R_REDDYX.XYZ

Observability: open-source projects on GitHub

92 repositories on Observability, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.

// RELATED TOPICS

LLM 2094MCP 1602AI Agents 1319Claude Code 1595Monitoring 52LLMOps 82Opentelemetry 33Openai 690Self Hosted 360Devops 82Developer Tools 620Langchain 196Codex 849AI Agent 690
zenml-io/kitaru

KITARU: AI AGENTS IN PRODUCTION

kitaru lets you record, replay, and improve AI agents in production on ZenML. Debugging and optimization become simpler and faster.

★ 319 · Python
heaven999b/hello-agent-system

Enterprise AI Agent Design Course

17 bilingual lessons teaching enterprise AI agent system design with hands-on exercises covering tools, RAG, security, evals, and distributed execution.

★ 316 · Python
runtm-ai/runtm

RUNTM: ISOLATED SANDBOXES

Open sandbox for AI agents: isolated environments where Claude Code and Cursor write and deploy code.

★ 306 · Python
chmonitor/chmonitor

CHMONITOR - SMART CLICKHOUSE MONITOR

Open-source advisor for ClickHouse: real‑time monitoring and AI‑based recommendations for indexes, partitions, and materialized views.

★ 305 · TypeScript
keelab/keelith

KEELITH GO FRAMEWORK FOR CLOUDS

Keelith — a production‑oriented Go framework for building distributed applications. It provides explicit lifecycle, transport, governance, observability and contract‑firs

★ 295 · Go
tobilg/ai-observer

AI OBSERVER: LOCAL MONITORING

Universal local monitoring system for AI coding assistants, collecting metrics and logs in real time.

★ 294 · Go
Brain0-ai/brain0

BLACK BOX FOR AI CODE

brain0 links every commit to agent prompts. Detects drift, audits agent data access (DLP), assesses risk from evidence, stores MCP memory, and emits signed provenance att

★ 289 · Rust
scasella/claude-flightdeck

LIVE DASHBOARD FOR CLAUDE CODE

claude-flightdeck adds an observation panel to terminal for Claude Code: context and cost, advisor timeline, permission checks, subagent cards and swimlanes. 233 stars on

★ 287 · TypeScript
Keesan12/martin-loop

MARTIN LOOP: AUTONOMOUS CODE AGENTS

Launch AI agents to write code without constant supervision. Martin Loop keeps tasks within strict boundaries, checks them and provides accountability from start to finis

★ 286 · TypeScript
graphsignal/graphsignal

PROFILER FOR AI AGENTS AND LLM

Graphsignal Profiler is a tool for debugging and monitoring inference. It helps find performance bottlenecks in deep neural networks and AI agents. Perfect for working wi

★ 276 · Python
future-agi/traceAI

TRACEAI - OPEN SOURCE AI TRACING

traceAI is an open-source framework for tracing AI applications on OpenTelemetry. Easily track model calls and metrics in real time.

★ 266 · Python
alibaba/loongsuite-pilot

LOCAL TELEMETRY AI PILOT

loongsuite-pilot collects telemetry from AI coders in local mode, unifying OpenTelemetry events from Claude Code, Codex, Cursor and agents. It tracks token usage, cost, t

★ 253 · TypeScript
initMAX/zabbix-mcp-server

ZABBIX MCP SERVER FOR AI

MCP server for the full Zabbix API: 237 tools, multi‑server, OAuth 2.1 + bearer, PDF reports, systemd‑ready. Works with ChatGPT, Claude, VS Code, Codex, JetBrains and any

★ 251 · Python
VictoriaMetrics/mcp-victoriametrics

MCP VICTORIAMETRICS: AI SERVER

The server implements the Model Context Protocol (MCP) for VictoriaMetrics, providing fast access to metrics and context for AI agents.

★ 245 · Go
NVIDIA/NeMo-Relay

RUST RUNTIME FOR AI AGENTS

NeMo-Relay is a multi-language runtime for AI agents in Rust. Manages execution scope, lifecycle events, and middleware for tool and LLM calls. 201 stars on GitHub.

★ 245 · Rust
agynio/platform

AI AGENTS IN KUBERNETES

Agyn — an open-source runtime that moves AI agents into company infrastructure with corporate controls.

★ 243 · TypeScript
RailtownAI/railtracks

RAILTRACKS FRAMEWORK FOR AI AGENTS

Railtracks is a Python framework for building resilient agentic systems. It simplifies orchestration of AI agents, provides fault tolerance and observability tools. It su

★ 235 · Python
traceloop/hub

HUB: RUST LLM GATEWAY

High-scale LLM gateway in Rust with built-in observability via OpenTelemetry. Easily scalable and production-ready.

★ 233 · Rust
LeoAlecksey/opsdeck

DEVOPS COCKPIT IN ONE WINDOW

opsdeck — free open-source tool for DevOps. Combines terminal with local AI, Kubernetes, SSH, databases, IDE with Git, alerts, notes and KeePass. Runs on Linux, Windows a

★ 222 · TypeScript
api7/aisix

OPEN SOURCE AI GATEWAY IN RUST

aisix — a single OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock. Supports routing, guardrails, caching, rate limits, and observability. 201 stars on GitHub.

★ 220 · Rust
rajudandigam/agent-inspect

AGENT-INSPECT: UNCOVER AGENT LOGIC

Visualize TypeScript AI agent execution: LLM calls, tools, logs, and errors in a tree.

★ 212 · TypeScript
RelayPlane/proxy

LOCAL LLM PROXY WITH COST CONTROL

Local LLM proxy measures the cost of each agent run and stops those that exceed the budget. Free, MIT‑licensed, written in TypeScript and already has 201 stars on GitHub.

★ 212 · TypeScript
glincker/levelrail

SELF-HOSTED DEPLOY WITHOUT KUBERNETES

levelrail is a self-hosted alternative to Vercel and Coolify. Deploy via git push, auto-HTTPS, logs, and rollbacks. No Kubernetes, just Docker and Go.

★ 210 · Go
Idun-Group/idun-agent-platform

IDUN AGENT PLATFORM OPENSOURCE

Open-source runtime idun-agent-platform turns any LangGraph or Google ADK agent into a production‑ready FastAPI service. It includes AG‑UI CopilotKit API, chat UI, 15+ gu

★ 205 · Python
secureagentics/Adrian

ADRIAN: AI AGENT SECURITY

Adrian monitors and blocks dangerous AI agent actions in real time, preventing malicious tool calls and prompt injections.

★ 203 · Python
rootflo/wavefront

WAVEFRONT AI MIDDLEWARE REVOLUTION

Wavefront — enterprise AI middleware, an alternative to UnifyApps, n8n, and Lyzr in Python. Flexible orchestration and quick start for AI solutions.

★ 203 · Python
ongridio/ongrid

ONGRID: INFRASTRUCTURE AGENT

Ongrid – an AI agent that analyzes infrastructure, finds the root cause, and fixes it directly from Slack, Telegram, Lark, or DingTalk.

★ 201 · Go
superloglabs/superlog

SuperLog: observability and debugging

SuperLog is an open-source TypeScript observability tool that automatically detects and fixes errors in code. It integrates with CI/CD and provides real-time application

★ 198 · TypeScript
FankChen/tracecrate

LOCAL-FIRST AI TRACE WORKBENCH

tracecrate — a local tool for inspecting AI agent traces. Supports Claude Code, Codex, and OTLP logs, lets you compare runs, and exports privacy-conscious reports with no

★ 195 · TypeScript
sksarvesh007/antiglaude

Claude Code Gateway Bridge

Connects Claude Code CLI to Google Gemini models via Anthropic Messages API with observability.

★ 170 · Python
replit/datacat

Self-Hosted Observability Platform

Self-hosted observability stack for metrics, logs, traces, dashboards, and alerts. Stores data in PostgreSQL or ClickHouse, accepts OpenTelemetry.

★ 170 · TypeScript
labtether/labtether

LABTETHER: SMART AI AGENT FOR HOMELAB

LabTether is a Go application that combines an AI agent with a Docker environment for automated deployment and management of homelab infrastructure. It uses the MCP proto

★ 126 · Go

New projects on this topic in Telegram

Telegram →
Observability — page 2 | REDDYX AI