KlaatAI

Building the future of AI-powered software development.
Your AI coding co-pilot for real developers.
Open Source • Multi-Model • Ship Faster

[KlaatAI @KlaatAI]

🚀 300+ GitHub Stars!

One year ago, KlaatAI was just an idea.

Today, Klaat Code has crossed 300+ GitHub stars. ⭐

This isn’t just another AI wrapper.

We built Klaatu, our intelligent multi-model routing engine that automatically selects the right frontier model for each coding task—balancing reasoning quality, latency, and cost.

With Klaat Code you get:

⚡ Intelligent multi-model routing
🧠 Repository-aware coding with Code Graph
💬 Unified chat, terminal & API experience
🚀 Faster, cost-efficient AI coding workflows

We recently benchmarked Klaat Code against leading AI coding CLIs and were excited to see it deliver strong coding performance while significantly reducing inference costs through intelligent routing.

This milestone wouldn’t have been possible without everyone who:

⭐ Starred the project
🐛 Reported bugs
💡 Shared ideas
🔥 Contributed code
❤️ Believed in what we’re building

We’re only getting started.

Over the coming months we’re focused on:

Better agents
More intelligent routing
Faster inference
More supported models
Enterprise features
An even better developer experience

If you haven’t tried Klaat Code yet, we’d love your feedback.

⭐ GitHub: https://t.co/iZYdz7g2ZH

Every issue, feature request, and star helps us build something developers genuinely love.

Thank you for being part of this journey. ❤️

#opensource #AI #DeveloperTools #LLM #GitHub #Coding #BuildInPublic #KlaatAI

[Aakash Singh @otakuaakash]

Been using this lately and honestly, it’s pretty impressive. 👀

The fact that you can get Kimi K3 + Qwen 3.8 Max on KlaatAI’s free tier right now makes it even more worth trying.

If you’re into coding with AI, give KlaatCode a shot. 🚀

[KlaatAI @KlaatAI]

This is exactly why we built KlaatCode. 🔥

And yes — you can try it for free.

For a limited time, KlaatAI’s free tier includes access to Kimi K3 and Qwen 3.8 Max.

Build. Ship. Experiment. 🚀
No expensive setup required.

Try KlaatCode → https://t.co/QExbJvUFB6

[PRATEEK GAUR @PRATEEK_GAUR_]

AI agents just made Flappy Bird.
Results:
KlaatAI (free tier) $0.05 · under 1 min
Cursor Auto $0.72
Grok 4.5 $1.90
Claude Sonnet 5 $2.10
One of them cost 40x less and still works.
Watch the side-by-side ⬇️
Made with KlaatAI.
Try https://t.co/HWIF9nzeil

[KlaatAI @KlaatAI]

@LinkedIn @LinkedInHelp

[PRATEEK GAUR @PRATEEK_GAUR_]

@LinkedInHelp @LinkedIn
Subject: Urgent Account Recovery Request – LinkedIn Account Compromised Dear LinkedIn Support Team, I am requesting your immediate assistance in recovering my LinkedIn account, as it has been compromised by an unauthorized individual. Account Details

LinkedIn Username: prateekgaur05

Registered Email: [email protected]

The attacker has taken control of my account and has added their own authenticator app for two-factor authentication, which has completely locked me out. I no longer have access to my account, even though I am the legitimate owner. To verify my identity and ownership of the account, I can provide:

My government-issued identification, if required.
My resume containing the same professional information as my LinkedIn profile.

Proof of my LinkedIn Premium subscription.

Previous security emails from LinkedIn, including the email notifying me when someone attempted to access or modify my account.

Any additional information or documentation that your security team requires.
I kindly request that you:
Verify my identity.
Remove the unauthorized authenticator app and any other security methods added by the attacker.
Restore my access to the account associated with [email protected].

Secure the account against any further unauthorized access.

This LinkedIn profile is extremely important for my professional career, networking, and job opportunities. I would greatly appreciate your urgent assistance in restoring access as soon as possible. Thank you for your time and support. I look forward to your response. Sincerely, Prateek Gaur Email: [email protected]

[KlaatAI @KlaatAI]

KlaatCode V2.4.2 is out now. Use DeepSeek 4 Flash for free.

[Sedra @SedraLab]

🤖 Terminal tabanlı AI kodlama asistanlarının bilindik sorunu: ya güçlü ama pahalı, ya ucuz ama yetersiz. klaatcode bu dengeyi akıllı bir yönlendirme katmanıyla değiştiriyor.

Her isteğinizi tek bir modele göndermiyor. Arkadaki Klaatu yönlendiricisi, işin zorluğuna göre nano’dan heavy’e beş katman arasında seçim yapıyor. Basit bir tamamlama için pahalı model çalıştırmıyor, karmaşık bir hata ayıklamada en güçlü modeli devreye alıyor.

Kendi benchmark’larında 30 görevde Claude Code ile aynı doğruluğu yakalamış. Ama görev başına maliyet 5.5 kat daha düşük. Asıl önemlisi, aynı testleri repo içindeki `bun run bench` komutuyla siz de çalıştırabiliyorsunuz.

Projenin asıl farkıysa kod tabanınızı bir bilgi grafiği olarak indekslemesi. Dosya okumak yerine symbol, çağrı ve etki sorguları yapıyor; her işte 5 ila 15 kat daha az token harcıyor. Bu, hem hız hem maliyet tarafında doğrudan kazanç demek.

Açık kaynak, tek komutla kuruluyor. Riskli işlemlerde izin istiyor, yazdığı kodu otomatik kontrol edip hatasını düzeltiyor. Terminalde gerçek bir çift programcı gibi çalışıyor.

Repo ilk yorumda.

[Qwen @Alibaba_Qwen]

📢Meet Qwen3.8-Max — our most capable model to date.

Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉

Qwen3.8-Max, a new bar for coding and cowork at 2.4T parameters:

- Autonomous coding: 10+ days of self-evolving development, from empty folder to production without hand-holding, complete project trace in the GitHub：https://t.co/iVHZWQoeSo
- Real work, real results: Production-quality deliverables across hundreds of professions.
- Long-horizon mastery: System-level autonomous planning with closed-loop adaptive learning, driving 500+ turns of chip design optimization and 365 days of e-commerce strategy.
- Native multimodal intelligence: Vision isn't just input — it's a continuous feedback loop for planning, execution, and self-correction.

💰Pricing:
Input: $2.0 / M tokens
Output: $6.0 / M tokens
Implicit Caching: $0.25 / M tokens

Start building with Qwen3.8-Max! 🚀

📖 Blog: https://t.co/iwjmQxLBof
✅ Qwen Studio: https://t.co/4V2pFvDovG
⚡ API: https://t.co/gAGqaLQGbN

[KlaatAI @KlaatAI]

AI is getting way too expensive" is on the HN front page again.

We're a small team building a model router precisely because of this. The thing I keep relearning: most coding-agent spend isn't the hard reasoning. It's everything around it: retries, tool calls, failovers, re-reading context that didn't change.

so we made two calls early: route every request to the cheapest model that can actually do the job, and never count tool calls or retries against limits.

still tiny. still shipping. But I think cost is the wedge Frontier Labs can't defend.

[KlaatAI @KlaatAI]

Cursor shipped a router last week. their claim: frontier-quality results at 60% lower cost by auto-picking the model per request.

this is the entire bet behind Klaatai. Your rename doesn't need the same brain as your race condition.

differences in how we do it: we route across 30+ models from every provider (not one vendor's lineup), tiers from nano all the way to titan, and the same router runs your chat, CLI, and VS Code. Free tier included.

Routing isn't a feature anymore. It's becoming the layer.

[Cursor @cursor_ai]

Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand.

Router delivers frontier-quality results at 60% lower cost.

[KlaatAI @KlaatAI]

Your linter fix doesn't need the same model as your race condition.

Klaatu-o1 scores each request and routes it across 30+ frontier models in tiers from nano up to the new Titan. Big models when the task earns it, cheap ones when it doesn't.

And tool calls, retries, and failovers never count against your message limits.

Free tier, no card → https://t.co/rWFjZbPdTL

[KlaatAI @KlaatAI]

@0xPrajwal_ Use KlaatAI for free

[KlaatAI @KlaatAI]

@Migma_AI Hey, Lets see if we can work together.

[KlaatAI @KlaatAI]

@anupamrjp https://t.co/1uTzn1TsVd

[KlaatAI @KlaatAI]

Paying frontier rates to rename a variable is pure waste.

We put Klaat Code head-to-head against Claude Code, Cursor and opencode on the exact same 33 real coding tasks. Same prompts. Same verification. No cherry-picking.

Results:
→ Klaat Code: 33/33 · $0.027/task
→ Claude Code (Sonnet 5): 33/33 · $0.146/task
Same accuracy. 5.4× less money.
The only difference: Klaatu-o1 routes every message to the cheapest of 30+ models that can actually handle it. Hard problems get frontier power. Everything else stays cheap. Tool calls are free. Code Graph + memory cuts tokens 5–15×.

GitHub already at 314 stars:
https://t.co/T3sLt7VHWp

Reproduce the entire benchmark yourself in under 2 minutes:

git clone https://t.co/T3sLt7VHWp
bun install && bun run bench
Live on Product Hunt right now:
https://t.co/CIu7tMfxzq

Try it free (no card):
https://t.co/tmuTpHX9gY
Poll (reply with number):
Still paying full frontier rates for trivial edits

Already built your own router
About to run the bench and tell us we’re full of shit (or not)

Drop the numbers. Roast the methodology. Tell us which task broke your expectations.
We answer every reply.
Who’s first?👇

[KlaatAI @KlaatAI]

Paying frontier rates to rename a variable is pure waste.

We put Klaat Code head-to-head against Claude Code, Cursor and opencode on the exact same 33 real coding tasks. Same prompts. Same verification. No cherry-picking.

Results:
→ Klaat Code: 33/33 · $0.027/task
→ Claude Code (Sonnet 5): 33/33 · $0.146/task
Same accuracy. 5.4× less money.
The only difference: Klaatu-o1 routes every message to the cheapest of 30+ models that can actually handle it. Hard problems get frontier power. Everything else stays cheap. Tool calls are free. Code Graph + memory cuts tokens 5–15×.

GitHub already at 314 stars:
https://t.co/T3sLt7VHWp

Reproduce the entire benchmark yourself in under 2 minutes:

git clone https://t.co/T3sLt7VHWp
bun install && bun run bench
Live on Product Hunt right now:
https://t.co/CIu7tMfxzq

Try it free (no card):
https://t.co/tmuTpHX9gY
Poll (reply with number):
Still paying full frontier rates for trivial edits

Already built your own router
About to run the bench and tell us we’re full of shit (or not)

Drop the numbers. Roast the methodology. Tell us which task broke your expectations.
We answer every reply.
Who’s first?👇

[KlaatAI @KlaatAI]

@Joi2James https://t.co/1uTzn1TsVd

[KlaatAI @KlaatAI]

@anupamrjp https://t.co/1uTzn1TsVd

[KlaatAI @KlaatAI]

@humansoul @rivonn yes

[KlaatAI @KlaatAI]

@lightsilver323 https://t.co/1uTzn1TsVd
https://t.co/UsmL6hNoGr

[RepoGems @RepoGems]

🚀 Open-source AI coding agent for terminal with Claude Code-grade accuracy.

See link below 👇

[Rivon @Rivonn]

claude code at 18% of the cost, with a reproducible benchmark to back it

klaatcode just hit 174 stars and trending in topic:ai on github

here is what it does:

> per-request cost routing across 5 tiers (nano > heavy), so simple edits don't burn reasoning tokens

> code-graph index instead of grep claims 5-15x fewer tokens per task than whole-file reading

> standalone binary, no node/bun runtime at runtime

> free tool calls inside a request, only user messages count against quota

their bench: same 30 fixtures as the claude code test set, 30/30 solved either way, $0.026/task vs $0.146/task

you can rerun it with `bun run bench` and check the math yourself

setup:

npm i -g klaatcode && klaatcode

apache 2.0, npm package is live, repo is in CS

the claude code tax is optional now