BLOG

Knowledge Share

Technical articles, tutorials, and insights

Found 386 posts · Page 1/33
Open SourceDeveloper ToolsFree Services

One Open Source Project a Day (No. 217): free-for-dev — The 137k-Star Ultimate Vault of Free Services for Developers

free-for-dev is one of GitHub's highest-starred resource repositories, cataloging 60+ categories and hundreds of SaaS/PaaS/IaaS services with genuine free tiers — from major cloud platforms to CI/CD, databases, AI tools, and auth services. 137k Stars, maintained by 1,600+ contributors, the must-bookmark "freebie guide" every developer needs.

·10 min read
Open SourceHomepageSelf-Hosted

One Open Source Project a Day (No. 218): Homepage — A Sleek Unified Dashboard for All Your Self-Hosted Services

Homepage is a modern, highly customizable self-hosted service dashboard. Configure service groups, bookmarks, and widgets in YAML, with Docker Label auto-discovery, 150+ service API integrations, and 40+ language support. 32.6k Stars, GPL-3.0, built on Next.js with static generation for instant load times.

·9 min read
Open SourceOpenshipSelf-Hosted

One Open Source Project a Day (No. 219): Openship — Vercel-Level Deploy Experience on Your Own Server

Openship is an open-source, self-hostable deployment platform — push code and it automatically builds, deploys, routes, and provisions SSL. Built-in databases, mail server, object storage, and backups. Runs via desktop app, web dashboard, CLI, or MCP endpoint. No vendor lock-in; containers keep running after you delete a project. 12.3k Stars, Apache 2.0.

·9 min read
Open SourceLangflowLLM

One Open Source Project a Day (No. 215): Langflow — Visual Drag-and-Drop AI App Builder

Langflow is a low-code AI application platform built on a visual flow editor. Connect LLMs, vector databases, tools, and Agents by dragging and dropping nodes, building production-ready RAG pipelines and multi-Agent systems without writing backend code.

·11 min read
Open SourceOpenVikingAgent Memory

One Open Source Project a Day (No. 216): OpenViking — A Self-Evolving Context Database for AI Agents

OpenViking is an open-source AI Agent context database from Volcengine, using a virtual filesystem to unify Agent memory, knowledge RAG, and skills. It lets Agents accumulate experience across sessions and self-evolve — 36,000+ Stars with VLDB 2026 paper backing.

·11 min read
DeepSeek HarnessdshAgent Loop

DeepSeek Harness Series (04): Agent Loop — How a Conversation Turn Actually Runs

The user sends a message, the Agent replies and calls three tools — but what's actually happening under the hood? This article fully unpacks the dsh Agent Loop: the Turn/Step structure, how the driver works, what each extension point does, and where you can insert control logic.

·8 min read
DeepSeek HarnessdshSession

DeepSeek Harness Series (05): Sessions and Memory — How Conversation History Survives

What happens when your Agent crashes mid-run? Does history survive a process restart? Can you rewind to an earlier step and try a different path? This article unpacks dsh's Session design: the append-only log, derived history, format versioning, the Fork API, and why the model never sees dirty failed attempts.

·10 min read
DeepSeek HarnessdshSystem Prompt

DeepSeek Harness Series (06): System Prompt Assembly — Engineering Dynamic Prompts

Before every model request, how does dsh stitch together prompt fragments from dozens of plugins into one coherent system prompt? This article unpacks ctx.systemPrompt's registration mechanism, section ordering, dynamic variables, automatic tool schema injection, and how Prompt Caching fits in.

·10 min read
DeepSeek HarnessdshCapability Seam

DeepSeek Harness Series (07): Capability Seams — Swap One Config Line, Swap Everything

Why doesn't dsh just import fs directly? Why can Shell execution be redirected to a remote sandbox with a single config change? This article explains dsh's Capability Seam design: the Service Definition / Provider / Consumer triad, and practical usage of core seams like ctx.fs, ctx.sandbox, ctx.shell, and ctx.llm.

·8 min read
DeepSeek HarnessdshSubagent

DeepSeek Harness Series (08): Multi-Agent Collaboration — Subagents and Agent Teams

One Agent calls another Agent — the result can be plain text or structured JSON. This article covers dsh's multi-Agent mechanisms: launching subagents, continuable subagents, tool filtering, personas, and the experimental Agent Teams.

·10 min read
DeepSeek Harnessdshobservability

DeepSeek Harness Series (09): Observability — How to Know What Your Agent Is Actually Doing

How many tokens did it burn? Which step was the slowest? Where exactly did it fail? This article covers dsh's observability mechanisms: Session event logs, Token metering, the Telemetry Seam (ctx.sessionTelemetry), OpenTelemetry integration, and how to use session/event listeners for real-time debugging.

·10 min read
DeepSeek Harnessdshplugin development

DeepSeek Harness Series (10): Building a Complete dsh Plugin — From Requirements to Production

The series finale. Take everything learned across the previous nine articles — tool registration, prompt sections, event listening, Session observation, permission interception — and combine them into a complete, production-quality plugin. See exactly what the skeleton of a real dsh plugin looks like.

·13 min read