keys-MiniMax-Code-CLI-Browser-Scroll-Context-Enhancement-Pack-with-Jev-Ultrafast-Integration

Validated enhancement pack for MiniMax Code CLI on arm64 DGX Spark + local GLM-5.3-EXL3: TUI scrollbar + context-meter patches, compaction repair for local vLLM, Jev Ultrafast + Playwright MCP browser integration, real usage ledger.

MiniMax Code CLI enhancement pack: continuous 25% context renewal, context progress meter, browser tooling, Syntra and djev-spark local decision integrations.

How it uses Jev

Component What it does Status --- --- --- patches/0001 Interactive scrollbar for the fullscreen transcript viewport (three-column grab target, thumb-centering drags) Validated on fork; upstream issue 217 patches/0002 Opt-in status-line context gauge ( Context ▕██████░░▏ 77% left ) with thresholds + minimal fallback Validated on fork; upstream issue 216 patches/0003 Continuous context renewal after 25% utilization, r…

Highlights

  • The compaction bug that kills long sessions on local vLLM is solved.
  • Real numbers, not claims. 266 calls / 23.8 M input / 177 K output tokens
  • arm64 honesty. No Google Chrome on arm64 Linux; the pack documents the

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to keys-MiniMax-Code-CLI-Browser-Scroll-Context-Enhancement-Pack-with-Jev-Ultrafast-Integration

Browse all
Browser & computer use
A browser agent that turns a single goal into a sequence of lightning-fast actions.
hermes-jev-skills project preview
Browser & computer use
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)
jev-frontend-qa project preview
Browser & computer use
Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.
open-spark-jev project preview
Benchmarks & research
Open-source, local decision models inspired by TypeSafe’s Jev and System One - built on Qwen3 for NVIDIA DGX Spark.
open-alternative-jev project preview
Jev alternatives & open source
Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks
jevmeter project preview
Applications
Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit
laya-browser-agent project preview
Benchmarks & research
Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwright/CDP, MCP-friendly.
jev-review (NiazMorshed2007) project preview
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
grok-bot-jev project preview
Agent tooling
Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples