DEV Community

# agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
OpenAI Operator scores 43% on hard web tasks. We scored 81%. Here are all 300 runs.
tinyfishie profile

OpenAI Operator scores 43% on hard web tasks. We scored 81%. Here are all 300 runs.

#showdev #agents #ai #automation
1
Comments
4 min read
Browser-action receipts are not logs
eliofbm profile
Eli

Browser-action receipts are not logs

#ai #agents #automation #browser
Comments
5 min read
A plugin for Observability + Budget Guardrails built with Hermes Agent

Hermes Agent Challenge Submission: Build With Hermes Agent
nujovich profile

A plugin for Observability + Budget Guardrails built with Hermes Agent

#hermesagentchallenge #devchallenge #agents
2
Comments 1
4 min read
Nexus

Hermes Agent Challenge Submission: Build With Hermes Agent
redwanshahriarshubho profile

Nexus

#hermesagentchallenge #devchallenge #agents
4
Comments
2 min read
From Blender Demos to Agent Toolchains: Why Terminal Skills Matter
alexshev profile

From Blender Demos to Agent Toolchains: Why Terminal Skills Matter

#agents #ai #automation #cli
Comments
6 min read
Project Mentor AI: Leveraging Hermes Agent for Autonomous Research, Planning, and Architecture Design

Hermes Agent Challenge Submission: Build With Hermes Agent
samarth28 profile

Project Mentor AI: Leveraging Hermes Agent for Autonomous Research, Planning, and Architecture Design

#hermesagentchallenge #devchallenge #agents
1
Comments
3 min read
AI and programming: A double-edged sword
albaraa_ali profile

AI and programming: A double-edged sword

#discuss #ai #productivity #agents
Comments
2 min read
Context engineering is an architecture strategy, not a model swap
thousand_miles_ai profile

Context engineering is an architecture strategy, not a model swap

#discuss #ai #agents #programming
Comments
6 min read
How I Stopped My Support Agent From Having Amnesia
yaswanthgunda profile

How I Stopped My Support Agent From Having Amnesia

#showdev #agents #ai #python
Comments
3 min read
We benchmarked an 84% token reduction. Then we open sourced the protocol.
mz06 profile

We benchmarked an 84% token reduction. Then we open sourced the protocol.

#ai #productivity #agents
Comments
5 min read
Hermes Agent's Brain: How Its Skills & Memory System Actually Works

Hermes Agent Challenge Submission: Write About Hermes Agent
_prshant01 profile

Hermes Agent's Brain: How Its Skills & Memory System Actually Works

#hermesagentchallenge #devchallenge #agents #opensource
3
Comments
6 min read
Why your AI agent keeps hallucinating (and how data testing fixes it)
unna_malai_0a82f75284643d profile

Why your AI agent keeps hallucinating (and how data testing fixes it)

#agents #ai #devops #testing
Comments
4 min read
HealthHermes: A Private AI Health Companion That Remembers Everything and Runs on Your Own Machine

Hermes Agent Challenge Submission: Build With Hermes Agent
bezawada_haritha_dfab7cbf profile

HealthHermes: A Private AI Health Companion That Remembers Everything and Runs on Your Own Machine

#hermesagentchallenge #devchallenge #agents
3
Comments
6 min read
How the itrstats tax assistant works: one query, every layer
kartikeyraj profile

How the itrstats tax assistant works: one query, every layer

#python #llm #agents #rag
Comments
10 min read
One Open Source Project a Day (No. 69): Academic Research Skills - A Full-Pipeline AI Agent Suite for Academic Research
wonderlab profile

One Open Source Project a Day (No. 69): Academic Research Skills - A Full-Pipeline AI Agent Suite for Academic Research

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