Releases: vercel-labs/agent-browser
Releases ยท vercel-labs/agent-browser
v0.29.0
New Features
- Sandbox package - Added
@agent-browser/sandboxwith shared, Eve, and Vercel Sandbox helpers, example projects, and docs for running agent-browser in hosted sandbox environments (#1465)
Improvements
- Updated sandbox release flow so the new package stays version-synced with the CLI release and publishes from the correct workspace path (#1465)
- Reflowed documentation prose across the README, docs site, examples, and skills so Markdown and MDX wrap naturally in editors and renderers (#1466)
Contributors
v0.28.0
New Features
- MCP server - Added
agent-browser mcp, a stdio Model Context Protocol server with typed tools, paginated discovery, protocol negotiation, and startup tool profiles. The defaultcoreprofile keeps context small, while--tools allexposes full CLI parity and composed profiles such ascore,network,reactare supported (#1454) - Plugin system - Added out-of-process plugin support over the
agent-browser.plugin.v1stdio protocol, withplugin add/list/show/run, manifest discovery, npm and GitHub refs, credential providers, browser provider plugins, launch mutators, custom command capabilities, config and env registry support, and capability-scoped policy gates (#1452)
Infrastructure
- Added context footprint eval coverage for CLI skills, MCP core, and MCP full-profile surfaces, plus MCP parity tests to keep tool behavior aligned with the CLI (#1454)
Contributors
v0.27.3
Bug Fixes
- Fixed Windows ARM64 installs by falling back to the Windows x64 binary during postinstall, avoiding failed downloads for a native ARM64 artifact that is not published (#1269)
Contributors
v0.27.2
Bug Fixes
- Fixed click reliability by scrolling off-viewport elements into view before resolving coordinates, handling JavaScript dialogs promptly, recovering mouse state after dialog-opening clicks, and detecting click interception by overlays before dispatching input (#1432, #1434)
- Fixed frame-scoped selectors and waits so CSS-selector actions and
waitrespect the selected iframe, including cross-process iframes, with translated click coordinates (#1432) - Fixed wait timeout handling so the documented 25s default is used,
--timeoutis honored across wait variants, and long waits receive an appropriate client read budget (#1432) - Fixed agent-facing form commands so
find labelmatchesaria-labelandaria-labelledby,selecterrors when no option matches, andtypeparses--clearand--delayinstead of typing them as text (#1432)
Improvements
- Cut warm CLI command latency from about 150ms to about 1ms by removing the unconditional daemon settle sleep and retrying once when a stale daemon socket is discovered (#1432)
- Extended daemon respawn and retry handling to batch commands so batches recover from a daemon exit after the initial liveness check (#1432)
Infrastructure
- Pinned GNU Linux release artifacts to glibc 2.28 with zigbuild, added a release guard for newer GLIBC symbols, and aligned Docker release helpers with the pinned target (#1417)
Contributors
v0.27.1
v0.27.0
New Features
- React introspection - First-class React DevTools integration with new
react tree,react inspect <fiberId>,react renders start|stop, andreact suspensecommands for full component-tree visibility, per-fiber props/hooks/state inspection, render profiling with mount/re-render counts and change details, and Suspense boundary classification with root-cause grouping and recommendations. React DevTools hook is vendored (MIT) and embedded in the binary with zero runtime dependencies (#1257) - Web Vitals - New
vitals [url]command that reports Core Web Vitals (LCP, CLS, TTFB, FCP, INP) plus React hydration phases for any page (#1257) - SPA navigation - New
pushstate <url>command for client-side SPA navigations without a full page load (#1257) - Init scripts and feature flags - New
--init-script <path>flag (repeatable; envAGENT_BROWSER_INIT_SCRIPTS) to register scripts before first navigation, and--enable <feature>flag (repeatable; envAGENT_BROWSER_ENABLE) for built-in init scripts such asreact-devtools(#1257) - Network route resource type filter -
network routenow accepts--resource-type <csv>to filter intercepted requests by CDP resource type (#1257) - cURL cookie import -
cookies set --curl <file>auto-detects JSON, cURL, and Cookie-header formats for bulk cookie import (#1257) - Dashboard proxy support - The observability dashboard now works from proxied origins via a same-origin proxy, enabling deployment behind reverse proxies and path-based routing (#1111)
Bug Fixes
- Fixed
doctorcommand generating duplicate check ids when called multiple times in the same process (#1330)
Infrastructure
- Switched npm publishing to trusted publishing via GitHub Actions OIDC, removing the need for manually managed npm tokens (#1273)
Contributors
v0.26.0
New Features
doctorcommand - Addedagent-browser doctorfor one-shot diagnosis of an install. Checks environment, Chrome, running daemons, config files, security, providers, and network connectivity; auto-cleans stale daemon sidecar files on every run; and performs a live headless launch test. Supports--offlineto skip network probes,--quickto skip the launch test,--fixfor opt-in repairs (install missing Chrome, close version-mismatched daemons, prune expired state files), and--jsonfor structured output (#1254)- Stable tab ids and labels - Tabs now have stable string ids like
t1,t2,t3that don't shift when other tabs close or popups appear. Tabs can be created with a memorable label viatab new --label <name> [<url>], and labels are interchangeable witht<N>ids everywhere a tab ref is accepted (tab <id|label>,tab close <id|label>). Bare-integer input is rejected with a teaching error so agents can't mistake stable handles for positional indices (#892, #1249, #1250) coreskill - Renamed the built-inagent-browserskill tocoreand replaced its ~40-line discovery stub with a ~420-line usage guide covering the core snapshot-ref-act loop, reading, interacting, waiting, common workflows, troubleshooting, and global flags.agent-browser skills get corenow returns content agents can use directly;--fulladds references and templates. Added ahidden:frontmatter flag so the originalagent-browserstub stays reachable fornpx skills adddiscovery without pollutingskills list(#1253)- JSON Schema for config files - Added
agent-browser.schema.jsondescribing every config option with types and descriptions, enabling IDE autocomplete and validation when referenced via$schemainagent-browser.jsonor~/.agent-browser/config.json. The schema is served from the docs site athttps://agent-browser.dev/schema.json(#1242, #1248)
Bug Fixes
- Fixed
--state/AGENT_BROWSER_STATEnot actually loading saved browser state (cookies and localStorage) at launch. The flag had been fully plumbed through parsing, env propagation, and validation since the native Rust rewrite, but the load step was never wired up. Storage state now loads after launch across all four paths: explicit launch, auto-connect, provider, and local Chrome (#1241)
Documentation
--helpoutput now shows the skills section first so agents discoverskills get core(the canonical usage guide) before the core command list (#1251)
Contributors
v0.25.5
Bug Fixes
- Fixed
--auto-connectCDP discovery preferring HTTP endpoint discovery over the DevToolsActivePort websocket path, which could fail on some setups. The CLI now reads the websocket path from DevToolsActivePort first and only falls back to HTTP discovery (#1218) - Fixed recording context viewport not inheriting the active viewport dimensions, causing recordings to use default resolution instead of the configured viewport (#1208)
- Fixed
get boxandget stylesprinting no data in text mode (#1231, #1233) - Fixed active page changing when closing or removing earlier tabs. The previously focused page is now preserved correctly (#1220)
Contributors
v0.25.4
New Features
skillscommand - Addedagent-browser skillscommand for discovering and installing agent skills, with built-in evaluation support for testing skills against live browser sessions (#1225, #1227)
Bug Fixes
- Fixed custom viewport dimensions not being used in streaming frame metadata and image resolution (#1033)
- Fixed
--ignore-https-errorsnot being re-applied to recording contexts, causing TLS errors during screen recordings (#1178) - Fixed duplicate option numbering in the auth skill documentation (#1161)
Documentation
- The docs site header now dynamically fetches the GitHub star count (#1202)
Contributors
v0.25.3
Bug Fixes
- Fixed hidden radio/checkbox inputs missing from snapshot refs when a
<label>wraps adisplay:none<input type="radio">or<input type="checkbox">. Chrome excludes these inputs from the accessibility tree entirely, making it impossible for AI agents to identify radio buttons and checkboxes via refs. Hidden inputs inside elements are now detected during cursor-interactive scanning and their parent nodes are promoted to the correct role with proper name and checked state (#1085)
Documentation
- Added clickable heading anchors to the docs site, making it easy to link directly to any section (#1175)