morluto / flameox
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
Why this job: topics: mcp-server, model-context-protocol, mcp
What it does
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.
Get started
npx flameox@latest setup- Maintenance
- Active
- Last commit 29 days ago
- Stars
- 234
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.2.6
- Released 2 months ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 100% closed
- 1 still open
- Pull requests
- 99 merged
- 1 waiting
- Releases
- 17
- 17 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| dx-corp / deep-code-reasoning-mcp | 109 | 26 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- JavaScript <1%
Topics
- benchmarking
- coding-agents
- debugging
- local-first
- mcp
- performance
- profiling
- python
- runtime-analysis
- developer-tools
- gpu-profiling
- mcp-server
Project record
- JobMCP servers
- StatusListed
- Commits523
- Forks29
- Watching2
- Stars in 28 days+51
- CreatedJul 25, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026