#agent-observability

Codex Task Watchdog

Local-first watchdog and Codex skill for stalled tool calls, long-running task monitoring, oversized-thread diagnosis, bounded cleanup, and...

ax: Agent Experience Layer for Claude Code

the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

MCP Capability Ledger

Infer least-privilege MCP tool policies from agent traces

Conductor

🎼 See what every live Claude Code window is doing — and reply to them. Read-only situational awareness + tmux control, as a CLI, a web cock...

Lookspan

Local-first observability dashboard for AI agents. MCP-native. Look at every span your agents emit.

Reactive Agents TS

A composable TypeScript framework for building reliable LLM agents on a harness you fully control. The same code runs the agent loop on ever...

Atrib

Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable...

AgentProvenance

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc...

Dunetrace

Real-time monitoring of production AI agents.

Agentlens

Open-source observability and audit trail platform for AI agents. MCP-native, tamper-evident event logging, real-time dashboard.

Hyperweave

Portable visual output layer for agents. One API call, one SVG. Zero dependencies, renders in any markdown.

Reins

Stop AI agents from doing things you didn't ask for.