Productivity observability for coding agents | Backed by @DraperVC @StanfordUniversity

San Francisco, CA
Joined November 2024
You can just grade your projects with your own skills! My favorites are Comment hygiene and Subagent cost
Today we're launching XTrace, an open-source macOS app for people who code with agents. See AI vs human time, API-equivalent spend, and insights on what to improve. Add your own scoring skills or ones you discover. Try it: github.com/XTraceAI/xtrace-d…
2
7
209
Know your productivity. Boost your productivity.
Today we're launching XTrace, an open-source macOS app for people who code with agents. See AI vs human time, API-equivalent spend, and insights on what to improve. Add your own scoring skills or ones you discover. Try it: github.com/XTraceAI/xtrace-d…
2
1
6
135
Thank you everyone for coming today! We had a blast! #SFTechWeek
What a night! Just finished my own #SFTechWeek panel event and it went amazing! So many people came and some are even CEO of IPO companies or engineering managers who flied all the way from Asia or Europe to learn the trend of coding agent best practices.
2
158
What a night! Just finished my own #SFTechWeek panel event and it went amazing! So many people came and some are even CEO of IPO companies or engineering managers who flied all the way from Asia or Europe to learn the trend of coding agent best practices.
4
2
2
20
1,023
wow my SF Tech Week event is super oversubscribed. The venue can only fit ~75 folks, but we have around 300 signups already! dm me if you are on the waitlist but rlly want to join
This is the most insightful panel on coding agents for engineers, CTOs, and engineering managers during SF Tech Week 2026. Next Thursday, Oct 8, I'm hosting: "Unlock the Full Power of Coding Agents: Software Engineering in the Agent Era" Panelists: - @austinywang (@cmux) - Carrick Rogers (Saris AI) - @felixmeng_ (@XTrace_ai ) What we'll cover: - How tech leaders keep up with new agent tools that come out every day - How to stop vibe coding from hurting your team's code quality - How to keep your agents and your team aligned ​ Sign up: lnkd.in/geSJ8-tN ​ Full calendar: tech-week.com @Techweek_ #SFTechWeek
1
1
12
409
XTrace retweeted
7/ Felix Meng — CEO of @XTrace_ai “Beyond README.md: Teaching AI Agents from the Mistakes They Actually Make” Felix will show how agent memory can live inside the harness—capturing real failures and corrections, then surfacing the right rule before the next risky action.
1
1
1
48
Bookmark this paper from NVIDIA! Ever added a skill to your agent and just... trusted it worked? NVIDIA ran the numbers. The linters that check a skill's structure and style tell you almost nothing about how it does on real tasks (correlation 0.14). What actually works: run the same task with and without the skill, and look at the difference. They did this 947 times. The skill helped in about 3 out of 4 runs. The other 1 in 4? Nothing, or worse. arxiv link in comments:
2
1
4
124
Our CEO is live on X again! Follow his new account plz
Hello world! My old account algo was a mess so this is my new account! Quick intro if you don't know who I am: > Founder and CEO of XTrace > Alum of Stanford and KCL > prev. Mathworks and Sandia > now live in SF
6
258
Hello world! My old account algo was a mess so this is my new account! Quick intro if you don't know who I am: > Founder and CEO of XTrace > Alum of Stanford and KCL > prev. Mathworks and Sandia > now live in SF
1
3
1
5
460
Introducing Claude.md doctor An agent skill that examines your CLAUDE.md / AGENTS.md, grades it and tells you how to FIX it It even backtests your sessions to find the flaws that you can't tell just from the file Free and open-source. Try it today with just 1 command: npx skills add agent-clinic/claude-md-doctor
8
6
3
126
17,244
𝗜 𝗯𝘂𝗶𝗹𝘁 𝗮 𝗱𝗼𝗰𝘁𝗼𝗿 𝘀𝗸𝗶𝗹𝗹 𝗳𝗼𝗿 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 𝗳𝗶𝗹𝗲𝘀 It backtests every rule against your own Claude Code session history and shows which ones actually get followed. Ours graded a C, the loudest rule had 0% compliance. try the skill: github.com/agent-clinic/clau…
2
2
2
10
595
Our company one-liner was: "Team procedural memory for AI agents" And we figured the concept of procedural memory hasn't been mentioned a lot. Here is what we think you should know
1
5
351
I asked 10+ engineering managers this week what their no.1 headache is since vibe-coding. 6-7 of them said it's their engineers didn't code with the rules they have in their claude.md. I looked into the file and it's 1000+ lines...
6
1
11
1,356
You can now connect HubSpot to your MemHub account! Contextmaxxing! Learn more ↓ mem.xtrace.ai/changelog/on/2…
2
235
HUGE!
You can now use XTrace Memory on Hermes Agent!
1
2
217
Hey X! I'm Diara. Grad student at @UCBerkeley. Originally from Kazakhstan. Left-handed fencer at Halberstadt, birthplace of Bay Area fencing Joining @XTrace_ai this summer as a growth intern If you're building in the AI space or just want to connect, would love to chat :)
1
2
5
367
Spaces are limited. RSVP soon!
Save the dates! July is packed at XTrace. We are hosting the following events across the Bay:
2
203