Mukunda Rao Katta - DEV Community

Mukunda Rao Katta

May 28

Different agent frameworks log 'input_tokens' differently. Here's the fix.

#devchallenge #hermesagentchallenge #agents #python

2

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 28

400 from Anthropic API. Two consecutive user messages. Every time.

#devchallenge #hermesagentchallenge #agents #python

2

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

Context window exceeded at turn 23. Here's how I track token usage without a tokenizer.

#devchallenge #hermesagentchallenge #agents #python

2

1 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent spent $3 before I noticed. Now it can't.

#devchallenge #hermesagentchallenge #agents #python

3

1

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent's stop condition was a 40-line if/elif chain. I replaced it with 3 lines.

#devchallenge #hermesagentchallenge #agents #python

4

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

My agent kept hitting context limits. This one function fixed it.

#devchallenge #hermesagentchallenge #agents #python

4

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

Your Hermes agent's audit log is leaking customer emails. Here's a 100-line lib that fixes that.

#devchallenge #hermesagentchallenge #agents #security

1

2

4 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

My agent kept forgetting what it was doing. A scratchpad fixed it.

#devchallenge #hermesagentchallenge #agents #python

2

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

I replaced 200 lines of ad-hoc state management in my Hermes agent with one object.

#devchallenge #hermesagentchallenge #agents #python

4

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

The two-line Hermes agent logger I wish existed a month ago

#devchallenge #hermesagentchallenge #agents #observability

3

3 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent called exec_shell. It shouldn't have been able to.

#devchallenge #hermesagentchallenge #agents #python

3

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent ran 500 turns and cost $40 before I noticed. Now it can't.

#devchallenge #hermesagentchallenge #agents #python

3

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent loop blew the context window at turn 47. llm-context-trim fixed it.

#devchallenge #hermesagentchallenge #agents #python

4

3 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

Building LLM message lists by hand is error-prone. There's a better way.

#devchallenge #hermesagentchallenge #agents #python

4

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent kept returning JSON in a markdown code block. I kept writing the same regex. Then I stopped.

#devchallenge #hermesagentchallenge #agents #python

4

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

Claude's extended thinking is useful. Sending raw <thinking> tags to users is not.

#devchallenge #hermesagentchallenge #agents #python

2

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

I changed one line in my Hermes system prompt. prompt-diff showed me exactly what.

#devchallenge #hermesagentchallenge #agents #prompts

2

3 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

Your Hermes agent's prompt cache is 30% hit because of one timestamp. Here's how to find it.

#devchallenge #hermesagentchallenge #agents #performance

4

4 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

My agent started lying. It took me two days to realize the system prompt had changed.

#devchallenge #hermesagentchallenge #agents #python

2

3 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

I changed my Hermes agent's system prompt and used tool-call-diff to prove it actually helped

#devchallenge #hermesagentchallenge #agents #testing

3

4 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

I couldn't reproduce the bug because I had no record of what tool calls my Hermes agent made.

#devchallenge #hermesagentchallenge #agents #python

3

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

My agent called web_search 47 times in 10 seconds. One class stopped it.

#devchallenge #hermesagentchallenge #agents #python

1

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

One Hermes tool call took 4.8 seconds. The others averaged 900ms. trace-anomaly found it.

#devchallenge #hermesagentchallenge #agents #observability

3

3 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent ran for 2 hours, hit a timeout at turn 89, and I had to start over. Now it checkpoints.

#devchallenge #hermesagentchallenge #agents #python

4

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

My Hermes agent spent how much? trace-cost for JSONL audit logs

#devchallenge #hermesagentchallenge #agents #observability

3

1

3 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

I had 3,000 agent trace events in JSONL. My manager wanted them in Excel. One line.

#devchallenge #hermesagentchallenge #agents #python

2

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

5000 events, one worker, one bug: trace-filter for agent JSONL traces

#devchallenge #hermesagentchallenge #agents #observability

3

4 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

grep for your agent traces — substring, exact, and regex in one call

#devchallenge #hermesagentchallenge #agents #python

2

2 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

I ran three Hermes agents in parallel. trace-merge stitched them into one timeline I could read.

#devchallenge #hermesagentchallenge #agents #observability

3

5 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

I logged 300 Hermes runs to one file. trace-session-split cut it into 300.

#devchallenge #hermesagentchallenge #agents #observability

3

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

p95 latency was 1.68 seconds. I didn't know until I built trace-stats.

#devchallenge #hermesagentchallenge #agents #observability

3

3 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

After every Hermes agent run, I print a 10-line summary. Now I know exactly what happened.

#devchallenge #hermesagentchallenge #agents #python

3

2 min read

Hermes Agent Challenge Submission: Write About Hermes Agent

Mukunda Rao Katta

May 25

Pipe your Hermes Agent audit log into Datadog in 5 lines (no OTel SDK required)

#devchallenge #hermesagentchallenge #observability #agents

3

5 min read

Hermes Agent Challenge Submission: Build With Hermes Agent

Mukunda Rao Katta

May 25

I had 800 lines of Hermes agent audit log. trace-tree turned it into a tree I could read.

#devchallenge #hermesagentchallenge #agents #observability

4

5 min read

Mukunda Rao Katta

May 25

I shipped 50 agent infrastructure libraries. Here is what I learned.

#hermeschallenge #ai #python #agents

7 min read

Mukunda Rao Katta

May 25

prompt-shield: a tiny, zero-dep prompt-injection detector you can drop in front of any agent

#hermeschallenge #ai #llm #agents

5 min read

Mukunda Rao Katta

May 25

A six-concern production harness for Nemotron agents on Crusoe Managed Inference

#hermeschallenge #ai #llm #agents

4 min read

Mukunda Rao Katta

May 25

agenttap: see exactly what your LLM SDK sent to the wire, with API keys scrubbed

#hermeschallenge #ai #llm #agents

4 min read

Mukunda Rao Katta

May 25

llmfleet: pool many agents' turns into one Batch API call and save 50 percent

#hermeschallenge #ai #llm #agents

4 min read

Mukunda Rao Katta

May 25

cachebench: stop finding out about prompt-cache regressions from the invoice

#hermeschallenge #ai #llm #agents

4 min read

Mukunda Rao Katta

May 25

I shipped eight agent-stack repos in eight hours. Here's what made it possible.

#hermeschallenge #ai #llm #agents

4 min read

Mukunda Rao Katta

May 25

I needed a stable cache key for LLM requests. The hard part was the input list order.

#hermeschallenge #ai #llm #rust

4 min read

Mukunda Rao Katta

May 25

My LLM provider went down for 11 minutes. My code spent 4 of them in connect timeouts.

#hermeschallenge #ai #llm #rust

4 min read

Mukunda Rao Katta

May 25

My RAG system slowly got worse for three months and nobody noticed.

#hermeschallenge #ai #rag #python

4 min read

Mukunda Rao Katta

May 25

I rewrote my Bedrock client three times. Then I extracted the boring parts into one library.

#hermeschallenge #aws #bedrock #python

4 min read

Mukunda Rao Katta

May 25

I Shipped 50 Agent-Stack Libraries. Here Is How They Fit Together.

#hermeschallenge #ai #python #agents

6 min read

Mukunda Rao Katta

May 25

prompt-eval-rubric: Score Your Agent's Outputs Without Paying for Another LLM Call

#hermeschallenge #ai #python #agents

5 min read

Mukunda Rao Katta

May 25

agent-fn-registry: Register Your Agent Tools With Schema, Side Effects, and Defaults in One Place

#hermeschallenge #ai #python #agents

5 min read

Mukunda Rao Katta

May 25

agent-replay-trace: Load and Step Through Agent Traces for Debugging

#hermeschallenge #ai #python #agents

5 min read

Mukunda Rao Katta

May 25

agent-shadow-mode: Run Your Agent in Record-Not-Execute Mode Before You Trust It

#hermeschallenge #ai #python #agents

5 min read

Mukunda Rao Katta

May 25

llm-pii-redact: Remove PII From Prompts Before They Reach the Model

#hermeschallenge #ai #python #agents

6 min read

Mukunda Rao Katta

May 25

Why I Built 50 Small Libraries Instead of One Big Agent Framework

#hermeschallenge #ai #python #agents

1

6 min read

Mukunda Rao Katta

May 25

Production Python Agent Checklist: 15 Things Before You Deploy

#hermeschallenge #ai #python #agents

6 min read

Mukunda Rao Katta

May 25

When and How to Use the Anthropic Batch API in Your Agent

#hermeschallenge #ai #python #agents

6 min read

Mukunda Rao Katta

May 25

What I Learned Shipping 50 Agent-Stack Libraries in One Sprint

#hermeschallenge #ai #python #agents

6 min read

Mukunda Rao Katta

May 25

My agent called search() with `{"query": null}`. The error message I returned saved the next 30 minutes.

#hermeschallenge #ai #python #agents

4 min read

Mukunda Rao Katta

May 25

How to Test LLM Agents Without Calling the Real API

#hermeschallenge #ai #python #agents

5 min read

Mukunda Rao Katta

May 25

Make Your Agent's API Calls Idempotent Before You Need To

#hermeschallenge #ai #python #agents

5 min read

Mukunda Rao Katta

May 25

Four Patterns for Multi-Agent Python Systems That Actually Work

#hermeschallenge #ai #python #agents

5 min read

Mukunda Rao Katta

May 25

Three Error Recovery Patterns for LLM Agent Tool Failures

#hermeschallenge #ai #python #agents

5 min read

Want to connect with Mukunda Rao Katta?