The Observability Index / Agent Observability / #50
duqaXxX/seedeep
by duqaXxX · Agent Observability · updated today
What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.
61
momentum
45
stars
2
forks
#50
rank
agent-observabilityagentic-codingai-agentsai-codinganthropicbunclaudeclaude-codecontext-engineeringcontext-windowcost-trackingdeveloper-tools
View on GitHub →
More in Agent Observability
mission-control
builderz-labs
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and ope
agenta
Agenta-AI
Agenta is a workspace where you and your team build agents and automations.
agenttrail
sodiumsun
Local observability for AI coding agents. Agenttrail Map shows project structure and activ
latitude-llm
latitude-dev
Open-source observability for AI agents. Find where your agents fail, dispatch your coding