MIT-licensed, local-first Python tool that turns profilers, benchmarks, and traces into bounded evidence an agent can act on — run via `uv` or as an MCP server for DeepSeek Harness.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-01
License
MIT
01What can it help you accomplish?
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
02How to install into DeepSeek Harness
Prerequisites
- 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
Installation steps
- 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)
Verify the integration
- Print the stdio client configuration with `flameox setup` to confirm the MCP wiring
- Confirm capabilities are discovered for your intent before analyzing or capturing
Rollback
- 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 integration and capability boundaries
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`
04Who is it for? When not to use it?
Good for
- 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
Not for
- 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.
05Compatibility, maintenance and safety notes
- 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)
06Frequently asked questions
How do I connect flameox to DeepSeek Harness?
Run the MCP server with `uv run flameox mcp serve --project-root "$PWD"` (the server fixes its project root at startup); `flameox setup` prints the equivalent stdio client configuration for your agent.
What does flameox actually do?
It coordinates profilers, benchmark tools, trace processors, and direct local targets so an agent gets a short path from an explicit native artifact or live command to bounded evidence, while keeping preservation optional.
Do I need to initialize a workspace or config file?
No. Version 0.2 is a clean break: there is no workspace to initialize, no `flameox.toml`, and no SQLite control plane — you pass exact artifact paths and formats straight to `analyze`.
Is my data sent anywhere?
No. Flameox is local-first; evidence stays in a bounded process-lifespan runtime, with optional session scratch/cache and explicit preservation to `<project>/.flameox` only when you request it.
07Related DSH workflows
ruflo
by ruvnet
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
reactive-resume
by reactive-resume
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
everos
by evermind-ai
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
openpencil
by zseven-w
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.
08Data and sources
Bounded local runtime evidence for coding agents.
Flameox coordinates profilers, benchmark tools, trace processors, and direct
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-01. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.