AmberFlow
Browser automation middleware with frozen task execution, deterministic DOM signals, and DSH bridge tools.
Install
$ dsh plugin --profile <名称> add github:Johnly1986/AmberFlow # 仓库直装（见 README 附注：私有库需凭证）Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Executes browser flows via frozen step-by-step plans without dynamic re-planning
- Provides four DeepSeek Harness agent tools: amberflow_apps, amberflow_run, amberflow_learn, and amberflow_plan
- Evaluates sub-goal step completion through strict DOM and URL signals rather than model assertions
- Offers hybrid decision evaluation prioritizing explicit target hints, falling back to local ONNX or remote providers (token-plan, Bailian, JevK5)
- Includes interactive demonstration recording (learn) to induce invariants and signals
- Configures provider endpoints and API keys via DSH plugin settings UI or local rc files
Useful For
- Automating complex, multi-step web scraping and transactional workflows reliably inside DeepSeek Harness
- Recording human browser navigation via CDP/headful modes to automatically generate reproducible automation recipes
- Running cost-efficient web agent tasks with strict zero-hallucination data bag (slots) constraints
Who It Fits
- DeepSeek Harness developers automating brittle browser journeys
- Automation engineers building deterministic, signal-verified web agent tasks
- Teams seeking repeatable browser automation with local ONNX fallbacks instead of token-heavy loops
Documented Limitations
- Requires Node.js >= 22.6 and Playwright Chromium installation
- Headful browser execution on headless servers requires Xvfb or CDP remoting
- Local neural decision fallback requires downloading ~1.7GB ONNX model weights or configuring external provider endpoints
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 4 runtime, 3 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as Apache-2.0.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Johnly1986/AmberFlow
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- b928ef2 · 2026-10-25
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 1GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-25
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Persistent multi-model agent teams with dynamic DAG orchestration, run monitoring, and token insights for DeepSeek Harness.
View plugin →Native SQLite-backed task management and project board bundle with Web UI and Agent workflow tools for DeepSeek Harness.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed security.
View plugin →Agent-native multi-market trading terminal and quantitative research plugin bundle for DeepSeek Harness.
View plugin →