LLM 可观测

🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.

The Security Toolkit for LLM Interactions

AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

Network inspector for your backend

Ultra-low-latency asynchronous C++17 logging and metrics library for performance-critical applications

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

🕵️‍♂️ TUI for sniffing network traffic using eBPF on Linux

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

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.

The CNCF sandbox for observability visualisation. Supports Prometheus, Tempo, Loki, Pyroscope, and more!

Bionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

The fastest unified streaming SQL Engine in a single C++ binary. ⚡ Millisecond latency. 100+ GB/s throughput. Continuously compute stateful context from streams, logs, metrics, events, and CDC.

🏕️ Reproducible development environment for humans and agents

Local-first AI token usage & cost tracker for 31 coding tools incl. Claude Code, Codex, Cursor, Gemini & DeepSeek Harness—with native apps. Never reads prompts.

eBPF-based autoinstrumentation of web applications and network metrics

MCP Router — development, support and security updates ended 2026-09-18. Historical source and final release for existing users.

Monoscope lets you ingest and explore your logs, traces and metrics. We store these in S3 compatible buckets. Query in natural language via LLMs.

An extensible Java library for HTTP request and response logging

🐳 Elastic Stack (ELK) v9+ on Docker with Compose. Pre-configured out of the box to enable Logging, Metrics, APM, Alerting, ML, and SIEM features. Up with a Single Command.

Easy token price estimates for 400+ LLMs. TokenOps.

Digging through logs is not observability. It's hope — wide events, structured errors, TypeScript-first, every runtime.

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

0x.Tools: X-Ray vision for Linux systems

Tencent Server Web

100x Efficient Log Management than Splunk :rocket: Reduce your observability cost by 90%

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

OpenTelemetry Instrumentation for AI Observability

Dynamiq is an orchestration framework for agentic AI and LLM applications

Large Language Models (LLMs) tutorials & sample scripts, ft. langchain, openai, llamaindex, gpt, chromadb & pinecone

🧠 Motorhead is a memory and information retrieval server for LLMs.

Interactive CV with AI chat integration. Built with React 19, TypeScript, Claude API. Chat with my AI avatar about my experience.

Read-only Windows diagnostics: the Event Log in plain language, blue screens explained. Offline and open source.

Fast, streaming indexing, query, and agentic LLM applications in Rust

This sample has the full End2End process of creating RAG application with Prompty and Azure AI Foundry. It includes GPT-4 LLM application code, evaluations, deployment automation with AZD CLI, GitHub actions for evaluation and deployment and intent mapping for multiple LLM task mapping.

What if OpenAI Deep Research and Dify were one platform? OpenAgent — harness architecture for rapidly building vertical AI agents, with deep reasoning loops, visual workflows, RAG, and A2A delegation.

LLM全栈优质资源汇总

Deprecated historical repo. Superlinked now develops SIE, a self-hosted inference engine for embeddings, reranking, OCR, extraction, and document processing.

Data-Driven Evaluation for LLM-Powered Applications

A fast and minimal framework for building agentic systems

A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG

Keras based framework for neuro-symbolic LM systems

Govern & Secure your AI

Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.

Sister project to OpenLLMetry, but in Typescript. Open-source observability for your LLM application, based on OpenTelemetry

Framework to bring LLM applications to production