Project roadmap

Roadmap

This page separates published releases from work in progress, proposals still being evaluated, and directions intentionally kept out of scope. Shipped lists the latest GitHub releases, each linked to its release notes. Work in progress — including changes merged in the repository but not yet released — appears under Underway. When the live feed is unavailable, static summaries stand in; the install page and homepage identify the latest published version.

Work grouped by status

Browse open issues

Shipped

1 item

  • v0.8.45

    Moonshot/Kimi provider support, API-key setup guidance, provider-surface sync, and current Windows install/runtime guidance

Underway

5 items

  • VS Code extension

    The repository ships an early local-runtime companion: terminal launch, health checks, read-only thread summaries, and restore-point browsing. Full chat and editor actions are not part of this slice.

  • Memory typed store

    The native store has shipped: Markdown is the durable source of truth, with a rebuildable SQLite FTS5 index over it. Graph-structured agent memory and multi-signal recall are still ahead

  • Feishu / Lark bot

    First long-connection bridge over the runtime API shipped; richer chat features underway

  • Chinese-market & i18n

    Locale-aware UI, platform refinements, region-specific search backends

  • Hugging Face model discovery + Model Lab

    Browse, download, and manage models from Hugging Face Hub directly in the TUI

Considered

5 items

  • Workrooms

    Durable, addressable agent-work threads over the Runtime API and user surfaces

  • Exa web-search backend

    Bundled alternative to the existing DDG + Bing path

  • Homebrew core formula

    Tap exists; pursuing homebrew-core inclusion

  • Native Windows installer

    MSI installer; the WinGet package, Scoop manifest, and NSIS setup already ship

  • Unsloth / NeMo / Arcee fine-tune integration

    One-click fine-tuning workflows backed by Unsloth, NVIDIA NeMo, and Arcee toolkits

Ruled out

5 items

  • Silent or content-level telemetry

    Codewhale counts anonymous usage by default, discloses it at first launch, and keeps every opt-out. What stays ruled out: conversations, code, prompts, files, model content, credentials, per-turn or per-tool timelines, collection hidden from the user, and any third-party ad or analytics SDK in the runtime binary. A selected hosted provider still receives the context required for its model turn; loopback routes can keep inference local.

  • Mandatory hosted relay for local sessions

    The local runtime and bring-your-own-provider routes continue to work without sending sessions through a Codewhale service

  • Required account for the local runtime

    Installing and running Codewhale locally requires no account

  • Sponsored model promotion

    Model picker stays neutral — no paid placement

  • Public share links for local sessions

    The retired share-link direction is not coming back; any future sharing design starts fresh.

Open model platform · ideas, not started

3 items

  • Community model registry

    Discover, share, and rate community fine-tuned models with reproducible recipes

  • One-click deploy

    Deploy any model to RunPod, Replicate, or your own infra with a single command

  • Model evaluation dashboard

    Transparent, reproducible comparisons across providers, quantization levels, and hardware

Keep roadmap decisions in the open.

Use issues for bugs and well-scoped feature requests, Discussions for ideas that need shaping, and pull requests for concrete changes with tests or documentation. Verification across languages, platforms, and providers helps maintainers judge priority.