
DevTrack
io.github.sraj0501由 GitHub 帳號 sraj0501 發布v3.2.0更新於 Nov 4, 2026
Read local work context and published Sage command knowledge over MCP.
概覽
DevTrack 的唯讀 MCP 伺服器讓助理讀取本機 Git 工作脈絡、工單對應、待審動作、日報脈絡與 Sage 指令知識。
- 可以做什麼
- 讀取目前工作脈絡:工單脈絡、已觀測的提交與工作項目對應
- 檢視暫存待審的動作佇列與每日結束報告脈絡
- 讀取語音資訊與已發布的 DevTrack Sage 指令知識
- 全部為唯讀存取:助理無法核准動作或修改 DevTrack 資料
- 適用情境
- 適合已用 DevTrack 觀察 Git 工作並對應到工單的人,希望助理在編輯器中直接回答目前工單、提交、待審更新與日報相關問題。
- 執行需求
- 以本機桌面程序執行(Windows、macOS 或 Linux),透過 MCP 安裝包安裝;需要 Git。須在目標儲存庫完成 DevTrack 設定並保持執行,使用 DevTrack 的 MCP 設定指令加入伺服器後重新載入助理。未宣告驗證、環境變數或標頭。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 DevTrack,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
DevTrack
Never write a standup again.
DevTrack watches your Git work, connects it to tickets, and prepares status updates and end-of-day reports in the background. It is local-first, offline-capable, and stages outbound actions for your review.
[GitHub Release] [Platforms] [License]
Website and documentation
Mogrov owns the DevTrack landing page, wiki, privacy page, and installer scripts. This repository owns the product code and GitHub releases.
What DevTrack does
- Observes commits without interrupting or replacing normal Git commands.
- Reports completed work without tracking hours or time spent per task in the v3.3.0 development line.
- Maps ticket-named branches such as
feature/AUTH-42-refresh-tokento work items. - Builds reviewable ticket updates and end-of-day reports from the work already completed.
- Keeps its client-side source of truth in local SQLite and uses Ollama by default for local AI.
- Shares current work and DevTrack Sage knowledge with compatible assistants through ten read-only MCP tools.
Nothing is posted merely because DevTrack generated it. PM updates, transitions, and deliveries are placed in a pending-actions queue before delivery; configured earned auto-approval rules can advance eligible actions. Anonymous telemetry is also opt-in and disabled by default.
Get started
DevTrack supports Windows, macOS, and Linux. Git is required. The core Go client, SQLite storage,
Git observation, queue, and MCP features do not require Python or an AI model. Managed AI features
add uv, PostgreSQL, and an LLM provider; Ollama is the default.
1. Install
Use the Mogrov download link, or install the latest stable release directly:
Linux or macOS
Windows PowerShell
Manual binaries and checksums are available on GitHub Releases.
Stable v3.2.0 retains the former time-tracking behavior. The fixes and removal are on dev at
860b91b, prepared for v3.3.0; rolling development builds use dev-<commit>. A push to dev does
not upgrade an installed binary or publish a new stable release. See the
development release notes and qualification plan.
2. Configure a repository
Run setup from the Git repository you want DevTrack to observe:
The setup wizard configures the operating mode, repository, LLM, identity, and optional PM
integration. Choose none for the PM integration when evaluating the local-only path. Managed mode
requires PostgreSQL for the optional Python service; Go-native features remain available while that
service and the model are being prepared.
Managed mode starts the local Python server for AI-written ticket comments, EOD narratives,
Boardroom reviews, planning, and voice personalization. External mode does not start Python: point
DEVTRACK_SERVER_URL at a separately operated Python/PostgreSQL server for those features. With no
server reachable, commit capture, deterministic ticket mapping, local history, queue, and MCP still
work; generated reports and other server-backed features are unavailable. Model failures on a
reachable server fall back to raw or templated wording. External mode skips automatic first-run
voice mining. See the LLM guide.
3. Try the workflow
Use a ticket-named branch and commit normally:
queue lets you inspect staged actions before approving anything. See the
Quick Start for the complete first-run walkthrough.
In the development line, capture enumerates unseen commits across local branch tips, so rapid commits and switching branches during processing are included. Keep the daemon running: existing history is seeded at startup, and catch-up for commits made while it was stopped is not guaranteed.
devtrack work start AUTH-42 selects fallback ticket context; work stop clears it and work status
shows it. These commands do not start or stop timers. devtrack work report generates a commit-based
EOD report through the configured server.
Incidents, stories, bugs, and tasks all map by their work-item reference: for example, a Jira
incident hotfix/OPS-123-restore-login, Azure DevOps story feature/ADO-456-add-export, or
GitHub issue fix/GH-42-handle-timeout. The PM system supplies the item type; the branch kind
does not. A canonical branch wins over an explicit commit reference, which wins over selected
ticket context. Run devtrack ticket convention and devtrack ticket check <branch> to inspect
the rule, or devtrack ticket link <commit-hash> <ticket-ref> to correct an observed mapping.
See work-item and ticket mapping for configuration, conflicts, and examples.
devtrack eod status and devtrack eod show read the latest report across local and server history.
devtrack queue list --all shows recent actions from both stores. Server actions use IDs such as
server:123: pass that full ID to queue approve, queue reject, or queue edit. Bare numeric IDs
address local actions. An unavailable server is reported explicitly.
Agent memory and DevTrack Sage
Add DevTrack's read-only MCP server to the current project:
Reload your MCP-capable assistant after setup. It can then read current ticket context, commits, pending actions, EOD context, voice information, and published Sage knowledge. MCP cannot approve actions or modify DevTrack data.
DevTrack Sage captures useful command activity from supported coding harnesses and turns repeated work into searchable local Markdown knowledge:
Learn more in MCP and Agent Memory and DevTrack Sage.
Where to go next
Contributors and maintainers can start with the repository documentation map and architecture.
Privacy
The default Go, SQLite, and Ollama path stays local. External PM systems, delivery channels, and
cloud LLMs receive data only when configured for the corresponding operation. Telemetry remains off
until explicitly enabled with devtrack telemetry on. Read the full
privacy guide before enabling external services.
License
DevTrack uses the DevTrack Community License: free for personal use and teams of up to 10 users; larger teams and hosted use require an enterprise license.
來源:README.md,提交 c2fbb93
工具
0版本歷史
2- v3.2.0最新Oct 21, 2026
- v3.1.1Sep 16, 2026
評分
已滿足適用檢查項的 40%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分
請在儲存庫或註冊中心條目中宣告授權條款。