Siddhant Khare

23 | Devtools ❤️ | Engineer @ona_hq | Maintainer @OpenFGA, github1s 💚 | Building agent infra & tools | Author of | opinions are mine

[Siddhant Khare @Siddhant_K_code]

I wrote a book for engineering leaders.

The Agentic Engineering Guide. 10 parts, 33 chapters. Context engineering, authorization, cost control, sandboxing, evaluation, governance, adoption playbooks.

Not a prompt tutorial. The decisions you face when shipping agents to production this quarter.

Early version. Open source. Rough edges included. Spot a mistake, open a PR.

https://t.co/nVn7rxuMRI

[Siddhant Khare @Siddhant_K_code]

Since December, I’ve primarily built 3 open-source products on weekends.

They still don’t look impressive if you only judge them by GitHub stars, but all three have led to VC interest. More importantly, the first two have also started getting meaningful enterprise usage.

Distill was the first one that helped me connect with some good VCs, but after building AgentTrace and AgentAuthz, the conversations became much stronger, and now there are actual enterprise users as well.

the reson I’m writng all this that you don’t always need a huge number of GitHub stars to get interest, users, or investors.

Stars can help, of course. But people who actually need the tool will find it, use it & sometimes even invest in it

[Siddhant Khare @Siddhant_K_code]

@YashikaBadaya "git gud" is the key!!

[Siddhant Khare @Siddhant_K_code]

@paw_lean @OpenAI Finally, the news is out!!!
congratulations again <3

[Siddhant Khare @Siddhant_K_code]

@hthieblot Invest in me or one of my products https://t.co/s8nLVUoDYu

[Siddhant Khare @Siddhant_K_code]

@rauchg Trying my best!!!

https://t.co/PxEovrv2EC

[Siddhant Khare @Siddhant_K_code]

Met the OG @AnupamMittal - really great & insightfuly conversation ❤️

[Siddhant Khare @Siddhant_K_code]

@samlambert Hard agree!!

I feel public appearances, podcasts are just for brand building/promos

[Siddhant Khare @Siddhant_K_code]

agent-trace is now on the GitHub Actions Marketplace!!!

Runs your evals in CI, posts scores to the step summary, fails on regression. Also shipped couple of new features & bug fix

OTLP streaming, W3C traceparent, CrewAI/LangGraph tracing, replay --diff,
human-in-the-loop approvals, RBAC, SSO, workspace isolation, web dashboard.

https://t.co/kjuefLv4kz

[Siddhant Khare @Siddhant_K_code]

@compileandpush for?

[Siddhant Khare @Siddhant_K_code]

agent-trace is now on the GitHub Actions Marketplace!!!

Runs your evals in CI, posts scores to the step summary, fails on regression. Also shipped couple of new features & bug fix

OTLP streaming, W3C traceparent, CrewAI/LangGraph tracing, replay --diff,
human-in-the-loop approvals, RBAC, SSO, workspace isolation, web dashboard.

https://t.co/kjuefLv4kz

[Siddhant Khare @Siddhant_K_code]

@innoscoutpro Both. Each tool call shows the args inline (command, file path, pattern, etc.) & a preview of the result. The diff highlights where the two sessions diverge - same tool, different args, or one session retried where the other didn't

[Siddhant Khare @Siddhant_K_code]

@rauchg Trying my best!!!

https://t.co/PxEovrv2EC

[Siddhant Khare @Siddhant_K_code]

@jainmahir_10 Ahh, sorry, I have already booked too many slots for these days.

Maybe next time <3

[Siddhant Khare @Siddhant_K_code]

Tools you need to run parallel AI experiments in your organization - build, test & decide fast!!

https://t.co/aKjpyPGaCh

[Siddhant Khare @Siddhant_K_code]

Tools you need to run parallel AI experiments in your organization - build, test & decide fast!!

https://t.co/aKjpyPGaCh

[Siddhant Khare @Siddhant_K_code]

Good survey question as a company to decide where to put money? Buying benchmark numbers or paying to Twt influencers to influence the “taste”

[Tibo @thsottiaux]

Do you still trust benchmarks or do you just listen to your friends? What makes you try a new model?

[Siddhant Khare @Siddhant_K_code]

Read here: https://t.co/G0O4aZZa7W

[Siddhant Khare @Siddhant_K_code]

My essay on "AI Fatigue" got featured in O'Reilly Radar by @mikeloukides

[Siddhant Khare @Siddhant_K_code]

I am in for all development and all that sh... But how do people get around without addressing the environmental impact? This photage is a nightmare for an environmentalist :/

[Hunter Weiss @Hunter_Weiss]

sorry it blew up, but for explosion fanatics, this is an all-time explosion caught on camera https://t.co/nt12WgCwc3

[Siddhant Khare @Siddhant_K_code]

If this is true, does it mean we have hit the ceiling for Model accuracy gains?

[Max For AI @MaxForAI]

笑死了，Claude Opus4.8蒸馏了阿里巴巴Qwen啊🤣

通过API用中文问你是谁，会很大概率回答

我是通义千问（Qwen），是阿里巴巴集团旗下的统义实验室自主研发的超大规模语言模型。