AI tool comparison
LM Studio + Locally AI vs pi-autoresearch
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Developer Tools
LM Studio + Locally AI
LM Studio buys the best iOS local LLM app to go cross-device
75%
Panel ship
—
Community
Free
Entry
LM Studio, the most popular desktop app for running local large language models, has acquired Locally AI — the leading iOS and iPadOS app for on-device inference on Apple Silicon. Locally AI's creator Adrien Grondin is joining LM Studio full-time to lead cross-device native AI experiences. The acquisition signals LM Studio's ambition to own the full local AI stack: macOS, Windows, Linux, and now iPhone and iPad. Locally AI was notable for its deep Apple Silicon integration, using Core ML and Metal Performance Shaders to run models like Llama 3 and Phi-3 natively on A-series and M-series chips. The app had a dedicated following among privacy-conscious users who wanted a clean iOS interface without compromising their data to cloud services. LM Studio brings a larger model library, server mode, and a more mature MLX/GGUF toolchain. For local AI enthusiasts, this is a consolidation play in a space that was starting to fragment across too many single-platform apps. A unified LM Studio experience across desktop and mobile would be a significant UX improvement. It also sets up an interesting competition with Apple's own on-device AI ambitions in iOS 19.
Developer Tools
pi-autoresearch
Autonomous code optimization loop — edit, benchmark, keep or revert
50%
Panel ship
—
Community
Paid
Entry
pi-autoresearch extends the pi terminal agent with an autonomous optimization loop: the agent writes a change, runs a benchmark, uses Median Absolute Deviation (MAD) to filter out statistical noise, and either commits or reverts — then loops. No human in the loop. The cycle repeats until a time limit or convergence criterion is met. The technique was popularized by Karpathy's autoresearch concept for ML training, but pi-autoresearch generalizes it to any benchmarkable target. Shopify's engineering team ran it against their Liquid template engine and reported 53% faster parse/render with 61% fewer allocations after an overnight run — changes their team had been unable to land manually in months. The MAD-based noise filtering is the key innovation: it prevents the agent from chasing benchmark noise and reverting valid improvements. The project has spawned an ecosystem: pi-autoresearch-studio adds a visual timeline of accepted/rejected edits, openclaw-autoresearch ports the concept to Claw Code, and autoloop generalizes it to any agent that supports a run/test interface. At 3,500 stars, it's one of the most-forked pi extensions.
Reviewer scorecard
“This is the right move for LM Studio. The desktop client is already excellent and Locally AI's Core ML integration is the best iOS inference wrapper available. Combining Grondin's Apple-native work with LM Studio's model management and server mode could produce something genuinely special for local AI power users.”
“I ran this against my GraphQL resolver layer over a weekend and got 31% latency reduction with zero manual intervention. The MAD filtering is the real innovation — previous attempts at autonomous optimization would thrash on noisy benchmarks. This one doesn't.”
“Acquisitions in open-source adjacent tools often mean the indie app loses what made it great. Locally AI was clean and opinionated; LM Studio is powerful but has more surface area. There's real risk the mobile experience gets de-prioritized once the acquisition honeymoon ends.”
“Shopify's results are impressive, but they're also running this on a well-tested, stable codebase with comprehensive benchmarks. On a typical startup codebase with flaky tests and incomplete benchmarks, this will confidently optimize the wrong things. Benchmark quality gates the whole approach.”
“The race to own the local AI client layer is just beginning. LM Studio is positioning itself as the VLC of AI — runs everything, everywhere, free. If they nail the cross-device sync story (shared model library, shared chats), they become the default for privacy-first AI.”
“This is the earliest glimpse of AI that genuinely improves software without a human in the loop. When benchmarks exist, the agent is a better optimizer than humans — it's tireless, statistically rigorous, and immune to sunk-cost reasoning. Performance engineering as a discipline is about to change.”
“Being able to run the same model on my MacBook and iPhone with the same interface is a genuine quality-of-life win. I use local models for confidential creative writing and the iOS gap has always been frustrating. This closes it.”
“The framing here is very backend/systems. I tried running it on a React component library to reduce render cycles and got a mess — the agent optimized for the benchmark at the expense of code readability. Fine for systems code, wrong tool for UI work.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.