Bundle
managed-agents
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
sandbaseai642
Browse
20 results
Bundle
dsh-maze
The execution maze for DeepSeek Harness agents: see how the agent actually worked — main path, detours and backtracks on one timeline, with data tracks, deterministic analysis, and multi-session comparison
lamost42364
Bundle
@loongsuite/dsh-plugin
Standalone OpenTelemetry GenAI observability plugin for DeepSeek Harness
loongsuite22
Bundle
dsh-session-audit
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.
bwndlct4
Bundle
@huichangzz/dsh-postmortem
Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.
zzh-newlearner2
Bundle
dsh-task-graph
Task Flow / Execution Graph plugin for DeepSeek Harness (DSH): visualize a single task's full execution — turns, LLM steps, tools, skills, subagents, retries, parallel branches — as an interactive DAG with live updates and trajectory linkage.
KevinZhangNothing2
Bundle
dsh-agent-replay
Replay and share redacted DeepSeek Harness sessions as standalone HTML
forrestsweet2
Bundle
@webwalkerhq/dsh-replay-lab
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
tbxy092
Bundle
dsh-plugin-trace-insight
A continuous, model-assisted semantic debugger for DeepSeek Harness trajectories.
Liu-Bot242
Bundle
dsh-agent-observe
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection
dsh-plugin-evaluation1
Bundle
dsh-plugin-runbook
A Jupyter-shaped, Git-backed research surface for DeepSeek Harness: session lineage, stable script attempts, visual evidence, provenance, safe previews, and explicitly confirmed reruns.
zhan-tz1
Bundle
dsh-litefuse-plugin
Litefuse observability for DeepSeek Harness: every user turn becomes one agent trace with per-call generations, tool spans, and subagent subtrees
litefuse1
Bundle
dsh-subagent-inspector
Read-only live subagent process inspector for DeepSeek Harness Web
chongyangdu2008-cyrus1
Bundle
dsh-context-lens
Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.
gordonlu1
Bundle
dsh-agent-run-logger
Local JSONL run traces and a live viewer for DeepSeek Harness sessions
bluefateludi1
Bundle
@bryan-cmf/dsh-infra-observability
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.
Bryan-cmf1
Bundle
dsh-agent-quality-diagnosis
DSH Web plugin for Agent execution quality diagnosis reports.
cat5521
Bundle
dsh-product-subagent-console
Design, observe, diagnose, and reuse evidence-backed multi-Agent work in DeepSeek Harness
Jokasa71
Bundle
@tbxy09/dsh-replay-lab
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
tbxy09
Bundle
dsh-deepcanary
Know when your DeepSeek Harness tasks need you. Local alerts, quiet notifications, and a task inbox.
Oscar-Williams