Havuz

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

Self-hosted observability platform — error tracking, performance tracing, metrics, uptime monitoring, and profiling.

eBPF tracer and analyzer for io_uring. Reconstructs per-request latency, io-wq punts, and batching from kernel tracepoints, then names the p

Lightweight open-core SIEM in Rust — S3-compatible for logs, Postgres for state.

Specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP, and A2A.

Request-level runtime coverage attribution for Spring MVC/WebFlux applications.

Drop-in Prometheus / Loki / Tempo HTTP gateway for ClickHouse. Translate PromQL, LogQL, and TraceQL into optimized CH SQL — keep Grafana, sw

The AI Runtime for Kubernetes

Fast large-file log & JSONL viewer for Windows — 1 GiB indexed in 92 ms, regex search in 115 ms. 丹青日志 · Windows 大文件日志/JSONL 查看分析器 (Rust)

Watch what your ai coding agents(claude, codex and opencode) are doing on your terminal and browser.

A Complete faster runtime for coding agents. Optimize the journey, not the hop. Make coding agents 25% faster and 30% cheaper on average whi

OpenTelemetry tracing for DeepSeek Harness (dsh): turns each agent turn into a GenAI span tree — steps, LLM calls with TTFT, tool executions

Personal usage analytics for Pi coding agent. Temporal-aware insights, context-aware suggestions, model efficiency analysis.

First LLM Studio: local-first LLM workbench for Apple Silicon + MLX. 本地优先 LLM 工作台，覆盖 Agent、对比、微调、评测与运行时遥测。

Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the

Cross-platform .NET performance engineering skill for coding agents, covering CPU, memory, GC, benchmarking, concurrency, startup, native pr

Open-source platform for always-on AI agents: a software factory for Claude Code that takes your projects from tickets to merged pull reques

Tree-shakable health endpoints for JS servers. Zero-dependency core, adapters for Hono, Elysia, Express, Next.js and TanStack Start, probes

Auditable AI operations agent for inventory exceptions, equipment alerts, and human-approved workflows.

Axon reads the logs your AI coding-agent harnesses already write — Claude Code, Codex, OpenCode — and shows which harness, project, agent, a

eBPF Runtime Reporter and Profiler

One command turns every agent session already on your disk into a graph: subagents, tool calls, retries, the moments you said no. Ask your a

Semantic cache strategy bench: replay recorded request traces through candidate caching policies and measure which one actually pays off.

Apache Airflow-compatible workflow orchestrator, re-engineered in Go: the drop-in Airflow UI and REST API on a single-binary control plane (

The Forensic Journal for your Infrastructure. Written in Go for maximum impact with minimal footprint.

Tired of scrolling through hundreds of near-identical posts across every social network just to find the few that actually matter. Instead o

Turn FastAPI BackgroundTasks into a production-grade task system. Retries, Resiliency, control, and visibility without workers or brokers.

Agent reliability rulebook: the threat model and rationale behind each Agent Reliability Analyzer rule

Tends your codebase while you're away. An always-on AI engineer that reviews your logs, implements your tickets and keeps your pull requests

A harness for hosted Grok Bot crews. Its core rule: it is not allowed to guess.

eBPF ransomware detection & response agent for Linux — single static binary, no kernel modules, behavioural scoring, process pause/kill

🇺🇦🇵🇱 A static analysis tool for OpenTelemetry Collector configurations. Built on OPA/Rego, it validates your pipelines, receivers, processor

An open-source Python SDK for analyzing, evaluating, and curating agent traces stored in BigQuery. Built on top of the BigQuery Agent Analyt

Uptime monitoring, public status pages and on-call in one. Checks as often as every 30 seconds from multiple regions, 8 check types includin

Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.

Community-maintained observability for self-hosted Supabase: logs, metrics, and traces.

CONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledg

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

Local-first observability dashboard to monitor, compare and analyze Codex, Claude Code and GitHub Copilot CLI sessions

Lightweight, dependency-free logging and analytics for LLM API calls — track tokens, cost, and latency to a plain JSONL file.

Circuit breaker for production PostgreSQL. Native extension that can ALLOW, WARN, or BLOCK dangerous SQL based on live database state. Apach

Agent PI - Agent Development Environment (ADE)

Dashboard for monitoring and exploring Engram memory: sessions, observations, prompts, and stats

The runtime reliability layer for AI agents.

Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin

See which notes your coding agent actually reads — a live radar for Claude Code and your Obsidian vault.

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done cla

The agentic debugger for Claude Code, Codex CLI and Gemini CLI: a token usage, cost and context-window tracker that shows what the tokens AR

Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory,

The One Dashboard every Voice Agent needs