Back to Topics Directory
Topic Hub

#agent-observability (15 Repositories)

Ranked open-source repositories tagged with #agent-observability, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

58.0%

Avg Review Latency

48.1h

Filter by language

15 repositories tagged #agent-observability

S TierTypeScript 120 1 GFIs

langgenius/mosoo

The open-source Agent Gallery and Gateway for Codex, Claude Agent SDK, and OpenCode. Developers publish an Agent once behind one HTTP API; users run it in an isolated cloud sandbox—no local harness setup, compute, or runtime infrastructure.

74.1%
Merge Rate
3h
First Review
100%
1st-Timers
5
Maintainers
A TierTypeScript 626

sandbaseai/sandbase-harness

Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.

80.6%
Merge Rate
2d
First Review
100%
1st-Timers
3
Maintainers
B TierPython 617

mikehasa/agentacct

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.

87.4%
Merge Rate
2d
First Review
67%
1st-Timers
0
Maintainers
A TierTypeScript 4.6k

latitude-dev/latitude-llm

Latitude is the open-source AI monitoring platform.

87.7%
Merge Rate
4d
First Review
77%
1st-Timers
10
Maintainers
B TierRust 259

taichuy/1flowbase

1flowbase: self-hosted AI gateway with protocol translation, dispatch, chat logs, built-in backend & React blocks to combine AI with business data. All managed by your Agent via MCP.

90.9%
Merge Rate
21h
First Review
100%
1st-Timers
0
Maintainers
B TierPython 1.0k

Jwuthri/Tracely-ai

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.

84.2%
Merge Rate
3d
First Review
75%
1st-Timers
0
Maintainers
A TierPython 3.1k

liaohch3/claude-tap

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.

83.8%
Merge Rate
4d
First Review
71%
1st-Timers
15
Maintainers
A TierRust 2.4k

parseablehq/parseable

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.

84.0%
Merge Rate
9d
First Review
67%
1st-Timers
8
Maintainers
A TierGo 5.7k

coze-dev/coze-loop

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.

73.7%
Merge Rate
1d
First Review
100%
1st-Timers
3
Maintainers
A TierGo 116

tma1-ai/tma1

Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

80.4%
Merge Rate
3d
First Review
75%
1st-Timers
3
Maintainers
B TierTypeScript 728 11 GFIs

traceroot-ai/traceroot

TraceRoot - open-source observability and self-improving layer for AI agents. YC S25

43.1%
Merge Rate
1d
First Review
33%
1st-Timers
29
Maintainers
D TierHTML 448

sodiumsun/agenttrail

Local observability map for AI coding agents. Watch Claude Code, Codex, and Cursor plans, tool calls, file changes, and progress in real time.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierHTML 304

stainlu/hermes-labyrinth

Read-only observability plugin for Hermes Agent: journeys, crossings, guideposts, and reports.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 755

Jwuthri/Tracely

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.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 781

chirpz-ai/pandaprobe

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.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
Best Agent-observability Open Source Repositories & C-Rank™ | GetMerged