DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Agent Series (13): Agent Security and Defense — Prompt Injection, Tool Abuse, and Data Leakage
wonderlab profile

Agent Series (13): Agent Security and Defense — Prompt Injection, Tool Abuse, and Data Leakage

#ai #agents #security #llm
Comments 1
6 min read
[Gemini][Agent] Google Managed Agents API
evanlin profile

[Gemini][Agent] Google Managed Agents API

#agents #api #gemini #google
9
Comments 1
11 min read
MCP tool naming: 6 patterns ranked by how well they survive a refactor
james_oconnor_dev profile

MCP tool naming: 6 patterns ranked by how well they survive a refactor

#agents #architecture #mcp #softwareengineering
2
Comments 2
7 min read
Shadow CTO — A GitHub Repo Memory Container Powered by Hermes Agent

Hermes Agent Challenge Submission: Build With Hermes Agent
pulkitgovrani profile

Shadow CTO — A GitHub Repo Memory Container Powered by Hermes Agent

#hermesagentchallenge #devchallenge #agents
4
Comments
4 min read
OpenClaw Sandbox vs Approvals vs Tool Policy: Three Different Safety Layers
hex_agent profile
Hex

OpenClaw Sandbox vs Approvals vs Tool Policy: Three Different Safety Layers

#ai #agents #automation #productivity
Comments
7 min read
The Context Window Trap: Why Enterprise AI Agents Break Down at Scale
nolanvale profile

The Context Window Trap: Why Enterprise AI Agents Break Down at Scale

#agents #llm #rag #systemdesign
Comments 1
4 min read
We Now Index All Three Agent Payment Protocols. Here's What the Data Shows.
tufti profile
Tuf Ti

We Now Index All Three Agent Payment Protocols. Here's What the Data Shows.

#ai #web3 #agents #bitcoin
Comments 1
3 min read
I Made Kimi Build Its Own Tiny Coding Team in 2 Days
dmae97 profile
dmae97

I Made Kimi Build Its Own Tiny Coding Team in 2 Days

#ai #opensource #cli #agents
Comments
3 min read
Six ways our four-agent system tried to lie to itself
dutchaiagents profile

Six ways our four-agent system tried to lie to itself

#ai #agents #multiagent #debugging
Comments
6 min read
oh-my-agent: skills now measure and optimize their own utility
gracefullight profile

oh-my-agent: skills now measure and optimize their own utility

#ai #productivity #programming #agents
3
Comments
4 min read
DeepSeek-V4: What a Million-Token Context Actually Changes
o96a profile

DeepSeek-V4: What a Million-Token Context Actually Changes

#agents #ai #architecture #llm
Comments 1
3 min read
Agent Skills Are Just Header Files (And Virtual Memory, And Unix Pipes)
botticelli profile

Agent Skills Are Just Header Files (And Virtual Memory, And Unix Pipes)

#ai #llm #agents #softwareengineering
Comments
5 min read
Logic Drift: The Failure Mode Agents Can't See
monom profile

Logic Drift: The Failure Mode Agents Can't See

#agents #ai #softwareengineering #vibecoding
8
Comments 9
7 min read
From File-Driven to Multi-Agent Collaboration: A Unified Design for the WiseClaw Medical Agent Harness
wisediag profile

From File-Driven to Multi-Agent Collaboration: A Unified Design for the WiseClaw Medical Agent Harness

#agents #ai #architecture #systemdesign
2
Comments
23 min read
Building a bridge to connect AI coding agents with your UI smoothly
davekurian profile

Building a bridge to connect AI coding agents with your UI smoothly

#agents #ai #tooling #ui
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.