observability

Python toolkit for building LLM agents with MCP servers, skills folders, memory, streaming, and metrics support.

Open-source CLI that analyzes AUDR traces to find avoidable LLM calls, wasted tool usage, context growth, and other execution inefficiencies in agent runs.

JarvisCore is a Python framework for building distributed multi-agent systems with peer-to-peer discovery, crash recovery, zero-trust credential handling, shared memory, and built-in observability.

AgentTrace is a Python-based observability and runtime self-healing system for AI agent workflows. It logs multi-step tool calls, surfaces latency issues, and attempts to repair malformed LLM tool arguments before they crash a run.

Read-only Kubernetes context engine that turns cluster state into structured context for SREs, scripts, and AI agents. It offers CLI commands for explain, graph, trace, health, dump, and a read-only HTTP API.

A post about TMA1 v2, a local observability and context-sharing tool for coding agents. It adds an MCP server, hook-based context injection, and cross-agent sharing between Claude Code and Codex.

Bifrost’s Agent Gateway adds A2A agent calls to its existing gateway, with logs, access control, transport bridging, and callback handling across models, tools, and agents.

AgentPulse is an observability tool for multi-agent systems, with run history, crash tracking, metrics, and investigation views for reviewing agent executions.