Browserbase
Cloud browser infrastructure for AI agents. Headless Chromium sessions with persistent cookies, localStorage, session recording — agent workflows carry state across runs. Memory at the session/automation tier rather than conversational.
At a glance
- Type
- Programmatic session persistence (dev infra)
- Tier
- T1
- Section
- Browser-agent memory
- Created
- 2024-06
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Free + paid
- Funding
- $40M total $300M val Series B · 2025-04
Taxonomy
- storage
- file
- retrieval
- extraction-pull
- persistence
- session
- update
- overwrite
- unit
- episode
- governance
- inspectable
- conflict
- none
When to use
Optimised for: programmatic browser session persistence
Anti-fit: not for end-users; developer infrastructure only
Pros & cons
Pros
Most developer-friendly path to remote browser agents — memory is structured around session replays, not chat history.
Cons
Infrastructure-tier product; not useful directly to end users without an agent layer on top.
Claims & capabilities
$40M Series B (June 2025) at $300M valuation. $67.5M total. 50M+ sessions in 2025. 1,000+ paying customers.
Technical surface
- API surface
- REST, SDK: Python, JS/TS
- Backend storage
- custom
- Deployment
- Managed-only
- Embedding model
- not applicable — browser sessions
- Multi-tenancy
- hard-isolation
- MCP
- native (first-party) — Browserbase MCP
- A2A
- searched not found
- OpenTelemetry
- searched not found
Compare Browserbase with…
Similar systems
Other browser-agent memory in the catalog, ranked by inbound references.
- Brave Leo T2
Privacy-focused integrated assistant. Memory is user-curated: explicit facts and preferences persist across all sessions, stored locally with no server retention. Agentic browsing experiment (Brave Nightly Dec 2025) takes multi-step actions inside sites referencing those preferences.
- Dia (Atlassian) T1
The Browser Company's AI-native browser; acquired by Atlassian for $610M (Sept 2025). Stores summaries and preferences locally; opt-in @history feature references up to 7 days of browsing as context. History/chats/bookmarks encrypted local-first.
- Fellou T1
Silicon Valley. Spatial agentic browser with explicit Agentic Memory layer learning from history and notes for instant recall of past research sessions. Operates on logged-in accounts (Quora, X, etc.); runs tasks while user is idle.
- Microsoft Edge Copilot Mode + Journeys T1
Copilot Mode (Oct 2025): Journeys groups related browsing across sessions into resumable project cards with AI summaries. Copilot Actions execute multi-step tasks inside the browser. Assistant can see all open tabs with permission and draws on history.
- Opera AI (formerly Aria) T2
Memory feature stores user-declared preferences and facts; injected into future prompts. Understands current tab content; manages open tabs contextually. Memory off by default, end-user controlled, stored alongside the prompt rather than the LLM.
- Perplexity Comet T1
AI-native Chromium-based browser. Assistant operates across tabs and sessions; persistent memory of preferences; multi-step agentic tasks without leaving the browser. Memory is opt-in and server-side; enterprise memory tier separately available.