korchasa awesome lists digest (11.06.2026)

This update across korchasa’s awesome lists is substantial: 183 new entries across three areas. Most of the volume comes from AIOps, with 167 additions; AI Agents adds 13 entries, and MCP adds 3. The selection below is not reduced to links: each project is shown with its repository, star count, and full available description from the collected delta.

AI Agents

The AI Agents section spans orchestration, long-term memory, execution isolation, development frameworks, and tools that let agents reach external content sources.

• ruvnet/ruflo — 58,416 stars. Ruflo is a leading agent orchestration platform for Claude, enabling the deployment of intelligent multi-agent swarms, coordination of autonomous workflows, and building conversational AI systems.
• siyuan-note/siyuan — 44,321 stars. SiYuan is a privacy-first, self-hosted, open-source personal knowledge management system with block-level referencing and Markdown WYSIWYG editing capabilities.
• Panniantong/Agent-Reach — 23,302 stars. Agent-Reach allows AI agents to access web content from major social media and video platforms through a CLI, without API fees, enhancing their perceptual capabilities.
• NVIDIA/NemoClaw — 21,047 stars. NVIDIA NemoClaw is an open-source reference stack enabling the secure and sandboxed operation of AI agents like OpenClaw and Hermes within NVIDIA OpenShell environments, offering managed inference …
• chopratejas/headroom — 17,189 stars. Headroom is a context compression layer for AI agents, reducing token usage by 60-95% with maintained accuracy across various workloads, offered as a library, proxy, or MCP server.
• opensandbox-group/OpenSandbox — 11,389 stars. OpenSandbox is a general-purpose, secure, and extensible sandbox runtime for AI applications, offering multi-language SDKs and robust isolation for agent execution.
• aden-hive/hive — 10,505 stars. Hive is an outcome-driven agent development framework designed for evolving agents with AI evaluation, human-in-the-loop, and self-improvement capabilities.
• j3ssie/osmedeus — 6,408 stars. Osmedeus is a powerful and modern orchestration engine designed for reconnaissance and penetration testing workflows, written in Go.
• strands-agents/harness-sdk — 6,056 stars. Strands Agents is a versatile SDK for building and operating AI agents with model-driven approaches, supporting various LLMs, multi-agent systems, and production deployments.
• TencentCloud/TencentDB-Agent-Memory — 5,104 stars. TencentDB Agent Memory provides a local, 4-tier progressive pipeline for AI agent long-term memory, enhancing performance and reducing token usage without external API dependencies.
• dromara/liteflow — 3,757 stars. LiteFlow is a lightweight, modern rule engine framework that orchestrates complex business components and integrates AI Agents as first-class citizens.
• agentscope-ai/agentscope-java — 3,611 stars. AgentScope Java is an agent-oriented programming framework for building production-ready LLM-powered applications, offering features like ReAct reasoning, tool calling, memory management, and multi…
• kepano/obsidian-skills — 0 stars. Obsidian Skills provides a collection of agent skills enabling AI agents to interact with Obsidian vaults, facilitating content creation and editing of Markdown, Bases, and JSON Canvas files, as we…

MCP

The MCP additions point to a practical layer around agents: context compression, portable local memory, and Microsoft Teams integration through a protocol server.

• chopratejas/headroom — 17,189 stars. Headroom is a context compression layer for AI agents, reducing LLM token usage by 60-95% while preserving accuracy, offered as a library, proxy, or MCP server.
• EverMind-AI/EverOS — 7,096 stars. EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.
• InditexTech/mcp-teams-server — 354 stars. MCP Teams Server is an MCP protocol server implementation enabling Microsoft Teams integration with capabilities to read, create, reply to messages, and mention members within Teams channels.

AIOps

AIOps is the largest part of this update. The selected entries cover agent memory, safety evaluation, LLMOps observability, RAG, DevOps benchmarks, inference, vector search, and audits for local LLM proxies.

• ClaudioDrews/memory-os — 1,016 stars. Memory OS is a 7-layer memory operating system for Hermes Agent, providing persistent memory, structured facts, context injection, and a self-curating wiki, running locally with any LLM provider.
• wuyoscar/Internal-Safety-Collapse — 777 stars. ISC-Bench is a research project and benchmark for evaluating the safety collapse of frontier LLMs and AI agents, demonstrating how they can be made to produce harmful outputs under specific task co…
• stoyan-stoyanov/llmflows — 706 stars. LLMFlows is a Python framework for building, operating, and observing LLM-powered applications, emphasizing explicit workflows, transparency, and easy debugging.
• bosun-ai/swiftide — 704 stars. Swiftide is a Rust library for building fast, streaming LLM applications with support for RAG pipelines, agentic workflows, and integrations with popular LLMs and storage.
• youssofal/MTPLX — 695 stars. MTPLX is an Apple Silicon-native inference engine that leverages Multi-Token Prediction (MTP) for speculative decoding, significantly boosting LLM inference speeds with mathematical correctness.
• ServerlessLLM/ServerlessLLM — 685 stars. ServerlessLLM is a system for deploying multiple AI models on shared GPUs, offering ultra-fast checkpoint loading, GPU multiplexing, and unified inference with LoRA fine-tuning.
• kossisoroyce/timber — 683 stars. Timber is an AOT compiler that converts classical ML models (XGBoost, LightGBM, scikit-learn, CatBoost, ONNX) into native C99 code for ultra-fast, portable, and low-footprint inference serving.
• elastic/mcp-server-elasticsearch — 669 stars. The Elasticsearch Model Context Protocol (MCP) Server enables AI agents to interact with Elasticsearch data using natural language, query indices, and retrieve information.
• Bessouat40/RAGLight — 664 stars. RAGLight is a modular Python framework for building Retrieval-Augmented Generation (RAG) applications, supporting various LLMs, embeddings, vector stores, and agentic workflows.
• AltimateAI/altimate-code — 661 stars. Altimate-code is an open-source, AI-powered agentic data engineering harness for dbt, SQL, and cloud warehouses, providing deterministic SQL analysis, lineage, and FinOps.
• codefuse-ai/codefuse-devops-eval — 655 stars. DevOps-Eval is an industrial-first evaluation benchmark specifically designed for large language models (LLMs) in the DevOps and AIOps domains.
• toby-bridges/api-relay-audit — 655 stars. API Relay Audit is a security tool for local AI API relays and LLM proxies, detecting prompt injection, model substitution, tool-call rewriting, Web3 risks, and other relay tampering.
• jina-ai/vectordb — 649 stars. Vectordb by Jina AI is a Pythonic vector database for efficient storage, retrieval, and serving of vectorized data, with CRUD operations and scalability options including sharding and replication.
• santifer/cv-santiago — 636 stars. An interactive portfolio featuring an AI chatbot with agentic RAG, full LLMOps observability, automated evaluations, and prompt injection defense.
• BUAADreamer/EasyRAG — 632 stars. EasyRAG is an efficient Retrieval-Augmented Generation (RAG) framework specifically designed for automated network operations, aiming for accurate, simple, and efficient inference.

The overall direction is clear: agentic systems increasingly need an operational substrate, not just a model and a prompt. Memory, sandboxes, observability, protocol integrations, safety controls, and inference-cost optimization are becoming part of the default stack.