Blog
Discover how AIPOCH Skills and AI agents like OpenClaw assist scientific research.
Open Science v0.23.0: Read Papers with the Agent and Keep Evidence in Context
Open Science v0.23.0 adds linked PDF reading context, click-to-reveal evidence, live notebook variables, Tencent plans, and safer local-data handling.
Open Science v0.21.0: CodeBuddy, Annotations, and Expanded Model Catalogs
Open Science v0.21.0 adds CodeBuddy, persistent text and image annotations, larger OpenCode catalogs, configuration markers, and Windows SSH passwords.
How to Reference Another Research Session in Open Science
Use Open Science Session References to give one research turn read-only access to another active Session without merging histories or creating permanent memory.
Open Science v0.20.2: Read Sources, Inspect Variables, and Navigate Sessions Faster
Open Science v0.20.2 adds a Spanish interface, sandboxed source previews, live Python and R variable inspection, session previews, and new model options.
How Open Science Detects Stale Notebook Outputs
See how Open Science tracks Python and R dependencies across runs, flags stale or unknown outputs, and helps researchers decide what to review and rerun.
Open Science v0.20.1: Describe Sessions, Inspect Usage, and Transfer MCP Configs
Open Science v0.20.1 adds editable session details, per-call usage charts, safe MCP configuration transfer, draft redo, and networking fixes.
Open Science v0.20.0: Connect Sessions and Keep Long Research Threads Fast
Open Science v0.20.0 adds session references, live Side Chat advisories, restorable long-paste attachments, and faster long-session navigation.
Open Science v0.19.0: Grok OAuth, Notebook Tracking, and Faster Sessions
Open Science v0.19.0 adds xAI Grok OAuth, governed Marketplace Specialists, notebook dependency tracking, mid-turn steering, and faster session startup.
AI Agent vs MCP Server: What Is the Difference?
Learn how AI agents and MCP servers differ, how they work together, and when to choose an agent, an MCP server, both, or a direct API in AI system design.
Run Research Tasks on Remote SSH Hosts with Open Science
Learn how to configure a remote SSH host, enable and select it per session, and use Open Science permissions, Skills, and artifacts to review remote work.
Open Science v0.18.2: More Control Over Exports, Connectors, and Agent Streams
Open Science v0.18.2 adds turn-selective Markdown and PDF exports, pre-registered OAuth clients, Russian localization, and responsive high-volume agent streams.
How a Specialist AI Agent Works in Open Science
Learn how Open Science Specialists combine a reusable AI agent role with scoped Skills, Connectors, permissions, and researcher review for research workflows.
Open Science v0.18.1: Choose Compute per Session and See Clearer Alerts
Open Science v0.18.1 adds session-scoped compute hosts, richer message-center context, French localization, new CLI controls, and reliability fixes.
What Model-Agnostic Means in Open Science
Learn how Open Science combines selectable agent runtimes, provider connections, models, and reasoning controls—and where compatibility, data flow, and hot-switching limits still apply.
Open Science v0.18.0: Organize Capabilities and Configure Specialists Faster
Open Science v0.18.0 adds cross-resource tags, faster Specialist browsing, redesigned Skill management, SSH password access, and Korean localization
Message Branches, New Sessions, and Side Conversations in Open Science
Open Science provides three related ways to keep exploratory work from derailing the main thread: message branches, Branch in new session, and Side Conversations. They differ in scope, context, and persistence; only the first two are conversation-branching mechanisms.
Open Science v0.17.0: Reusable Specialists and Clearer Research Context
Open Science v0.17.0 adds signed Specialist packages, persistent image-derived context for text-only models, context composition insights, and version-aware plan previews.
DeepSeek Harness for Scientific Agents: What's Still Missing
DeepSeek Harness makes agent runtimes composable. This architecture review examines the added controls scientific workflows need for plans, artifacts, provenance, branching, and review.
Open Science v0.16.0: a usage dashboard, a composer queue, and headless plan controls
Open Science v0.16.0 is out. This release adds a Usage dashboard, a session-scoped composer message queue, the ability to branch from completed agent messages, view-in-context artifact navigation, and CLI plan controls — plus a round of reliability and host-sdk improvements.
How to Organize a Research Project in Open Science
Learn when to use Projects, Sessions, message branches, the Files Library, and Artifact Versions to keep AI-assisted research organized and traceable.
How Open Science Extends a Research Agent
Learn how Open Science combines reusable Skills, permissioned MCP Connectors, Specialist profiles, and SSH Remote Compute—and where each capability stops.