Havuz

Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.

Local-first analysis of Claude Code and Codex sessions: token spend, context windows, files touched, and cost.

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into

Self-hosted browser session replay built on S2 with live tailing

Self-hosted Laravel monitoring agent. Drop-in Nightwatch alternative, open-source.

Token Efficiency For AI Agents

Beta · Self-hosted status dashboard for a homelab. Mount the Docker socket and your containers show up on their own; push heartbeats for any

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

Litefuse - Agent Observability and Evaluation Platform

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

ZhuLing — Zero-config AI Agent framework for Java. One YAML to launch Agents on Spring AI + DDD, with MCP tools, full observability and a Re

Evidence-driven production readiness checklist for shipping web applications with confidence

Pi coding agent extensions with code intelligence (LSP + Tree-sitter AST), semantic refactoring, code review, web/Context7 docs, and ask-use

Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — de

Lightweight OpenTelemetry receiver and local dashboard for LLM development — single binary, zero dependencies

Pan by Euraika — a self-hosted AI workspace for Hermes Agent. Chat, skills, extensions, memory, profiles, and runtime controls.

Runtime behavior diffs for pull requests

Tools for AI agents to test, fix and optimise your codebase

Self-hostable incident-investigation agents for Sentry, Datadog, and Slack.

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc

Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custo

Fast, zero-dependency access log analyzer, security threat inspector, and TUI dashboard for Caddy v2

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

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

The AI Runtime for Kubernetes

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

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。

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

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

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

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

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.

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

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

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

The One Dashboard every Voice Agent needs

Langfuse on GreptimeDB. Self-hosted LLM observability.

Cloud native chaos engineering toolkit for Go. Inject faults across HTTP, gRPC, Kafka, Redis, SQL, and MongoDB. YAML defined policies, multi

Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.

Economical human-readable logs and structural (event pattern) retrieval for agentic trajectories

The command center for n8n automation operators: multi-instance management, real-time error tracking, AI-assisted debugging, a Code Lab, and

Introspection dashboard for the pi coding agent — tools, prompts, skills, and the system prompt injected on init.

Zero-overhead eBPF process tracer for Linux malware triage and incident response. Traces syscalls, network, and file events per-process with

Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Met