Magnitude
Formerly an OSS AI browser-agent / natural-language E2E testing framework (YC 2025). The magnitudedev/magnitude repo now hosts an OSS local inference engine + desktop app that serves open models to agents.
Deprecated · Verified 2026-10-29 · fresh as of 2026-10-29 · 41 cited facts, 4 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- OSS browser-agent framework for web tests (YC) vendor fix
- Tier
- T3
- Section
- Computer-use & desktop agents
- Created
- 2025 (GitHub first commit) repo fix
- Latest release
- v0.x ongoing on GitHub repo fix
- License
- Apache-2.0 repo fix
- GitHub
- magnitudedev/magnitude — ~7.2k stars, last commit n/a (repo repurposed to inference engine) repo fix
- Pricing
- OSS free; cloud / enterprise on roadmap vendor fix
- Funding
- YC 2025 batch (~$500k standard YC) third-party fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source vendor fix
- Developer activity
- OpenRank 5.57 (12-mo avg 5.57) · 46 participants — 2026-09 third-party fix
When to use
Optimised for: Natural-language E2E tests as the unit of work
Anti-fit: Test-automation focus — not for autonomous operator-style tasks
Pros & cons
Pros
YC-backed; clean test-first framing; Apache 2.0 license.
Cons
Narrow scope (QA); small team; no funding disclosure beyond YC.
Claims & capabilities
YC-backed; OSS; visual-first agent loop (screenshots not just DOM)
Technical surface
- API surface
- CLI + Playwright-style API
- Backend storage
- Local Playwright state
- Deployment
- Self-hosted only — local library/desktop app
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- Single-tenant (local CLI)
- MCP
- no — not mentioned in repo
- A2A
- searched not found
- OpenTelemetry
- searched not found
Alternatives to Magnitude → live options ranked by shared design, licence, hosting and MCP support
Similar systems
Other computer-use & desktop agents in the catalog, ranked by inbound references.
- Browser Use T1
Python library that turns any LLM into a browser agent — extracts DOM into a structured representation the LLM can act on (rather than pure screenshot). Browser Use Inc. raised $17M seed Q1 2025 (Felicis); cloud product at cloud.browser-use.com. Project is one of the most-starred browser-agent OSS repos.
- Stagehand T1
Open-source browser-automation framework by Browserbase (TypeScript core plus Python and Go SDKs). Mixes Playwright-style code with natural-language act/extract/observe; pairs with Browserbase Cloud.
- Hyperbrowser T2
Cloud-hosted headless browser API tuned for AI agents — captcha solving, stealth mode, session recordings. Y Combinator S24; pitched as a faster / cheaper Browserbase alternative. Used as substrate by agents that need browser execution but don't want to run their own Chromium fleet.
- UI-TARS T2
ByteDance Seed's open-source GUI-agent foundation model — released Jan 2025; trained end-to-end on screenshot → action pairs. Comes with UI-TARS-Desktop (Electron app) that runs the model against the user's screen. SOTA on OSWorld at release; weights on HuggingFace.
- Anthropic Computer Use T1
Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.
- Skyvern T2
Open-source autonomous browser agent that uses computer vision + LLMs to navigate websites. Workflow-based: agents follow recorded plans that adapt to layout changes. Skyvern Inc. raised $4.5M seed (Sep-2024, Felicis lead). Self-hostable; cloud version on skyvern.com.
Sources (40 cited facts, 4 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is OSS browser-agent framework for web tests (YC) vendor
- What it does & what's distinct Formerly an OSS AI browser-agent / natural-language E2E testing framework (YC 2025). The… repo
- Claims / benefits YC-backed; OSS; visual-first agent loop (screenshots not just DOM) repo
- Modalities screenshots + DOM + natural-language tests vendor
- Created 2025 (GitHub first commit) repo
- Latest release v0.x ongoing on GitHub repo
- License Apache-2.0 repo
- GitHub magnitudedev/magnitude — ~7.2k stars, last commit n/a (repo repurposed to inference engi… repo
- Mindshare YC launch; niche but credible in QA/test-automation circles vendor
- Funding YC 2025 batch (~$500k standard YC) third-party
- Pricing OSS free; cloud / enterprise on roadmap vendor
- Data handling OSS = your infra vendor
- Deployment Self-hosted only — local library/desktop app repo
- HQ US (YC, San Francisco) third-party
- Code/weights release OSS — github.com/magnitudedev/magnitude repo
- API surface CLI + Playwright-style API vendor
- Backend storage Local Playwright state vendor
- Multi-tenancy Single-tenant (local CLI) vendor
- Encryption TLS for LLM calls; local state otherwise vendor
- Versioning Tests versioned in user repo (git) vendor
- Namespace primitives per-project (test suite) vendor
- MCP support no — not mentioned in repo repo
- Import / export Tests exportable as code / markdown vendor
- Validated verticals QA / end-to-end web test automation vendor
- Time to running <30min (npm install) repo
- Anti-fit Test-automation focus — not for autonomous operator-style tasks vendor
- Optimised for Natural-language E2E tests as the unit of work vendor
- Adjacent infrastructure Playwright; Anthropic / OpenAI APIs vendor
- Pros YC-backed; clean test-first framing; Apache 2.0 license. vendor
- Cons Narrow scope (QA); small team; no funding disclosure beyond YC. vendor
- Project & sources magnitude.run; github.com/magnitudedev/magnitude vendor
- commit-trajectory [{"ym":"2026-03","cum":328},{"ym":"2026-04","cum":632},{"ym":"2026-05","cum":719}] repo
- cost-pricing-model subscription vendor
- cost-last-verified 2026-06-29 vendor
- adoption-accelerator yc-s25 third-party
- architecture-deployment-locus local vendor
- licensing-bucket open-source vendor
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":100.73,"as_of":"2026-09","openrank_12mo":5.57,"openrank_current":5.57,"parti… third-party
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-29
- Homepage “https://magnitude.run/” → “https://magnitude.dev/”
- 2026-10-26
- Lifecycle first recorded as “superseded”
- License “Apache 2.0” → “Apache-2.0” source
- Deployment “Library / CLI; runs locally” → “Self-hosted only — local library/desktop app” source
- MCP support first recorded as “no — not mentioned in repo” source
Related systems
References (2)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: Playwright; Anthropic / OpenAI APIs
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: Playwright; Anthropic / OpenAI APIs