LvcidPsyche/auto-browser

MCP Browser & Automation

Give your AI agent a real browser with human‑in‑the‑loop control, offering reusable auth profiles, approvals, audit trails and local‑first deployment.

Track releases GitHub

Python Latest v1.1.3 · 1d ago Security brief →

Features

MCP‑native browser control plane for LLM agents and operators
Human takeover via noVNC live sessions when web flows become brittle
Reusable named authentication profiles to avoid repeated logins
Local‑first deployment with Docker Compose or GitHub Codespaces
Built‑in safety features: approvals, PII scrubbing, audit trails and Witness receipts

Recent releases

View all 20 releases →

No immediate action

v1.1.3 Breaking risk 1d

Background-task reliability fix

Open

Review required

v1.1.2 Bug fix 2d

Auth Breaking upgrade

ASGI scope path handling fix

Open

Config change

v1.1.1 Breaking risk 17d

Auth

Policy preset rename

Open

v1.1.0 New feature 25d

Notable features

Modular controller architecture with app factory, focused routers, middleware modules, browser services, action pipeline, and MCP tool packs.
MCP-native improvements: tool annotations, resource listing/subscriptions, harness candidate tools, per-tool metrics, and response metadata.
Governed skill induction foundation including contracts, tamper-checked traces, verifier adapters, staged candidates, signed provenance, review-only graduation, and skill drift monitoring.

Full changelog

Auto Browser v1.1.0

This release turns the refactor work into the new stable architecture line.

Highlights

Modular controller architecture: app factory, focused routers, middleware modules, browser services, action pipeline, and MCP tool packs.
MCP-native improvements: tool annotations, resource listing/subscriptions, harness candidate tools, per-tool metrics, and response metadata.
Governed skill induction foundation: contracts, tamper-checked traces, verifier adapters, staged skill candidates, signed provenance, and review-only graduation.
Skill drift monitoring for re-checking staged candidates and marking degraded skills.
Release hardening: route failure logging, JSON-safe descriptor cache, deep health packaging fallback, startup fail-closed router registration, safer drift artifact reads, and stable deep-health error responses.

Validation

Local release audit passed with lint, mock evals, fixture evals, pip-audit, npm audit, wheel builds, coverage gate, compile checks, and tracked-file secret scan.
Local controller suite: 462 passed, 2 skipped, 150 subtests passed.
GitHub CI, CodeQL, and Dependency Graph passed on main commit 2c5fa58.
GitHub code scanning and Dependabot both report 0 open alerts on main.

View release on GitHub

v1.0.6 New feature 25d

Security fixes

Hardens controller surface: exact‑match dashboard bearer exemptions, governed‑only page JavaScript evaluation, webhook SSRF validation, trace redaction, and signed staged skill artifacts

Notable features

Stage 0 convergence harness for Agent Skill Induction with task contracts, tamper‑checked traces, deterministic verification, budgeted iteration and staged skill induction
UV/Stagehand verifier adapter boundaries, ensemble verifier plumbing, benchmark scaffolds and a deterministic example contract
Full‑profile MCP harness tools for convergence runs and staged candidate review

Full changelog

v1.0.6

Highlights

Ships the Stage 0 convergence harness for Agent Skill Induction: task contracts, tamper-checked traces, deterministic verification, budgeted iteration, and staged skill induction.
Adds UV/Stagehand verifier adapter boundaries, ensemble verifier plumbing, benchmark scaffolds, and a deterministic example contract.
Adds full-profile MCP harness tools for convergence runs and staged candidate review.
Hardens the controller surface: exact-match dashboard bearer exemptions, governed-only page JavaScript evaluation, webhook SSRF validation, trace redaction, and signed staged skill artifacts.
Improves operator diagnostics with /version, clearer harness-unavailable errors, and better gateway/cron logging.