agent-observability
Tracked open-source repos tagged agent-observability, sorted by stars.
Related topics
Topics that frequently appear alongside agent-observability on the same repo.
Recent risers
Repos created in the last 90 days, tagged agent-observability.
- #1
See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.
★ 707 - #2
An infinite canvas for your AI coding agents. Every repo is a region on one zoomable live map - watch Claude Code, Codex, and Cursor sessions, plans, tool calls, and file changes in real time. Local, zero-dependency.
★ 650 - #3
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
★ 641
- #1
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.
★ 6,154+22Star change over the last 7 days - #2
Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.
★ 5,711+5Star change over the last 7 days - #3★ 4,676+33Star change over the last 7 days
- #4
Latitude is the open-source AI monitoring platform.
★ 4,615+9Star change over the last 7 days - #5★ 4,450+4Star change over the last 7 days
- #6★ 3,679+0Star change over the last 7 days
- #7★ 3,219+9Star change over the last 7 days
- #8
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.
★ 3,165+20Star change over the last 7 days - #9
Parseable is an open source, unified infrastructure observability platform built in Rust on a data lake architecture. It tracks logs, metrics, traces, and events across apps, agents, and systems, reducing storage costs by up to 90% through columnar telemetry compression.
★ 2,450+2Star change over the last 7 days - #10
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan
★ 1,719+203Star change over the last 7 days - #11
Trace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
★ 1,176-22Star change over the last 7 days - #12
open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.
★ 783+1Star change over the last 7 days - #13
TraceRoot - open-source observability and self-improving layer for AI agents. YC S25
★ 756+8Star change over the last 7 days - #14
See what your coding agents did and what it cost. Breaks each task down into work steps — tools used, files changed, tests run, time and tokens spent. Local-first dashboard for Claude Code, Codex, OpenCode, and more. No login, no telemetry.
★ 707+34Star change over the last 7 days - #15
An infinite canvas for your AI coding agents. Every repo is a region on one zoomable live map - watch Claude Code, Codex, and Cursor sessions, plans, tool calls, and file changes in real time. Local, zero-dependency.
★ 650+227Star change over the last 7 days - #16
Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.
★ 641+5Star change over the last 7 days
