongoing agent updates with binary rewards and token-level OPD corrections. Use it as a starting point for online agent improvement only if you can score rollouts reliably and manage privacy risk.

OpenClaw beta added live control of a real Chrome session through Chrome DevTools MCP; the project also added native SGLang provider support and parallel tool calling work. Try it if you need self-hosted agents to handle authenticated browser flows with local inference backends.