MCP Server · AI & ML

agent-obs

Trace AI agent execution: every tool call, every error, every dollar. Open source agent observability for Claude, Cursor, opencode, and any MCP-compatible agent. Local-first, free forever.

Tier 1 sealed by lossy-channel-auto

Source: https://github.com/KryptosAI/agent-observability
Registry namespace: io.github.kryptosai/agent-observability
Imported from: npm
License: MIT
Pricing: Open Source
Added: Jul 24, 2026

Seal evidence

Auto-sealed Tier 1 on import from npm registry search. Lossy Channel layers 1–2 to be backfilled by the Foreman.

L1-wash

Pinned to 1.0.7

Similar tools

MCP Server Tier 1

agentforge

DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools.

🧠 AI & ML pitched by Alex

MCP Server Tier 1

onyx-mcp

Proof of Agent Execution — the neutral trust layer issuing portable, signed execution credentials for AI agents (x402 · MCP · ERC-8004).

🧠 AI & ML

MCP Server Tier 1

blender-copilot

Blender MCP server for AI 3D creation, automation, and VRChat avatar workflows

🧠 AI & ML

MCP Server Tier 1

mcp-memory-server

Persistent shared knowledge graph memory for AI agents via MCP — built for kagent, compatible with any MCP-capable agent framework

🧠 AI & ML