Issue 2026-06-21
v0.8.61
CodeWhale
any model, open models first
Section 04 · 路线

Roadmap 路线图

What's confirmed, what's being weighed, what's been ruled out. Anything not on this page is fair game for discussion.

Shipped 已完成

1 items
  • 01
    v0.8.45
    Moonshot/Kimi provider support, API-key setup guidance, provider-surface sync, and current Windows install/runtime guidance

Underway 进行中

5 items
  • 01
    VS Code extension
    Phase 0 shipped — terminal launch, runtime health, read-only Agent View; deeper editor integration next (#461–#463)
  • 02
    Memory typed store
    SQLite + FTS5 backend with graph-structured agent memory and multi-signal recall (#534–#536)
  • 03
    Feishu / Lark bot
    First long-connection bridge over the runtime API shipped; richer chat features underway (#757)
  • 04
    Chinese-market & i18n
    Locale-aware UI, platform refinements, region-specific search backends (#755)
  • 05
    Hugging Face model discovery + Model Lab
    Browse, download, and manage models from Hugging Face Hub directly in the TUI

Considered 考虑中

5 items
  • 01
    Web UI / share-link mode
    Local web interface over serve --http; curated, generated static share links (#471, #481)
  • 02
    Exa web-search backend
    Bundled alternative to the existing DDG + Bing path (#431)
  • 03
    Homebrew core formula
    Tap exists; pursuing homebrew-core inclusion
  • 04
    Native Windows installer
    MSI / WinGet; Scoop manifest already ships
  • 05
    Unsloth / NeMo / Arcee fine-tune integration
    One-click fine-tuning workflows backed by Unsloth, NVIDIA NeMo, and Arcee toolkits

Ruled out 暂不考虑

4 items
  • 01
    Telemetry / phone-home
    The agent runs on your machine — what happens there stays there
  • 02
    Hosted SaaS dashboard
    The terminal IS the dashboard; the website is informational only
  • 03
    Required login / accounts
    Bring your own API key, that's it
  • 04
    Sponsored model promotion
    Model picker stays neutral — no paid placement

Open model platform 开放模型平台

3 items
  • 01
    Community model registry
    Discover, share, and rate community fine-tuned models with reproducible recipes
  • 02
    One-click deploy
    Deploy any model to RunPod, Replicate, or your own infra with a single command
  • 03
    Model evaluation dashboard
    Transparent, reproducible comparisons across providers, quantization levels, and hardware
参与塑造

Want to shape this list?

The roadmap reflects what the maintainer plans to do — but PRs and well-argued discussions reorder it constantly. Show up with a working prototype and watch "Considered" become "Underway".