Ankur Rustagi

[Ankur Rustagi @RustagiAnkur]

We took a contrarian bet on how to handle context. Instead of following the industry standard of using the primary model for compaction, we built a subagent system around Mercury 2. This led to 90% lower costs and 82% faster latency.

[Ankur Rustagi @RustagiAnkur]

At Augment, we aren’t tied to a single provider, which gives us the freedom to prioritize models with optimal speed and cost-efficiency for our users. Our recent experiments proved that Mercury 2 provides the ideal intelligence level for tasks like context compaction.

[Inception @_inception_ai]

@augmentcode rebuilt their context compaction layer around Mercury 2. 82% latency cut. 90% cost cut. Comparable quality to Opus 4.7. Running in production today.

"We took a counter-intuitive bet. We decoupled summarization entirely, offloading it to Mercury 2 as a dedicated subagent. Mercury 2 is the highly efficient engine powering our most critical workflows."

-@RustagiAnkur & @jm1234567890, Members of Technical Staff at Augment Code

The subagent layer needs the most efficient model. Full methodology and eval setup in the writeup.

https://t.co/LPVTdaMjli

[Ankur Rustagi @RustagiAnkur]

@jitenoswal Saw the infinite loop issue on @firecrawl agent. Although seems like it's common with small context windows and low intelligence model. Good work.

[Martian @withmartian]

When you filter to PRs where someone actually engaged with the PR after the review, scores shift significantly.

@OpenAI’s Codex sees the largest swing at +17.2pp. @augmentcode climbs to #2 in F1 with +12.3pp.

Some tools score higher when nobody engages, others score higher when humans are actively involved. The delta reflects how each tool is being used, not which one is better.

[Ankur Rustagi @RustagiAnkur]

@bayer04_en is a special place. When @kaihavertz29 scored the penalty, they didn't boo him. Infact celebrated him for doing so well in his football career. This is so wholesome to watch. Cheers Leverkusen!

[Bayer 04 Leverkusen @bayer04_en]

10 years at Bayer 04. Welcome back Kai. 🫶🖤❤️

#B04ARS

[Ankur Rustagi @RustagiAnkur]

Some positivity and peace from the #Jews of #India
https://t.co/WjX49f51lh

[Vinod Sharma @vinodbf16]

Inspired by @karpathy's brilliant https://t.co/tqV3DiBThL — ported it to Rust. 208 lines, zero deps, ~400x faster

• Tape autograd (no graph/Rc)
• Flat Vec<f64>, cache-friendly
• No GC, just truncate
• Native math, no interpreter
• 283s → 0.68s

https://t.co/9nA5oLAm6O

[Ankur Rustagi @RustagiAnkur]

@sama and @DarioAmodei can't shake hands. https://t.co/ojtGzqclaH
Lessons:
- money and success does not guarantee peace and love.
- everyone thinks they are right. The right wrong arguments sometimes happen at world stages as well.

[Ankur Rustagi @RustagiAnkur]

@amruthagujjar Claude also tries to do the same. They need the money and recognition.

[Ankur Rustagi @RustagiAnkur]

@grok would you know?

[Ankur Rustagi @RustagiAnkur]

Everyone is projecting the first one person unicorn. Curious are there any one person unicorn/10 ($100m) startups sold yet?

[Ankur Rustagi @RustagiAnkur]

I think I broke @GeminiApp search. Guess what was the query

[Ankur Rustagi @RustagiAnkur]

https://t.co/XgXPk6BrzO beta is live . Best quality PDF generation that is just like your web dashboards. It's like @resend for creating a pdf. And it's 50-90% cheaper than any alternative. Enjoy!

[Ankur Rustagi @RustagiAnkur]

@taheerBuilds @steipete @nutrientdocs AI can make it, I created https://t.co/FEgQgcVLPk , highest quality PDF creation and 50-80% cheaper than any other player.

[Ankur Rustagi @RustagiAnkur]

If you ever wondered whether agents talk to each other.

Two agents built at @augmentcode came up with there language ABX. And used it to identify, resolve and verify an issue. Today is just hackathon but integrated sdlc automation is the future.

[Ankur Rustagi @RustagiAnkur]

Today is #hackathon day @augmentcode . We created an OpenClaw version internally and asked it to come up with an optimized language to talk to an older version agent. They came up with ABX (augment bot exchange) .

[Ankur Rustagi @RustagiAnkur]

@amruthagujjar Thanks for the shoutout @amruthagujjar !

[Ankur Rustagi @RustagiAnkur]

Tomorrow, my colleagues at @augmentcode and I will be sharing about our SOTA code context engine. It improves @claudeai and @cursor_ai quality by ~70% .

[Augment Code @augmentcode]

Want to experience the magic of our Context Engine with your existing toolbase?

Introducing Context Engine MCP: semantic indexing that works across Claude Code, Cursor, Zed, GitHub Copilot, and 10+ other agents.

See an interactive live demo on Tuesday, February 10 at 10 AM PT. Implement in your workflows on the same day.

Register now: https://t.co/cNjYr7qoWe

[Ankur Rustagi @RustagiAnkur]

Who is MCPlexor for?
🔹 Power Users: Waitlist open for MCPlexor Cloud (managed routing, no infra).
🔹 Privacy / Local: Use the new Ollama backend. Zero cost, offline.

checkout: https://t.co/3CFCMr37Ac

#AIAgents #MCP #Ollama #DevTools

[Ankur Rustagi @RustagiAnkur]

Shipped #Ollama support for MCPlexor 🚀
If your agent uses Linear + GitHub + Notion, you're dumping ~40k tokens into context on every request. That's 20% of a 200k context window gone to tools.
MCPlexor fixes this. <1k tokens overhead. Dynamic routing. Try 100% local.
Details 👇

[Ankur Rustagi @RustagiAnkur]

The solution: Semantic Multiplexing

MCPlexor sits between your agent and your tools.

Agent asks for "create issue"
We route to Linear
Only Linear tools load
Result: 95% token reduction.

And now, you can run the routing logic locally with Ollama (Llama 3, Mistral).