{"slug":"mechanize","name":"Mechanize","website":"https://mechanize.work","tagline":"RL environments to automate software engineering, founded by ex-Epoch AI researchers","description":"Mechanize builds RL environments and 'boot camps' aimed at automating white-collar work, starting with software engineering agents. Founded by former Epoch AI leaders, it works with Anthropic on RL environments and is backed by investors including Nat Friedman, Daniel Gross, and Patrick Collison.","domains":["coding"],"locations":["San Francisco"],"founders":[{"name":"Tamay Besiroglu","xHandle":"tamaybes"},{"name":"Ege Erdil","xHandle":"EgeErdil2"},{"name":"Matthew Barnett","xHandle":"MatthewJBar"}],"teamSize":"51-100","funding":"~$9.1M (reported)","raising":null,"founded":2025,"notable":"Offered $500K salaries to engineers building environments; publishes GBA Eval","entityType":"Pure-play commercial","canonicalUrl":"https://envindex.com/startup/mechanize","research":{"startupSlug":"mechanize","entityType":"Pure-play commercial","lastResearched":"2026-08-16","lastVerified":"2026-08-16","verificationStatus":"company-reported","confidence":"medium","sourceIds":["mechanize-gba"]},"sources":[{"id":"mechanize-gba","url":"https://www.mechanize.work/technical-blog/introducing-gba-eval/","title":"Introducing GBA Eval","publisher":"Mechanize","sourceType":"official","publishedAt":"2026-05-02","accessedAt":"2026-08-16","verificationStatus":"company-reported"}],"capabilityCatalog":{"startupSlug":"mechanize","reviewedAt":"2026-08-16","status":"cataloged","items":[{"name":"GBA Eval","kind":"Benchmark","summary":"A long-horizon coding eval in which agents build a Game Boy Advance emulator in Rust within 24 hours.","access":["Public / Open"],"sourceUrl":"/environments/gba-eval","sourceLabel":"EnvIndex catalog page","verificationStatus":"company-reported","lastVerified":"2026-08-16","artifactSlug":"gba-eval"}]},"artifacts":[{"slug":"gba-eval","name":"GBA Eval","ownerSlug":"mechanize","artifactType":"Benchmark","availabilityKind":"public-sample","access":["Public / Open"],"summary":"A long-horizon coding eval in which agents build a Game Boy Advance emulator in Rust within 24 hours.","description":"GBA Eval measures whether a coding agent can implement a Game Boy Advance emulator from scratch and compile it to WebAssembly. Mechanize describes it as one carefully graded task rather than a general-purpose software-engineering benchmark.","domains":["coding","long-horizon"],"capabilities":{"long-horizon":"yes","code-execution":"yes","sandboxed":"unknown","deterministic-reset":"unknown"},"taskCount":1,"verifierType":"Programmatic tests plus deterministic gameplay replay","firstReleased":"2026-05-02","lastVerified":"2026-08-16","verificationStatus":"company-reported","confidence":"high","links":[{"label":"Technical description","url":"https://www.mechanize.work/technical-blog/introducing-gba-eval/","kind":"official"},{"label":"Benchmark and leaderboard","url":"https://gbaeval.com","kind":"leaderboard"}],"sourceIds":["mechanize-gba"],"editorialNote":"Mechanize explicitly cautions that this single task is not a complete measure of general coding capability."}]}