Knowledge Share
Technical articles, tutorials, and insights
Enterprise Knowledge Base (00): Build the Evaluation Dataset Before Writing a Single Line of Code
Comparing six open-source RAG frameworks means nothing if each is tested on different documents with different questions. This is the zero article in the series — building a unified test set first, so every subsequent benchmark runs on the same 89 questions. The article covers the decision path from 'just use BEIR' to 'synthesize domain-specific questions with an LLM,' plus the complete code for generating the evaluation set.
Enterprise Knowledge Base (01): Why RAG Is Just the Starting Point
The real challenge in enterprise knowledge bases isn't technology selection — it's bad data quality, fragmented knowledge, mixed modalities, and knowledge decay. These are problems RAG can't solve. This article maps the complete technology landscape: from classic vector RAG to graph RAG, hypergraph RAG, and Agent-native knowledge systems, with what each generation actually fixes.
Open Source Project #174: AirLLM — Run 70B Models on 4GB GPU, 405B on 8GB, and 2.8-Trillion-Parameter Kimi K3 on 3.7GB
AirLLM breaks the VRAM wall with layer-wise inference: splits transformer models into per-layer shards on disk, loads one layer at a time during inference, releases memory immediately after. No quantization, distillation, or pruning required. Runs 70B to 2.8T parameter models on consumer GPUs. Supports Llama 4, Qwen3, DeepSeek-V3/R1, Kimi K3. Optional 4bit/8bit block-wise compression for ~3x speedup. 25.8k Stars, Apache 2.0, pip install airllm.
Open Source Project #175: Buzz — Block Rebuilds Team Collaboration on Nostr, Where AI Agents Hold Their Own Cryptographic Identity
Block's open-source team workspace launched July 21, 2026, where humans and AI agents collaborate as equal members in shared channels. Built on Nostr: every agent holds its own cryptographic keypair — identity and history are portable across any Nostr-compatible system. Rust backend, Tauri desktop, supports Claude Code, Codex, Goose. YAML workflow engine, buzz-cli (JSON in/out, machine-first design for LLM tool calls), NIP-34 Git integration. 21.3k Stars, Apache 2.0, self-hostable.
Open Source Project #176: Better Harness — A Five-Dimension Workflow Evaluator for AI Coding Agents That Reviews the Loop, Not the Diff
QoderAI's open-source tool that converts project and session evidence into prioritized workflow improvements for AI coding agents. Evaluates the workflow around the agent — not final code quality — across five dimensions: task understanding, controlled execution, change validation, reliable delivery, and learning capture. Three independent evidence agents analyze in parallel; a lead agent synthesizes findings into HTML/Markdown/JSON reports. Supports Claude Code, Codex, GitHub Copilot, Cursor, Qwen Code. 1.5k Stars, MIT license.
Open Source Project #177: Apache Airflow — Workflow Orchestration in Python, the Standard Tool for Data Engineers
Apache Airflow is a platform for programmatically authoring, scheduling, and monitoring workflows. Core concept: DAGs (Directed Acyclic Graphs) — define task dependencies in Python code, trigger by schedule or data events, monitor every step in the Web UI. Covers four major scenarios: ETL/ELT pipelines, ML training pipelines, scheduled reporting, and infrastructure automation. 46.4k Stars, Apache 2.0, version 3.3.0, 600+ built-in Operators and Providers.
Open Source Project #178: OptMem — 426-Token Prompt, Persistent Memory Across Sessions for AI Agents
VictorTaelin's persistent memory solution for AI agents. Single Python script, zero dependencies, append-only flat file plus binary tree summarization. Agents run memo wake at session start to load memories, memo note to record worth-keeping facts during work. No vector database required — plain text, fully inspectable. 1M memories wake in 0.03 seconds. The entire integration is one 426-token prompt block pasted into AGENTS.md or CLAUDE.md. 1.1k Stars.
Open Source Project #179: Node-RED — Visual Programming for Wiring Hardware, APIs, and Online Services Together
OpenJS Foundation's low-code, event-driven programming platform. Drag nodes onto a browser canvas, connect them with wires, and you have a complete data flow — from sensors to databases, MQTT to HTTP APIs. A de facto standard in industrial IoT with native support for OPC-UA, Modbus, and MQTT. Runs on Raspberry Pi, factory edge gateways, and cloud servers. Node-RED 5 ships Explorer panel, built-in dark theme, and a fully redesigned editor. 23.5k Stars, Apache 2.0.
Open Source Project #180: Omnigent — Databricks' Meta-Harness for Unified Control of Claude Code, Codex, and Cursor
AI coding agent meta-orchestration framework open-sourced by Databricks co-founder Matei Zaharia. Sits above Claude Code, Codex, Cursor and other tools to provide policy governance (token budgets, tool access limits), cloud sandboxing (Modal/E2B/Daytona/Kubernetes), real-time collaboration (session sharing/co-driving/forking), MLflow observability, and YAML-defined multi-agent orchestration. The Kubernetes analogy for AI agents. 8.1k Stars, Apache 2.0, Alpha stage.
Open Source Project #181: Open Code Review — Alibaba's Battle-Tested AI Code Review Tool, 1/9 the Tokens of a General Agent
Alibaba open-sources its internal AI code review tool, battle-tested across tens of thousands of engineers and millions of detected defects before public release. Core: a hybrid architecture pairing deterministic engineering pipelines (file selection, bundling, rule matching) with an LLM agent (dynamic judgment). Same underlying model as Claude Code — higher precision and F1, roughly 1/9 the token usage. Supports review (git diff) and scan (full-file audit) modes, delegation mode for your own agent, and GitHub Actions / GitLab CI / Gerrit integration. 18.1k Stars, Apache 2.0.
Open Source Project #182: Graphify — Turn Your Entire Codebase into a Queryable Knowledge Graph for AI Coding Assistants
YC-backed open-source tool that uses tree-sitter AST to parse code locally and an optional LLM backend to process docs, PDFs, images, and video — building everything into one queryable knowledge graph. AI assistants traverse the graph instead of grepping. Every edge is tagged EXTRACTED/INFERRED/AMBIGUOUS. Incremental updates patch only changed files in ~0.8 seconds. Supports Claude Code, Cursor, Codex, and 15+ other AI tools via MCP. Optional Neo4j/FalkorDB backends. 101k Stars, Apache-2.0 + MIT.
Open Source Project #183: Ontology Playground — Microsoft's Zero-Backend Visual Ontology Learning Tool
Microsoft's open-source pure-static web app for learning ontology design and Microsoft Fabric IQ. Visual drag-and-drop ontology designer, RDF/OWL import/export, six industry domain pre-built ontologies, nine structured courses with interactive quizzes, and a one-line embeddable widget. Zero server dependency — runs directly in the browser, deployable to GitHub Pages or Azure Static Web Apps. React 19 + TypeScript + Cytoscape.js. 2.3k Stars, MIT license.