Flameox
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
- Transport
- Not stated
- Package
- —
- Registry id
- —
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
<img src="docs/assets/flameox-mascot-flamegraph.png" width="420" alt="flameox mascot: an ox with a flame graph between its horns"
Bounded local runtime evidence for coding agents.
Flameox coordinates profilers, benchmark tools, trace processors, and direct local targets. It turns an explicit artifact or command into bounded evidence while keeping durable preservation optional. The agent chooses hypotheses and experiments; Flameox records observed inputs, execution provenance, typed evidence, coverage, and limitations.
There is no workspace to initialize or project configuration to maintain. Pass exact artifact paths to analysis and an explicit argv plus absolute working directory to capture. Flameox does not search parent directories, edit project files, or provide a hosted service.
Quick start
Configure an MCP client with the global setup command:
npx flameox@latest setup
Setup detects supported clients and asks which configurations to update. For automation, select
clients explicitly, for example --client codex --yes or --all --yes; --dry-run reports the
paths and actions without writing. Setup preserves unrelated client configuration and does not
change project files. See the npm package guide for details.
For direct CLI use, pass exact artifact paths or an explicit command:
uvx flameox analyze artifact.preview /absolute/path/to/artifact.json
uvx flameox capture --provider direct --cwd "$PWD" -- python benchmark.py
To launch the stdio MCP server manually:
uvx flameox mcp serve
For local development, clone the repository, install its development dependencies, and inspect the available tools:
git clone https://github.com/morluto/flameox.git
cd flameox
uv sync --extra dev --extra memory --extra trace --extra cpu
uv run flameox mcp inspect
Evidence and storage
Analysis and unpreserved capture use bounded session scratch. Session analysis_id values expire
when evicted or when the server stops. Explicit preservation creates the user-level Flameox data
directory and stores native bytes and a canonical evidence bundle by SHA-256. Set
FLAMEOX_DATA_DIR to choose another location. Preservation is optional; it does not imply full
console-output retention.
Flameox distinguishes observed, derived, and inferred claims. Profiles guide exploration but do not establish causality or performance improvement. Confirmatory claims require representative workloads, declared metrics and estimands, compatible identities, preserved samples, and a semantic oracle.
MCP
The MCP server has no workspace binding. It exposes named analysis and capture tools through the
same capability registry as the CLI. Analysis tools accept explicit sources; capture tools accept
a typed target and provider. Tool schemas expose capability-specific fields directly. Inspect the
catalog with flameox mcp inspect; use --capability CAPABILITY_ID or --tool TOOL_NAME for
focused schemas and examples. The complete contract and current tool catalog are in
the interface guide.
Capture takes argv, not a shell string. A direct target supplies an absolute working directory and
bounded environment overrides. Results may include next_page; replay its named analysis tool
and arguments unchanged. Capture continuations read collected artifacts and do not rerun the
target. MCP work belongs to the live request, so cancellation applies directly and no detached job
survives a restart.
Documentation
From the project's README.