採 MIT 授權、本地優先的 Python 工具，將效能分析、基準測試與追蹤轉化為代理可據以行動的邊界化證據——透過 `uv` 執行，或作為 DeepSeek Harness 的 MCP 伺服器使用。
DSH 整合
原生執行環境
作者聲明
安全稽核
未稽核
最後核實
2026-09-01
授權條款
MIT
01它能幫你完成什麼？
Trace and profile hotspots in application and native code, GPU kernels, and inference stacks from a coding agent
bounded, inline runtime evidence — profiler / benchmark / trace output — without a durable control plane
Developers and coding agents (including DeepSeek Harness) that need local-first performance evidence
Capture runtime evidence from a live command or an existing native artifact inside an agent loop
process-lifespan evidence with optional preservation to `<project>/.flameox`
Performance engineers who want agents to burn down hotspots with explicit, auditable evidence
02如何將外掛接入 DeepSeek Harness？
先決條件
- Python project managed with `uv` (the README installs extras via `uv sync` / `uv run`)
- A local target: an existing native artifact (with its exact path and format) or a live command to benchmark
安裝步驟
- 01
Sync the optional extras you need: `uv sync --extra dev --extra memory --extra trace --extra cpu`
- 02
Discover capabilities for an intent: `uv run flameox capabilities discover --intent "CPU hotspots"`
- 03
Analyze an existing artifact: `uv run flameox analyze artifact.preview /absolute/path/to/artifact.json`
- 04
Or capture live evidence: `uv run flameox capture --provider direct -- python benchmark.py`
- 05
Run the MCP server for an agent: `uv run flameox mcp serve --project-root "$PWD"` (the MCP server fixes its project root at startup)
驗證整合成功
- Print the stdio client configuration with `flameox setup` to confirm the MCP wiring
- Confirm capabilities are discovered for your intent before analyzing or capturing
復原
- Stop the `flameox mcp serve` process and drop the `--project-root` MCP config printed by `flameox setup`
- Version 0.2 has no SQLite control plane, so removing `<project>/.flameox` leaves no stale state
03DSH 整合程度與能力邊界
MCP server (`flameox mcp serve`) exposing profiler / benchmark / trace capabilities to DeepSeek Harness agents; also runnable as direct `uv` CLI commands
Capabilities discovery
an intent such as "CPU hotspots"→the matching profiler / benchmark / trace capabilities for an agent to use
Artifact analysis
an explicit native artifact path (e.g. artifact.preview with exact path and format)→bounded inline evidence for the supplied artifact
Live capture
a direct target command (e.g. `python benchmark.py`) via `--provider direct`→bounded runtime evidence from the live command
writes optional session scratch/cache and, on explicit preservation, to `<project>/.flameox`
04適合誰？何時不該用？
適合
- Developers and coding agents (including DeepSeek Harness) that need local-first performance evidence
- Performance engineers who want agents to burn down hotspots with explicit, auditable evidence
不適合
- Version 0.2 is a clean break: old `.diagnostics` state is not migrated, and there is no workspace to initialize, no `flameox.toml`, and no SQLite control plane.
05相容性、維護與安全提醒
- Version 0.2 is a clean break: old `.diagnostics` state is not migrated, and there is no workspace to initialize, no `flameox.toml`, and no SQLite control plane.
- Flameox is local-first: evidence stays in a bounded process-lifespan runtime, and preservation to `<project>/.flameox` is optional and only happens on explicit request.
MIT · actively maintained (latest release v0.1.15, 2026-08-30)
06常見問題
如何將 flameox 連線到 DeepSeek Harness？
使用 `uv run flameox mcp serve --project-root "$PWD"` 啟動 MCP 伺服器（伺服器在啟動時固定其專案根目錄）；`flameox setup` 會印出等價的 stdio 用戶端組態供代理使用。
flameox 具體做什麼？
它協調效能分析器、基準測試工具、追蹤處理器與直接本地目標，讓代理能從明確的原生成品或即時命令快速取得有邊界的證據，且結果儲存是可選的。
需要初始化工作區或組態檔嗎？
不需要。0.2 版是一次全面重寫：無須初始化工作區、沒有 `flameox.toml`，也沒有 SQLite 控制面——您直接將精確的成品路徑與格式傳給 `analyze` 即可。
我的資料會被上傳嗎？
不會。flameox 是本地優先的；證據保留在生命週期受控的執行時期中，僅在您明確要求時，才會將選用的工作階段快取儲存至 `<project>/.flameox`。
07相關的 DSH 工作流程
rea
作者 morluto
用智慧體逆向工程一切，從應用行為一直到原生二進位制。
ruflo
作者 ruvnet
原版智慧體元框架（meta-harness）：支援多智慧體叢集部署、自主工作流編排與對話式 AI 系統構建，內建自適應記憶、自學習智慧與 RAG 檢索，原生整合 Claude Code / Codex / Hermes 等大量工具。
reactive-resume
作者 reactive-resume
開源簡歷製作外掛，強調隱私保護，支援自定義、可移植和自託管。
everos
作者 evermind-ai
為所有 AI 智慧體提供的便攜統一記憶層，本地優先、Markdown 原生、資料歸使用者所有，跨應用與工作流自進化。
08資料與來源
Bounded local runtime evidence for coding agents.
Flameox coordinates profilers, benchmark tools, trace processors, and direct
此頁面根據專案公開文件、儲存庫中繼資料與 DSH Plugins 的結構化解析所產生；最後核實於 2026-09-01。發現錯誤？提交更正。
最佳 DeepSeek Harness 外掛
從全目錄挑出的 12 個值得優先安裝的外掛，涵蓋各個分類。