Agent infrastructure
terminal-bench-science
harbor-framework/terminal-bench-science
A community benchmark evaluating AI agents on expert-curated, terminal-verifiable scientific research workflows.
Topics
Related projects
wisp-science1.1kLocal-first desktop AI research workbench for scientific computing with Python and R, integrating literature, databases, MCP bioinformatics tools, GPU runtimes, and major LLM providers.
ClawX7.6kA desktop client for OpenClaw agents that replaces CLI orchestration with chat, scheduling, channels and skill management.
agenta4.9kAn open-source workspace for building, sharing, and running specialized AI agents in chat and in the background with tracing and team access.
metorial3.4kAn open-source identity and access control plane that sits between agents and integrations, handling authentication, scoped permissions, and auditability through unified SDKs.
agentfield2.7kAn open-source AI backend control plane that turns agent functions into scalable REST services with routing, retries, discovery and observability.
intelligent-terminal2.2kAn experimental Windows Terminal fork with native ACP agent integration, offering a docked agent pane, session management, error detection and support for multiple coding-agent CLIs.