DEV Community

Fenju Fu profile picture

Fenju Fu

404 bio not found

Joined Joined on 
49 Agents, One Crash: Why Workflow Checkpoints Are the Real Bottleneck

49 Agents, One Crash: Why Workflow Checkpoints Are the Real Bottleneck

Comments
3 min read
Why Your AI Agent Needs Engineered Perception — Not Just API Calls

Why Your AI Agent Needs Engineered Perception — Not Just API Calls

Comments
3 min read
Your AI Agent Needs Hands, Not Just a Brain — What GitHub Trending Tells Us

Your AI Agent Needs Hands, Not Just a Brain — What GitHub Trending Tells Us

Comments
2 min read
Why Long-Running Agent Workflows Need Checkpoint Recovery — Not Just Memory

Why Long-Running Agent Workflows Need Checkpoint Recovery — Not Just Memory

Comments
3 min read
Why AI Agents Need Engineering-Grade Multimodal Skills — Not Just Better Prompts

Why AI Agents Need Engineering-Grade Multimodal Skills — Not Just Better Prompts

Comments
2 min read
Why AI Agents Need RPA to Achieve Unattended Automation

Why AI Agents Need RPA to Achieve Unattended Automation

Comments
2 min read
Why Multi-Agent Collaboration Needs an Orchestration Layer, Not Just Shared Workspace

Why Multi-Agent Collaboration Needs an Orchestration Layer, Not Just Shared Workspace

Comments 1
2 min read
Why AI Agent Skills Need a Registry, Not Just a Scanner

Why AI Agent Skills Need a Registry, Not Just a Scanner

Comments
3 min read
Why AI Agents Need Hands: The RPA + Agent Combo for Real Automation

Why AI Agents Need Hands: The RPA + Agent Combo for Real Automation

Comments
2 min read
Stop Configuring Agent Frameworks — Start Using AI Assistants Today

Stop Configuring Agent Frameworks — Start Using AI Assistants Today

Comments
2 min read
Why Long-Running Agent Workflows Need Checkpoint Recovery — Lessons from Today's GitHub Trending

Why Long-Running Agent Workflows Need Checkpoint Recovery — Lessons from Today's GitHub Trending

1
Comments
2 min read
Why Your AI Agent Sucks at Multimodal Tasks (And How to Fix It)

Why Your AI Agent Sucks at Multimodal Tasks (And How to Fix It)

Comments
2 min read
When Agents Start Doing Real Work, You Need an Execution Layer

When Agents Start Doing Real Work, You Need an Execution Layer

Comments
2 min read
A Fleet Without a Conductor Is Just a Parking Lot — Why Multi-Agent Orchestration Is the Missing Layer

A Fleet Without a Conductor Is Just a Parking Lot — Why Multi-Agent Orchestration Is the Missing Layer

Comments
3 min read
SkillHub v0.2.23, Run Locally: A New Avatar, the Same Package Version

SkillHub v0.2.23, Run Locally: A New Avatar, the Same Package Version

Comments
3 min read
When Agents Become a Fleet, You Need a Skill Registry — Not Just Memory

When Agents Become a Fleet, You Need a Skill Registry — Not Just Memory

Comments
2 min read
Agents Are Moving from Chat to Desktop Automation — Here's What GitHub Trending Tells Us

Agents Are Moving from Chat to Desktop Automation — Here's What GitHub Trending Tells Us

Comments
2 min read
AI Assistants Are Becoming Multi-Platform Workstations — Here's How to Get Started

AI Assistants Are Becoming Multi-Platform Workstations — Here's How to Get Started

Comments
2 min read
Why Long-Running Agent Workflows Keep Breaking (And How to Fix It)

Why Long-Running Agent Workflows Keep Breaking (And How to Fix It)

Comments 1
3 min read
Two roots, one valid size: a local Spark-X2.5-1.7B and SymPy demonstration

Two roots, one valid size: a local Spark-X2.5-1.7B and SymPy demonstration

Comments
4 min read
From Open-Source Multimodal Demos to Enterprise-Grade Agent Skills — What Today's GitHub Trending Tells Us

From Open-Source Multimodal Demos to Enterprise-Grade Agent Skills — What Today's GitHub Trending Tells Us

Comments
3 min read
When Agents Take Over Operational Interfaces: From Reverse Engineering to Enterprise RPA

When Agents Take Over Operational Interfaces: From Reverse Engineering to Enterprise RPA

Comments
3 min read
Checking an empty-input defect with Spark-X2.5 and OpenCodeReview locally

Checking an empty-input defect with Spark-X2.5 and OpenCodeReview locally

Comments
3 min read
Agent Chains Are Hot — But Who Orchestrates the Multi-Agent Workflows?

Agent Chains Are Hot — But Who Orchestrates the Multi-Agent Workflows?

Comments
2 min read
A changed runbook, a fresh local Spark-X2.5 answer

A changed runbook, a fresh local Spark-X2.5 answer

Comments
4 min read
Unified Entry Is Step One — Governance Is Step Two: What Today's GitHub Trending Reveals About AI Agent Toolchains

Unified Entry Is Step One — Governance Is Step Two: What Today's GitHub Trending Reveals About AI Agent Toolchains

Comments
3 min read
Model calls first, model-off cache replay second: Spark-X2.5 tests SkillHub with e2e

Model calls first, model-off cache replay second: Spark-X2.5 tests SkillHub with e2e

Comments
4 min read
From Suggestions to Actions: Why Agent + RPA Is the Next Leap After GitHub's Hottest Repos

From Suggestions to Actions: Why Agent + RPA Is the Next Leap After GitHub's Hottest Repos

Comments
3 min read
From "Here's Some Code" to "I'll Do It For You": The Shift in AI Developer Tools

From "Here's Some Code" to "I'll Do It For You": The Shift in AI Developer Tools

Comments
2 min read
When Agent Chains Run for Hours: Why Checkpointing Is the Real Challenge

When Agent Chains Run for Hours: Why Checkpointing Is the Real Challenge

Comments 1
3 min read
When Agents Need Real Skills: Why Multimodal Capabilities Are the Next Bottleneck

When Agents Need Real Skills: Why Multimodal Capabilities Are the Next Bottleneck

Comments
2 min read
When Agents Do the Grunt Work: The Execution Layer They Need

When Agents Do the Grunt Work: The Execution Layer They Need

Comments
3 min read
When Agents Team Up: The Orchestration Layer Multi-Agent Systems Need

When Agents Team Up: The Orchestration Layer Multi-Agent Systems Need

Comments
3 min read
700 Skills, 0 Governance: The Missing Layer in Agent Skill Stacks

700 Skills, 0 Governance: The Missing Layer in Agent Skill Stacks

Comments 1
3 min read
Agents Can Read the Internet Now — But Who Fills the Forms?

Agents Can Read the Internet Now — But Who Fills the Forms?

Comments
2 min read
Agents Got Personalities and Eyes — But How Do You Actually Set Up Your Own AI Assistant?

Agents Got Personalities and Eyes — But How Do You Actually Set Up Your Own AI Assistant?

Comments
2 min read
Persistent Teams Are Great — But What Happens When a 50-Step Workflow Breaks at Step 37?

Persistent Teams Are Great — But What Happens When a 50-Step Workflow Breaks at Step 37?

Comments
3 min read
Agents Can Render Videos Now — But Can They Read Your Documents?

Agents Can Render Videos Now — But Can They Read Your Documents?

Comments
2 min read
Agents Have Safe Runtimes and Multi-Engine Orchestration — But Who Operates the Desktop?

Agents Have Safe Runtimes and Multi-Engine Orchestration — But Who Operates the Desktop?

Comments
2 min read
Multimodal Capabilities Are Going Local — But Agents Still Need Plug-and-Play Skill Packages

Multimodal Capabilities Are Going Local — But Agents Still Need Plug-and-Play Skill Packages

Comments
2 min read
Agents Can Work Inside Documents Now — But Who Handles the Cross-App Repetitive Tasks?

Agents Can Work Inside Documents Now — But Who Handles the Cross-App Repetitive Tasks?

1
Comments
3 min read
SkillHub v0.2.21, Run for Real: Suite Bundles, Device Flow Login and Pi

SkillHub v0.2.21, Run for Real: Suite Bundles, Device Flow Login and Pi

Comments 1
3 min read
Multiple Agents Are Hot on GitHub Trending — But Who Orchestrates the Task Breakdown?

Multiple Agents Are Hot on GitHub Trending — But Who Orchestrates the Task Breakdown?

Comments
2 min read
Paperclip Manages Agents, OpenBao Manages Secrets — But Who Manages Agent Skills?

Paperclip Manages Agents, OpenBao Manages Secrets — But Who Manages Agent Skills?

Comments
3 min read
Agent Management Is Solved. But Who's Actually Doing the Clicking?

Agent Management Is Solved. But Who's Actually Doing the Clicking?

Comments
2 min read
Agent Runtimes Are Everywhere — But Can You Actually Set One Up?

Agent Runtimes Are Everywhere — But Can You Actually Set One Up?

Comments
2 min read
Google's Ax and Anthropic's Financial Services Are Trending — But Who Solves Long-Running Workflow Resilience?

Google's Ax and Anthropic's Financial Services Are Trending — But Who Solves Long-Running Workflow Resilience?

Comments
2 min read
Engineering Multimodal Agents: Why iFly-Skills Goes Beyond API Wrappers

Engineering Multimodal Agents: Why iFly-Skills Goes Beyond API Wrappers

Comments
2 min read
Computer-Use is solved. Unattended workflow execution is not.

Computer-Use is solved. Unattended workflow execution is not.

Comments
2 min read
Why Multi-Agent Orchestration Needs a Workflow-First Approach

Why Multi-Agent Orchestration Needs a Workflow-First Approach

Comments
2 min read
Skills Are the New Packages: Why Agent Skills Need a Registry, Not Just a Collection

Skills Are the New Packages: Why Agent Skills Need a Registry, Not Just a Collection

Comments
2 min read
Deterministic Execution + Agent Intelligence: The Missing Pattern in Real-World Automation

Deterministic Execution + Agent Intelligence: The Missing Pattern in Real-World Automation

Comments
2 min read
Beyond API Wrappers: Why Multimodal Skills Need Engineering-Grade Packaging

Beyond API Wrappers: Why Multimodal Skills Need Engineering-Grade Packaging

Comments
2 min read
Beyond Code Review: Why Cross-System Desktop Automation Is the Next RPA Frontier

Beyond Code Review: Why Cross-System Desktop Automation Is the Next RPA Frontier

Comments
3 min read
Multi-Agent Collaboration Is Going Vertical — Here's Why Enterprises Need a Cross-Domain Orchestrator

Multi-Agent Collaboration Is Going Vertical — Here's Why Enterprises Need a Cross-Domain Orchestrator

Comments
2 min read
From Leaked Prompts to Enterprise Skill Governance: What Today's GitHub Trending Tells Us

From Leaked Prompts to Enterprise Skill Governance: What Today's GitHub Trending Tells Us

Comments
2 min read
Agents Have APIs. Your Legacy Apps Don't. Why Agent + RPA is the Real Automation.

Agents Have APIs. Your Legacy Apps Don't. Why Agent + RPA is the Real Automation.

Comments
2 min read
Everyone Ships Agent Tools. Nobody Ships the Onboarding.

Everyone Ships Agent Tools. Nobody Ships the Onboarding.

Comments 1
2 min read
Everyone Talks About Running Agents. Nobody Talks About Resuming Them.

Everyone Talks About Running Agents. Nobody Talks About Resuming Them.

Comments
2 min read
OpenAI Built a Skills Catalog. iFLYTEK Built the Skills Themselves.

OpenAI Built a Skills Catalog. iFLYTEK Built the Skills Themselves.

Comments
2 min read
loading...