
Data Engineer @tenaraiglobal๐ผ โข Opensource | Building schemabrain โค๏ธ
Github ๐
Joined February 2016
- Tweets2K
- Following404
- Followers381
- Likes3.2K
Pinned Tweet
This is awesome ๐คฉ๐คฉ๐คฉ Our team @bytehash_tech won the runner up in @web3con hackathon ๐๐
I'm so happy ๐คฉ๐คฉ๐ฅณ๐ฅณ๐ฅณ
gm! we are very pleased to announce @web3con 2022 hackathon winners ๐ฅณ
๐ฅ $15,000 Grand Prize - Brought to you by @Decentology & @0xPolygon:
NAT
๐ฅ $10,000 Runner Up - Brought to you by @Filecoin, @LivepeerOrg & @radicle:
bytehash
more winners ๐
Arun ๐ retweeted
I just built my own coding harness, just like Claude Code. (100% open-source)
A harness is the code wrapped around an LLM. The model only decides the next step, and the harness handles everything else, planning, tools, memory, and safety.
In simple words model acts as the brain and the harness provides the hands.
A coding harness is that same wrapper pointed at a codebase. It turns a plain text generator into something that reads files, edits code, runs tests, and fixes real bugs.
Here's everything that went into mine:
- the core agent loop
- file tools that double as external memory
- planning for long-running tasks
- subagents that work in their own context
- sandboxed execution in a throwaway VM
- human-in-the-loop approval
- persistent memory and checkpointing
The whole thing is built on CrewAI, a 100% open-source framework.
I also wrote an article on this. It covers everything that goes into building a coding harness, the agent loop, planning, subagents, sandboxing, memory, and checkpointing, built step by step.
The article is quoted below.
How do you stop AI agents from reading or exposing PII?
Relying on system prompts is fragile. We built a ๐ฑ๐ฎ๐๐ฎ๐ฏ๐ฎ๐๐ฒ ๐ณ๐ถ๐ฟ๐ฒ๐๐ฎ๐น๐น for AI agents:
๐ Locked Catastrophic Floor (credentials, cards)
๐ Config-as-code (git-ready YAML diffs)
Try it: github.com/Arun-kc/schemabraโฆ
26
Built this Data Dictionary UI for SchemaBrain with Claude.
Schema โ entities, PII, joins, metrics.
#BuildInPublic #claude #claudedesign
49
A boundary you ask a model to respect only holds while it feels like respecting it.
Turn the temperature up on an agent, and it doesn't just hallucinate โ it quietly stops following your "use only these 3 sources" rule too.
Enforce limits outside the model, not in the prompt.
1
32
Arun ๐ retweeted
Gmeow
Who's excited to play a web3 game that doesn't feel like a chore?๐ผJust download on March 26th, play, have fun, earn MEOWS with your friends
If this is you, then...
Gmeow it back!
Arun ๐ retweeted
Dencun. โ
Memecoin frenzy. โณ
The top-two retail-focused L1s are competing for users.
But what do users really want? And how do we measure it?
โข Speed โ TPS
โข Cost โ Avg fee per transaction
โข Volume โ Transaction count
Most users also want ease of conducting transactions, but that's easier said than measured.
Based on these 3 consumer metrics, @Solana is outpacing Ethereum. Not just @ethereum, it's outpacing @base.
Solana's:
โ TPS is 110x more than Ethereum.
โ Transaction count is 9.7x Ethereum's.
โ Fee (avg) is lesser than Ethereum and Base.
(This is after Dencun and amid the memecoin frenzy though).
Will this disparity continue?
Arun ๐ retweeted
If 100 people use a chain, how many will be retained after a month?
@osmosis has the highest retention rate at 33% while with @Aptos_Network, only 8 of 100 users remain after a month.
Here are the rest:
โข @SeiNetwork: 8.8/100
โข @Polygon: 19.4/100
โข @THORChain: 19.8/100
โข @solana: 20.9/100
โข @arbitrum: 25.1/100
โข @Optimism: 27.4/100
โข @avax: 28.6/100
โข @cosmos: 31.7/100
Arun ๐ retweeted
๐ Earn Web 3 Giveaway ๐
We are giving away 10 FREE passes for @EarnWeb3DAO ๐ซ
To enter:
1๏ธโฃ Comment on this post
2๏ธโฃ Retweet for an extra chance
Winners will be drawn tomorrow! ๐
Day 23 of #100DaysOfWeb3
Going through level 9 of the sophomore track @LearnWeb3DAO โก
๐ ๏ธICO -- In Progress๐คฉ
#wagmi ๐
#100DaysOfCode
Day 22 of #100DaysOfWeb3
Started going through level 9 of the sophomore track @LearnWeb3DAO โก
๐ ๏ธICO ๐คฉ
#wagmi ๐
#100DaysOfCode
Astonishing growth! ๐คฉ๐ฅณ All the best @LearnWeb3DAO and thanks for all the amazing contents. It's really helpful for all of us Web3 learners ๐๐
WEโRE HIRING! ๐
After 8 months of buildingโฆ we are expanding the team!
Send us your Resumรฉ!
Say hi ๐๐
angel.co/company/learnweb3-dโฆ
3. Upsert load
Upsert load is a kind of variation of the incremental load. It's basically update + insert.
Upsert is an operation that will update an existing row if a specified value already exists in a table, and insert a new row if the specified value doesn't already exist
1















