DEV Community

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Why Every Library in the Agent Stack Has Zero Runtime Dependencies
mukundakatta profile

Why Every Library in the Agent Stack Has Zero Runtime Dependencies

#hermeschallenge #ai #python #agents
Comments
6 min read
Single-Flight Batching: When Many Callers Need the Same LLM Response
mukundakatta profile

Single-Flight Batching: When Many Callers Need the Same LLM Response

#hermeschallenge #ai #python #agents
Comments
6 min read
I run 30 agents in parallel. They share one budget. Here is the pool primitive that makes that safe.
mukundakatta profile

I run 30 agents in parallel. They share one budget. Here is the pool primitive that makes that safe.

#hermeschallenge #ai #rust #concurrency
Comments
4 min read
Heuristic Prompt Compression: Cut Your Context Window Usage Without Losing Key Information
mukundakatta profile

Heuristic Prompt Compression: Cut Your Context Window Usage Without Losing Key Information

#hermeschallenge #ai #python #agents
Comments
4 min read
Replay Every LLM Prompt Against a New Model Before You Migrate
mukundakatta profile

Replay Every LLM Prompt Against a New Model Before You Migrate

#hermeschallenge #ai #python #agents
Comments
3 min read
llmfleet: a gather-window dispatcher that fixes your parallel Claude eval rate limits
mukundakatta profile

llmfleet: a gather-window dispatcher that fixes your parallel Claude eval rate limits

#hermeschallenge #ai #python #agents
Comments
5 min read
prompt-eval-rubric: Composable 0.0-1.0 Scoring Rubrics for LLM Outputs
mukundakatta profile

prompt-eval-rubric: Composable 0.0-1.0 Scoring Rubrics for LLM Outputs

#hermeschallenge #ai #python #agents
Comments
6 min read
Your Agent Is Calling That Tool Again: tool-loop-guard
mukundakatta profile

Your Agent Is Calling That Tool Again: tool-loop-guard

#hermeschallenge #ai #python #agents
Comments
6 min read
prompt-replay: Record LLM Outputs Today, Replay Against a New Model Tomorrow
mukundakatta profile

prompt-replay: Record LLM Outputs Today, Replay Against a New Model Tomorrow

#hermeschallenge #ai #python #agents
Comments
5 min read
Six Security Layers for Python LLM Agents
mukundakatta profile

Six Security Layers for Python LLM Agents

#hermeschallenge #ai #python #agents
Comments
6 min read
agentsnap: Jest-Style Snapshot Tests for AI Agent Tool Calls
mukundakatta profile

agentsnap: Jest-Style Snapshot Tests for AI Agent Tool Calls

#hermeschallenge #ai #javascript #agents
Comments
5 min read
Cut Your Anthropic Bill in Half with the Batch API
mukundakatta profile

Cut Your Anthropic Bill in Half with the Batch API

#hermeschallenge #ai #python #agents
Comments
5 min read
agenttap: see exactly what your Python LLM client sends over the wire
mukundakatta profile

agenttap: see exactly what your Python LLM client sends over the wire

#hermeschallenge #ai #python #agents
Comments
5 min read
Build System Prompts From Named Sections Instead of One Giant String
mukundakatta profile

Build System Prompts From Named Sections Instead of One Giant String

#hermeschallenge #ai #python #agents
Comments
4 min read
Stable Anthropic Cache Scope Hashes: Know Whether Your Prompt Will Hit the Cache
mukundakatta profile

Stable Anthropic Cache Scope Hashes: Know Whether Your Prompt Will Hit the Cache

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