computesdk

Current plans

Direct accepted alternatives

cua · job 82%runtime · job 74%mistle · job 74%cua_ai · job 82%opensandbox · job 81%Ink · job 81%ternlang · job 75%litellm_agent_platform · job 84%architect_mcp_server · job 84%mcp_test_2 · job 79%ghostdesk · job 79%mcp_filesystem · job 76%basic_fns_mcp · job 77%mcpd · job 80%mithril · job 73%pi-mcp · job 74%mcp_workspace · job 75%Together Code Interpreter MCP Server · job 77%mcp_background_job · job 74%docker_mcp_chatgpt · job 72%Reachpad MCP · job 75%coding_tools_mcp · job 73%local_coding_agent · job 75%freya_mcp_server · job 74%taskflow_ai · job 72%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.

Inspect histories

Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.

This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series