Bundle
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
Bundle
Session execution analytics and audit reports for DeepSeek Harness. Understand how your agent actually worked: steps, tool calls, failures, repeated actions, token usage and verification signals.
Bundle
Disk-usage audit for DeepSeek Harness (dsh) data directories: total size, per-directory breakdown, largest files, and oversized-file warnings (session logs can hit hundreds of MB). Zero runtime dependencies, read-only. CLI + agent-callable disk_audit tool.
Bundle
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
Bundle
DSH++ — a local-first control plane for DeepSeek Harness. Plugin security auditing and workflow regression testing for dsh, in a CLI plus a loopback web console.
limlnx523