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.
22 results
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console.
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
Read-only DSH session insights and local model usage statistics
Standalone OpenTelemetry GenAI observability plugin for DeepSeek Harness
Tencent Cloud Service CLS observability plugin for DeepSeek Harness — direct upload to Tencent Cloud CLS
What a DeepSeek Harness run costs in tokens, money, and time. OpenTelemetry traces, metrics, and logs in GreptimeDB, with seven Grafana dashboards.
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.
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.
A continuous, model-assisted semantic debugger for DeepSeek Harness trajectories.
Replay and share redacted DeepSeek Harness sessions as standalone HTML
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.
Local JSONL run traces and a live viewer for DeepSeek Harness sessions
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.
Design, observe, diagnose, and reuse evidence-backed multi-Agent work in DeepSeek Harness
Read-only live subagent process inspector for DeepSeek Harness Web
A Jupyter-shaped, Git-backed research surface for DeepSeek Harness: session lineage, stable script attempts, visual evidence, provenance, safe previews, and explicitly confirmed reruns.
DSH Web plugin for Agent execution quality diagnosis reports.
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
Litefuse observability for DeepSeek Harness: every user turn becomes one agent trace with per-call generations, tool spans, and subagent subtrees
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection
Know when your DeepSeek Harness tasks need you. Local alerts, quiet notifications, and a task inbox.